A safety detection method and device for a crane, a storage medium and an electronic device

Abstract

The application discloses a kind of crane safety detection method, device, storage medium and electronic equipment, involve crane safety technical field.The application obtains the carrier picture of preset crane;Identify the carrier feature in carrier picture, determine the carrier state of preset crane, wherein, carrier state is at least include working state, load state and move car state;From a plurality of preset detection items, determine the target detection item corresponding to carrier state, at least one preset detection item is preconfigured for each carrier state, preset detection item corresponds at least one preset detection picture, preset detection item is used to carry out safety detection to preset crane according to at least one preset detection picture;In the case where target detection item does not pass safety detection, generate preset alarm information.Thereby, the technical effect that safety detection is automatically carried out to crane according to the working state of crane is realized, and then the technical problem that crane safety detection cannot be realized according to the state of crane is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of crane safety, and more particularly to a safety detection method and device for a crane, a storage medium and an electronic device. BACKGROUND

[0002] In the industrial production process, production safety is crucial. The traditional management is realized by the management personnel guiding in the management field, and the quality and state of the managers themselves affect the final management effect, and cannot effectively reduce the frequency of accidents, especially the hoisting operation and other high-risk operations need to be supervised in all directions, in real time and accurately.

[0003] However, the management personnel cannot continuously manage the operation site in the operation site, and can only supervise some key places, so that in other operation sites, supervision cannot be in place, and it is impossible to supervise the operation process in all directions, in real time and accurately, which will increase the accident rate.

[0004] For example, the invention patent application with the publication number CN116129346A, the publication date of May 16, 2023, and the name of "Safety monitoring system and method for worker approaching lotus crane based on monocular camera" needs manual observation and experience to determine the rotation center of the crane and the height of the crane, and to mark, and the monitoring system needs personnel to pay attention at all times. Manual observation and experience to determine the rotation center of the crane and the height of the crane, there are human uncertain factors, which will lead to large detection result error. SUMMARY

[0005] In order to overcome the defects and deficiencies existing in the prior art, the present application provides a safety detection method and device for a crane, a storage medium and an electronic device, the present application aims to automatically recognize the existence of material hazards and unsafe behaviors of personnel in the operation process by real-time calculation and analysis of the video monitoring picture of the crane hoisting operation area, intelligently, accurately and efficiently, automatically recognize the related unsafe behaviors, and at the same time, timely voice alarm prompt is given to the on-site operation personnel, and the related alarm video and alarm record are automatically stored, and the occurrence of unsafe behaviors is timely and effectively stopped. The present application realizes the technical effect of automatically detecting the safety of the crane according to the working state of the crane, and further solves the problem that the safety detection of the crane cannot be realized according to the state of the crane.

[0006] In order to solve the problems existing in the prior art, the present application is realized by the following technical scheme.

[0007] The first aspect of the present application provides a safety detection method for a crane, which comprises the following steps:

[0008] S1, acquire at least one carrier picture of a preset crane;

[0009] S2, identify a carrier feature in at least one of the carrier pictures, and determine a carrier state of the preset crane; the carrier state at least includes a working state, a load state, and a moving state;

[0010] S3, determine a target detection item corresponding to the carrier state from a plurality of preset detection items; each carrier state is pre-configured with at least one preset detection item, the preset detection item corresponds to at least one preset detection picture, and the preset detection item is used for safety detection of the preset crane according to at least one preset detection picture;

[0011] S4, generate a preset alarm information in the case that the target detection item fails to pass the safety detection.

[0012] Further preferably, in the S2 step, the carrier picture includes any one or a combination of internal perspective picture, top perspective picture, peripheral perspective picture, and driver perspective picture; the internal perspective picture is a driver cabin image of the preset crane; the top perspective picture is an image of a region between a carrier hook of the preset crane and the ground collected at the top of the preset crane; and the peripheral perspective picture is an image of the preset crane collected in a third person perspective.

[0013] More preferably, the carrier feature in the top perspective picture at least includes the carrier hook of the preset crane.

[0014] More preferably, the carrier feature in the peripheral perspective picture at least includes the preset crane, a carrier outrigger of the preset crane, the carrier hook, and / or a carrier wheel.

[0015] More preferably, in the case that the carrier outrigger is identified in the peripheral perspective picture, it is detected whether there is a human image in the top perspective picture; and in the case that there is a human image in the top perspective picture, it is determined that the carrier state of the preset crane is the working state.

[0016] More preferably, in the case that the carrier hook and the hoisted object are identified to have a physical connection in the top perspective picture, and the position of the carrier hook is detected to change in the peripheral perspective picture, it is determined that the carrier state of the preset crane is the load state.

[0017] More preferably, in the case that the carrier hook and the hoisted object are identified to have a physical connection in the top perspective picture, and the picture rotation is detected in the driver perspective picture, it is determined that the carrier state of the preset crane is the load state.

[0018] Further preferably, in the case where the variation range of the intersection ratio between the preset crane and the carrier wheels in the peripheral view picture is within a preset range within a first preset time range, the carrier state is determined as the moving state.

[0019] Further preferably, in the S3 step, the target detection item corresponding to the carrier state is determined from a plurality of preset detection items, specifically,

[0020] In the case where the preset crane is in the working state, the preset detection picture corresponding to the target detection item includes a driver view picture and a peripheral view picture, and it is detected whether the first preset object exists in the driver view picture and the peripheral view picture. In the case where it is detected that the first preset object does not exist in the driver view picture and the peripheral view picture, it is determined that the target detection item fails the safety detection.

[0021] Further preferably, the first preset object wears a command identification.

[0022] Further preferably, in the S3 step, the target detection item corresponding to the carrier state is determined from a plurality of preset detection items, specifically,

[0023] In the case where the preset crane is in the working state, the preset detection picture corresponding to the target detection item includes a driver view picture and a peripheral view picture, and it is detected whether the second preset object exists in the driver view picture and the peripheral view picture. In the case where it is detected that the second preset object does not exist in the driver view picture and the peripheral view picture, it is determined that the target detection item fails the safety detection.

[0024] Further preferably, the second preset object simultaneously has a first monitoring identification and a second monitoring identification.

[0025] Further preferably, in the S3 step, the target detection item corresponding to the carrier state is determined from a plurality of preset detection items, specifically,

[0026] In the case where the preset crane is in the working state, the preset detection picture corresponding to the target detection item includes an internal view picture and a peripheral view picture, and it is detected whether the target object exists in the internal view picture. In the case where the target object does not exist in the internal view picture, it is detected whether the target object with a third preset identification on the head exists in the peripheral view picture. In the case where the target object does not exist in the internal view picture and the target object with the third preset identification on the head does not exist in the peripheral view picture, it is determined that the target detection item fails the safety detection.

[0027] Further preferably, the target object represents an image of a driver of the preset crane, and the third preset identifier represents a safety helmet worn by the driver.

[0028] Further preferably, in the S3 step, the target detection item corresponding to the state of the carrier is determined from a plurality of preset detection items, specifically,

[0029] In the case where the preset crane is in the working state, the preset detection picture corresponding to the target detection item includes a top-view picture, whether a human image exists in a first preset alert area of the top-view picture is detected, and in the case where the human image exists in the first preset alert area is detected, it is determined that the target detection item fails the safety detection.

[0030] Further preferably, the first preset alert area is a region in the top-view picture where a carrier boom of the preset crane has a falling risk and is pre-labeled.

[0031] Further preferably, in the S3 step, the target detection item corresponding to the state of the carrier is determined from a plurality of preset detection items, specifically,

[0032] In the case where the preset crane is in the working state, the preset detection picture corresponding to the target detection item includes a peripheral-view picture, whether a position change amount of a carrier outrigger of the preset crane and a corresponding pad within a second preset time range is consistent is detected, and in the case where the position change amount of the carrier outrigger and the corresponding pad within the second preset time range is inconsistent is detected, it is determined that the target detection item fails the safety detection.

[0033] Further preferably, the preset crane includes a plurality of carrier outriggers, each of which is pre-configured with a corresponding pad, and the corresponding relationship between the carrier outrigger and the pad is determined according to a distance between the carrier outrigger and the pad in the peripheral-view picture.

[0034] Further preferably, in the S3 step, the target detection item corresponding to the state of the carrier is determined from a plurality of preset detection items, specifically,

[0035] In a case where the preset crane is in the working state, the preset detection picture corresponding to the target detection item includes a driver perspective picture and a peripheral perspective picture, whether the driver perspective picture appears picture rotation is detected, and in a case where the driver perspective picture appears picture rotation, whether a change ratio of a boom node of the preset crane in the peripheral perspective picture exceeds a first preset ratio threshold is detected, in a case where the driver perspective picture appears picture rotation and the change ratio of the boom node exceeds the first preset ratio threshold, it is determined that the target detection item fails to pass the safety detection.

[0036] Further preferably, in the S3 step, the target detection item corresponding to the carrier state is determined from a plurality of preset detection items, specifically,

[0037] In a case where the preset crane enters the load state from the moving state, the preset detection picture corresponding to the target detection item includes a peripheral perspective picture, whether the peripheral perspective picture has a target warning mark is detected, and in a case where the peripheral perspective picture has the target warning mark, it is determined that the target detection item passes the safety detection.

[0038] Further preferably, in the S3 step, the target detection item corresponding to the carrier state is determined from a plurality of preset detection items, specifically,

[0039] In a case where the preset crane enters the load state from the moving state, the preset detection picture corresponding to the target detection item includes a peripheral perspective picture and a top perspective picture, whether the peripheral perspective picture and the top perspective picture have a base plate is detected, and in a case where the peripheral perspective picture or the top perspective picture has the base plate, it is determined that the target detection item passes the safety detection.

[0040] Further preferably, in the S3 step, the target detection item corresponding to the carrier state is determined from a plurality of preset detection items, specifically,

[0041] In a case where the preset crane is in the load state, the preset detection picture corresponding to the target detection item includes a cab perspective picture, whether a target object in the cab perspective picture has a target behavior is detected, and in a case where the target object has the target behavior, it is determined that the target detection item fails to pass the safety detection.

[0042] Further preferably, in the S3 step, the target detection item corresponding to the carrier state is determined from a plurality of preset detection items, specifically,

[0043] In a case where the preset crane is in the load state, the preset detection picture corresponding to the target detection item is determined as a cab view picture; and whether a target object exists in the cab view picture is detected, and in a case where the cab view picture does not exist, it is determined that the target detection item fails to pass the safety detection.

[0044] Further preferably, in the S3 step, the target detection item corresponding to the carrier state is determined from a plurality of preset detection items, specifically,

[0045] In a case where the preset crane is in the load state, the preset detection picture corresponding to the target detection item is determined as a top view picture, whether a human image exists in a second preset warning area of the top view picture is detected, and in a case where the human image exists in the second preset warning area, it is determined that the target detection item fails to pass the safety detection.

[0046] Further preferably, the second preset warning area is an area in which the carrier hook of the preset crane or the hoisted object in the top view picture has a falling risk.

[0047] Further preferably, in the S3 step, the target detection item corresponding to the carrier state is determined from a plurality of preset detection items, specifically,

[0048] In a case where the preset crane is in the load state, the preset detection picture corresponding to the target detection item is determined as a peripheral view picture, whether a change ratio of a boom node of the preset crane in the peripheral view picture exceeds a second preset ratio threshold is detected, and in a case where the change ratio of the boom node exceeds the second preset ratio threshold, it is determined that the target detection item fails to pass the safety detection.

[0049] Further preferably, in the S3 step, the target detection item corresponding to the carrier state is determined from a plurality of preset detection items, specifically,

[0050] In a case where the preset crane is in the load state, the preset detection picture corresponding to the target detection item is determined as a peripheral view picture, whether sling equipment exists in a large hook and a small hook of the preset crane in the peripheral view picture is detected, and in a case where the sling equipment exists in the large hook and the small hook of the preset crane, it is determined that the target detection item fails to pass the safety detection.

[0051] Further preferably, in the S3 step, the target detection item corresponding to the carrier state is determined from a plurality of preset detection items, specifically,

[0052] In a case where the preset crane is in the load state, the preset detection picture corresponding to the target detection item comprises a peripheral view picture, and the indicator light of the preset crane in the peripheral view picture is detected, and in a case where the indicator light indicates overload, it is determined that the target detection item fails to pass the safety detection.

[0053] Further preferably, in the S3 step, from a plurality of preset detection items, the target detection item corresponding to the carrier state is determined, specifically,

[0054] In a case where the preset crane is in the load state, the preset detection picture corresponding to the target detection item comprises a peripheral view picture, and the indicator light of the preset crane in the peripheral view picture is detected, and in a case where the indicator light indicates overload, it is determined that the target detection item fails to pass the safety detection.

[0055] The second aspect of the present application provides a safety detection device of a crane, which comprises

[0056] The acquisition module is configured to acquire at least one carrier picture of a preset crane.

[0057] The identification module is configured to identify a carrier feature in at least one of the carrier pictures, and determine a carrier state of the preset crane, wherein the carrier state comprises at least a working state, a load state and a moving state.

[0058] The determination module is configured to determine, from a plurality of preset detection items, a target detection item corresponding to the carrier state, wherein each carrier state is pre-configured with at least one preset detection item, the preset detection item corresponds to at least one preset detection picture, and the preset detection item is used for safety detection of the preset crane according to at least one preset detection picture.

[0059] The generation module is configured to generate preset alarm information in a case where the target detection item fails to pass the safety detection.

[0060] The third aspect of the present application provides a readable storage medium for storing a program, wherein the readable storage medium is controlled to execute the safety detection method of the crane according to the first aspect of the present application when the program is executed.

[0061] The fourth aspect of the present application provides an electronic device comprising a memory and a processor, wherein the processor is configured to execute a program stored in the processor, and the program is executed to execute the safety detection method of the crane according to the first aspect of the present application.

[0062] In the embodiment of the present application, at least one carrier picture of a preset crane is acquired; a carrier feature in the at least one carrier picture is recognized to determine a carrier state of the preset crane, wherein the carrier state at least includes a working state, a load state and a moving state; from a plurality of preset detection items, a target detection item corresponding to the carrier state is determined, wherein each carrier state is pre-configured with at least one preset detection item, the preset detection item corresponds to at least one preset detection picture, and the preset detection item is used for safety detection of the preset crane according to the at least one preset detection picture; in the case that the target detection item fails to pass the safety detection, preset alarm information is generated, thereby realizing the technical effect of automatically performing safety detection on the crane according to the working state of the crane, and further solving the technical problem that the crane safety detection cannot be realized according to the crane state.

[0063] Compared with the prior art, the beneficial technical effects brought by the present application are as follows:

[0064] 1. According to the working state of the crane, intelligent, accurate and comprehensive automatic safety detection of the crane operation process is realized.

[0065] 2. Real-time intelligent identification and alarm prompt of the crane operation process are realized, the current situation of relying on a large amount of manpower and material resources for risk control is improved, the intelligent level of risk control in the operation site is improved, and the change of safety supervision mode from manual to intelligent is promoted. BRIEF DESCRIPTION OF DRAWINGS

[0066] Figure 1 is a flowchart of a safety detection method of a crane according to an embodiment of the present application;

[0067] Figure 2 is a schematic diagram of an optional intelligent identification system according to an embodiment of the present application;

[0068] Figure 3 is a schematic diagram of a safety detection device of a crane according to an embodiment of the present application;

[0069] Figure 4 is a structural block diagram of a computer terminal according to an embodiment of the present application. DETAILED DESCRIPTION

[0070] In order for those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0071] It is to be understood that the terms "first", "second", and the like, used in the description and the claims of the application as well as the above description of the drawings merely specify a certain order, and cannot be understood as implying a specific order or chronology. It is to be understood that the data thus designated can be interchanged, where appropriate, so that the embodiments of the application described herein can be carried out in an order other than that illustrated or described herein. Furthermore, the terms "comprise" and "have" and any variations thereof, are intended to cover non-exclusive inclusion, for example, processes, methods, systems, products, or devices that include a list of steps or units not necessarily limited to those explicitly listed, but can include other steps or units not expressly listed or inherent to such processes, methods, products, or devices.

[0072] According to an embodiment of the application, a safety detection method for a crane is provided. It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described herein can be executed in an order different from that shown herein.

[0073] Embodiment 1

[0074] As a preferred embodiment of the application, reference is made to the drawings accompanying the description Figure 1 , Figure 1 is a flowchart of a safety detection method for a crane according to an embodiment of the application, the method comprising the following steps:

[0075] Step S1, obtaining at least one carrier picture of a preset crane;

[0076] Step S2, identifying the carrier features in the at least one carrier picture to determine the carrier state of the preset crane, wherein the carrier state comprises at least: working state, load state and moving state;

[0077] Step S3, determining the target detection item corresponding to the carrier state from a plurality of preset detection items, wherein each carrier state is pre-configured with at least one preset detection item, the preset detection item corresponds to at least one preset detection picture, and the preset detection item is used for safety detection of the preset crane according to the at least one preset detection picture;

[0078] Step S4, generating a preset alarm information in the case that the target detection item fails to pass the safety detection.

[0079] In the embodiment of the present application, at least one carrier picture of a preset crane is acquired; a carrier feature in the at least one carrier picture is recognized to determine a carrier state of the preset crane, wherein the carrier state at least includes a working state, a load state and a moving state; from a plurality of preset detection items, a target detection item corresponding to the carrier state is determined, wherein each carrier state is pre-configured with at least one preset detection item, the preset detection item corresponds to at least one preset detection picture, and the preset detection item is used for safety detection of the preset crane according to the at least one preset detection picture; in the case that the target detection item fails to pass the safety detection, preset alarm information is generated, thereby achieving the technical effect of automatically performing safety detection on the crane according to the working state of the crane, and further solving the technical problem that the crane safety detection cannot be realized according to the crane state.

[0080] Embodiment 2

[0081] As another preferred embodiment of the present application, the embodiment is a further detailed elaboration and supplement to the technical solution of the present application based on the above-mentioned embodiment 1. In the embodiment, in the step S2, the carrier picture includes any one or a combination of multiple of an internal perspective picture, a top perspective picture, a peripheral perspective picture and a driver perspective picture; the internal perspective picture is a driver cabin image of the preset crane; the top perspective picture is an image of a region between a carrier hook of the preset crane and the ground collected at the top of the preset crane; the peripheral perspective picture is an image of the preset crane collected in a third-person perspective; and the driver perspective picture is a perspective image of a driver in the driver cabin.

[0082] In the above-mentioned step S3, the preset detection picture includes an internal perspective picture, a top perspective picture, a driver perspective picture and a peripheral perspective picture.

[0083] As an example, the top perspective picture is collected by a camera arranged at the top end of a carrier boom of the preset crane, and the camera is located on the same vertical line as the carrier hook.

[0084] In the above-mentioned step S2, the carrier feature includes a carrier hook, a carrier support leg, a carrier boom and a carrier wheel of the preset crane.

[0085] In the above-mentioned step S2, the carrier state at least includes a working state, a load state and a moving state, and the safety detection judgment criteria of the preset crane in different carrier states are different.

[0086] For example, the preset crane can retract a hoisting accessory to move, can deploy in a designated work area, and can carry a load to hoist after the preset crane is deployed.

[0087] Optionally, the working state is used to indicate that the preset crane has reached the work area for unfolding and is ready for subsequent lifting, wherein the most prominent feature of the working state is that the outriggers of the preset crane are unfolded to increase the stability of lifting, and the working state of the preset crane can be determined according to the outriggers of the carrier of the preset crane, and thus the carrier feature used to determine the working state is the outriggers of the carrier.

[0088] Optionally, the load state indicates that the preset crane has reached the work area for unfolding and that the carrier hook of the preset crane is physically connected to the hoisted object, and thus on the basis that the preset crane has reached the unfolding state, whether the preset crane is in the load state can be determined according to whether the carrier hook of the preset crane is physically connected to the hoisted object, and thus the carrier feature used to determine the load state is the connection relationship between the carrier hook and the hoisted object.

[0089] Optionally, the moving state is used to indicate that the preset crane is moving by the carrier wheels, and thus in the moving state, the outriggers of the preset crane are necessarily retracted, and the state of the carrier wheels will change, and thus on the basis that the preset crane is not in the unfolding state, whether the preset crane is in the moving state can be determined according to the carrier wheels of the preset crane, and thus the carrier feature used to determine the moving state is the feature of the carrier wheels, such as the change of the carrier wheels or the change of the overlap ratio of the carrier wheels and the preset crane.

[0090] In the above step S3, different carrier states correspond to different preset detection items, at least one preset detection item is selected according to the carrier state, and each target detection item can be detected, so as to realize accurate safety detection of the preset crane, and thus the work safety of the preset crane is ensured.

[0091] For example, in the case that the preset crane is in the working state, the preset crane is allowed to adjust the length of the carrier boom after unfolding the outriggers of the carrier, and in the case that the preset crane is in the load state, the preset crane is not allowed to adjust the length of the carrier boom, and thus the safety detection criteria of the preset crane are different in different carrier states, and thus different preset detection items can be selected for safety detection of the preset crane according to the carrier state of the preset crane.

[0092] Optionally, in the case of obtaining the peripheral view picture of the preset crane, obtaining at least one carrier picture of the preset crane includes: obtaining a first preset work picture, wherein the first preset work picture includes a plurality of work areas of the preset crane; performing image segmentation on the work picture to obtain a plurality of preset segmentation areas; and identifying a preset segmentation area including the preset crane as a peripheral view picture of the preset crane.

[0093] According to the above embodiment of the present application, the first preset work picture comprises a plurality of work areas of the preset crane, each work area allows the preset crane to spread in the work area to carry out hoisting, but the plurality of work areas do not necessarily have the preset crane to work, therefore, the work area where the preset crane exists can be intercepted in the first preset work picture to determine the peripheral view picture, so as to realize the determination of the peripheral view picture.

[0094] Optionally, in the case of acquiring the peripheral view picture of the preset crane, acquiring the at least one carrier picture of the preset crane comprises: acquiring at least one second preset work picture, wherein each second preset work picture corresponds to a work area, and the preset crane is allowed to spread in the work area; and identifying the preset work picture where the preset crane exists as the peripheral view picture of the preset crane.

[0095] According to the above embodiment of the present application, the picture of each work area is acquired as the second preset work picture, each work area allows the preset crane to spread in the work area to carry out hoisting, but the plurality of work areas do not necessarily have the preset crane to work, therefore, the second preset work picture where the preset crane exists can be selected from the plurality of second preset work pictures as the peripheral view picture of the preset crane, so as to realize the determination of the peripheral view picture.

[0096] As an optional embodiment, the carrier feature in the at least one carrier picture is identified to determine the carrier state of the preset crane, comprising: identifying a top view picture and a peripheral view picture in the at least one carrier picture, wherein the top view picture is an image of a region between the carrier hook of the preset crane and the ground collected at the top of the preset crane, and the peripheral view picture is an image of the preset crane collected in the third person view; identifying the carrier feature in the peripheral view picture, wherein the carrier feature at least comprises: the carrier support leg of the preset crane; in the case of identifying the carrier support leg in the peripheral view picture, detecting whether there is a human image in the top view picture; and in the case of there being a human image in the top view picture, determining that the carrier state of the preset crane is the working state.

[0097] According to the above embodiment of the present application, in the case that the carrier state is in the working state, the most prominent feature is that the support leg of the preset crane is spread to increase the stability of hoisting, therefore, the working state of the preset crane can be determined according to the carrier support leg of the preset crane, and then the carrier support leg of the preset crane is identified through the peripheral view picture and the top view picture, if the carrier support leg of the preset crane is identified, it is indicated that the carrier support leg of the preset crane has been spread, so that it can be determined that the preset crane is in the working state.

[0098] As an optional embodiment, the identifying the carrier feature in the at least one carrier picture and determining the carrier state of the preset crane comprises: identifying a top view picture and a peripheral view picture in the at least one carrier picture, wherein the top view picture is an image of a region between a carrier hook of the preset crane and the ground collected at the top of the preset crane, and the peripheral view picture is an image of the preset crane collected in a third-person view; identifying the carrier feature in the top view picture and the peripheral view picture, wherein the carrier feature at least comprises the carrier hook of the preset crane; and in a case where the carrier hook is identified to have a physical connection with the hoisted object in the top view picture and the position of the carrier hook is detected to change in the peripheral view picture, determining that the carrier state of the preset crane is the load state.

[0099] In the above embodiment of the present application, when the preset crane is in the load state, the preset crane carries the weight of the hoisted object to move the hoisted object, and the preset crane needs to have a physical connection with the carrier hook of the preset crane to carry the weight of the hoisted object. During the movement of the hoisted object, the carrier hook also moves with the hoisted object. Therefore, by detecting the connection relationship between the carrier hook of the preset crane and the hoisted object and the movement of the carrier hook, it can be determined whether the preset crane is in the load state.

[0100] Optionally, the change in the position of the carrier hook comprises: up-and-down movement of the carrier hook relative to the ground, swinging of the carrier hook, and rotation of the carrier hook relative to the center of rotation of the preset crane.

[0101] Optionally, in a case where the carrier hook swings or rotates relative to the center of rotation of the preset crane, the hoisted object connected with the carrier hook moves left and right in the peripheral view picture.

[0102] As an optional embodiment, the identifying the carrier feature in the at least one carrier picture and determining the carrier state of the preset crane comprises: identifying a top view picture and a driver view picture in the at least one carrier picture, wherein the top view picture is an image of a region between a carrier hook of the preset crane and the ground collected at the top of the preset crane; identifying the carrier feature in the top view picture, wherein the carrier feature at least comprises the carrier hook of the preset crane; and in a case where the carrier hook is identified to have a physical connection with the hoisted object in the top view picture and the picture is detected to rotate in the driver view picture, determining that the carrier state of the preset crane is the load state.

[0103] The above embodiment of the present application, the preset crane in the load state, the preset crane will bear the weight of the hoist, so that the hoist moves, and the preset crane needs to be physically connected with the carrier hook of the preset crane to bear the weight of the hoist, in the process of moving the hoist, the carrier hook also moves with the hoist, and in the case of rotating the carrier boom of the preset crane, the hoist connected with the carrier hook can also move, and the driver's view picture will appear picture rotation, therefore, by detecting the connection relationship between the carrier hook of the preset crane and the hoist, and whether the picture of the driver's view picture is rotated, whether the preset crane is in the load state can be determined.

[0104] Optionally, in the top view picture, whether there is a hoist between the hook and the ground can be identified, if there is no hoist, it indicates that there is no physical connection between the hoist and the carrier hook; if there is a hoist, the connecting piece (such as a hoist sling) between the hoist and the carrier hook is detected in the hook picture, if the connecting piece is not detected, it indicates that there is no physical connection between the hoist and the carrier hook, otherwise it can be determined that there is a physical connection between the hoist and the carrier hook.

[0105] As an optional embodiment, the method for identifying the carrier feature in at least one carrier picture and determining the carrier state of the preset crane comprises: identifying a peripheral view picture in the at least one carrier picture, wherein the peripheral view picture is an image of the preset crane collected in a third person view; identifying the carrier feature in the peripheral view picture, wherein the carrier feature at least comprises: the preset crane and the carrier wheels of the preset crane; and determining that the carrier state is a moving state in the case that the variation range of the intersection and union ratio of the preset crane and the carrier wheels in the peripheral view picture within a first preset time range is within a preset range.

[0106] In the above embodiment of the present application, in the case that the variation range of the intersection and union ratio of the preset crane and the carrier wheels in the peripheral view picture within a first preset time range is within a preset range, the carrier state is determined to be a moving state, which comprises: collecting a first time sequence picture of the peripheral view picture, and identifying the preset crane and the carrier wheels of the preset crane in the first time sequence picture; collecting the peripheral view picture of the preset crane according to a preset time interval to obtain a second time sequence picture; identifying the preset crane and the carrier wheels of the preset crane in the second time sequence picture; and determining that the carrier state is a moving state in the case that the variation range of the intersection and union ratio of the preset crane and the carrier wheels in the first time sequence picture and the second time sequence picture is within a preset range, which realizes the determination of the moving state.

[0107] Optionally, the preset time interval is one frame.

[0108] Optionally, in the case that the preset crane is in the moving state, the preset crane can move through the carrier wheels, for example, the preset crane can move from the first working area to the second working area, and during the movement of the preset crane, the carrier boom and the carrier outrigger of the preset crane must be retracted, and the carrier outrigger of the preset crane needs to be opened first when the preset crane is deployed, and the carrier outrigger of the preset crane is retracted last when the preset crane is retracted, therefore, in the case that the carrier outrigger of the preset crane is not detected, it is indicated that the preset crane has a high probability of being in the moving state, and then the features of the carrier wheels of the preset crane can be extracted, and whether the preset crane is in the moving state can be determined according to the feature change of the carrier wheels.

[0109] Optionally, the intersection over union (IOU) is a concept used in target detection, and the IOU calculates the intersection rate of the “predicted bounding box” and the “real bounding box”, that is, the ratio of their intersection and union. Through the peripheral view pictures collected at different times by fixing the position, if the preset crane moves, the intersection over union of the preset crane and the carrier wheels at different times will change, and then whether the preset crane is in the moving state can be determined according to the change of the intersection over union of the carrier wheels and the preset crane at different times, wherein the intersection over union of the carrier wheels and the preset crane at different times can be determined according to the plurality of carrier pictures in the time sequence.

[0110] As an optional embodiment, from the plurality of preset detection items, the target detection item corresponding to the carrier state includes: in the case that the preset crane is in the working state, the preset detection picture corresponding to the target detection item includes: the driver view picture and the peripheral view picture, wherein the peripheral view picture is an image of the preset crane collected in the third person view; and whether the first preset object exists in the driver view picture is detected, wherein the first preset object wears a command mark, and in the case that the first preset object exists in the driver view picture and the peripheral view picture, it is determined that the target detection item passes the safety detection.

[0111] In the above embodiments of the present application, during the crane operation, a commander needs to be configured for the preset crane, and it is necessary to ensure that the commander is in the driver's field of view of the preset crane, therefore, by detecting whether the first preset object wearing the command mark exists in the driver view picture and the peripheral view picture, the detection of whether the preset crane is configured with the commander can be realized, and then in the case that the first preset object wearing the command mark does not exist in the driver view picture and the peripheral view picture, it is determined that the preset crane is not configured with the commander, and then it is determined that the target crane does not pass the safety detection of the target detection item.

[0112] Optionally, the first preset object is the commander, and the command mark is a modification table worn by the commander or a warning symbol worn by the commander.

[0113] As an optional embodiment, from the plurality of preset detection items, determining the target detection item corresponding to the carrier state comprises: in the case that the preset crane is in the working state, determining that the target detection item corresponds to the preset detection picture comprising: the driver's view picture and the peripheral view picture, wherein the peripheral view picture is an image of the preset crane collected in the third person view; detecting whether the second preset object exists in the driver's view picture and the peripheral view picture, wherein the second preset object has the first guardian mark and the second guardian mark at the same time, and in the case that the second preset object does not exist in the driver's view picture and the peripheral view picture, it is determined that the target detection item does not pass the safety detection.

[0114] In the above embodiment of the present application, during the crane operation process, a guardian needs to be configured for the preset crane, and it is necessary to ensure that the guardian is in the driver's field of view of the preset crane. Therefore, by detecting whether the second preset object having the first guardian mark and the second guardian mark at the same time exists in the driver's view picture and the peripheral view picture, the detection of whether the guardian is configured for the preset crane can be realized, and further, in the case that the second preset object does not exist in the driver's view picture and the peripheral view picture, it is determined that the guardian is not configured for the preset crane, and further, it is determined that the target crane does not pass the safety detection of the target detection item.

[0115] Optionally, the second preset object is a guardian, the first guardian mark can be a safety helmet worn by the guardian, such as a white safety helmet, and the second guardian mark can be a guardian sleeve mark worn by the guardian, and the guardian needs to wear the safety helmet and the guardian sleeve mark at the same time.

[0116] As an optional embodiment, from the plurality of preset detection items, determining the target detection item corresponding to the carrier state comprises: in the case that the preset crane is in the working state, determining that the target detection item corresponds to the preset detection picture comprising: the internal view picture and the peripheral view picture, wherein the peripheral view picture is an image of the preset crane collected in the third person view; detecting whether the target object exists in the internal view picture, and in the case that the target object does not exist in the internal view picture, detecting whether the target object with the third preset mark on the head exists in the peripheral view picture, wherein the target object represents the image of the driver of the preset crane, and the third preset mark represents the safety helmet worn by the driver, and in the case that the target object does not exist in the internal view picture, and the target object with the third preset mark on the head does not exist in the peripheral view picture, it is determined that the target detection item does not pass the safety detection.

[0117] In the above embodiment of the present application, when the preset crane is in the working state, the driver of the preset crane may need to leave the cab, but in order to ensure the safety of the driver, the driver needs to wear a safety helmet when leaving the cab. Therefore, when the preset crane is in the working state, whether the driver is in the cab can be detected through the cab view picture, and whether the driver wears a safety helmet when leaving the cab can be detected through the peripheral view picture when it is detected that the driver is not in the cab.

[0118] As an optional embodiment, from the plurality of preset detection items, the target detection item corresponding to the carrier state is determined, including: when the preset crane is in the working state, the target detection item corresponding to the preset detection picture is determined, including: a top view picture, wherein the top view picture is an image of a region between a carrier hook of the preset crane and the ground collected at the top of the preset crane; whether there is a human image in a first preset warning area of the top view picture is detected, wherein the first preset warning area is a region in the top view picture where the carrier boom of the preset crane has a falling risk, and when it is detected that there is a human image in the first preset warning area, it is determined that the target detection item fails the safety detection.

[0119] In the above embodiment of the present application, when the preset crane is in the working state, the carrier boom of the preset crane will be adjusted. In order to avoid falling risk during the adjustment of the carrier boom, whether personnel enter a first preset warning area projected by the carrier boom can be detected through the top view picture.

[0120] Optionally, the first preset warning area is determined according to a projection area of the projection area of the carrier boom on the ground. When the projection area of the carrier boom on the ground is recognized in the top view picture, a warning line is set according to a preset distance, and the area surrounded by the warning line is the first preset warning area.

[0121] As an optional embodiment, from the plurality of preset detection items, the target detection item corresponding to the carrier state is determined, including: when the preset crane is in the working state, the target detection item corresponding to the preset detection picture is determined, including: a peripheral view picture, wherein the peripheral view picture is an image of the preset crane collected in a third-person perspective; whether a position change amount of a carrier support leg of the preset crane and a corresponding pad within a second preset time range is consistent is detected in the peripheral view picture, wherein the preset crane includes a plurality of carrier support legs, each carrier support leg is pre-configured with a corresponding pad, the correspondence between the carrier support leg and the pad is determined according to the distance between the carrier support leg and the pad in the peripheral view picture, and when it is detected that the position change amount of the carrier support leg and the corresponding pad within the second preset time range is inconsistent, it is determined that the target detection item fails the safety detection.

[0122] In the above embodiment of the present application, the carrier leg and the pad need to be bound by the steel wire rope in the case that the preset crane is in the working state. If the position change amounts of the carrier leg and the corresponding pad in the second preset time range are inconsistent, it is indicated that the carrier leg and the pad are not bound by the steel wire rope.

[0123] Optionally, the second preset time can be the state determination of the preset crane returning from the load state to the working state.

[0124] As an optional embodiment, from the plurality of preset detection items, determining the target detection item corresponding to the carrier state includes: in the case that the preset crane is in the working state, determining that the preset detection picture corresponding to the target detection item includes: the driver's perspective picture and the peripheral perspective picture, wherein the peripheral perspective picture is an image of the preset crane collected in the third person perspective; detecting whether the driver's perspective picture appears picture rotation, and in the case that the driver's perspective picture appears picture rotation, detecting whether the change proportion of the boom node of the preset crane in the peripheral perspective picture exceeds the first preset proportion threshold, and in the case that the driver's perspective picture appears picture rotation and the change proportion of the boom node exceeds the first preset proportion threshold, determining that the target detection item fails the safety detection.

[0125] In the above embodiment of the present application, in the case that the driver's perspective picture appears picture rotation and the change proportion of the boom node exceeds the first preset proportion threshold, it is indicated that the slewing ring rotates while the telescopic arm is working, and thus, the safety detection requirement is not met.

[0126] As an optional embodiment, from the plurality of preset detection items, determining the target detection item corresponding to the carrier state includes: in the case that the preset crane enters the load state from the moving state, determining that the preset detection picture corresponding to the target detection item includes: the peripheral perspective picture, wherein the peripheral perspective picture is an image of the preset crane collected in the third person perspective; detecting whether the target warning mark exists in the peripheral perspective picture, and in the case that the target warning mark exists in the peripheral perspective picture, determining that the target detection item passes the safety detection.

[0127] In the above embodiment of the present application, after the preset crane moves to the working area, the target warning mark such as the warning tape, the fence, the stake and the like needs to be arranged in the working area, and thus, in the case that the target warning mark exists in the peripheral perspective picture, it is determined that the preset crane meets the safety requirement, and thus, it is determined that the preset crane passes the safety detection of the target detection item.

[0128] As an optional embodiment, from the plurality of preset detection items, determining the target detection item corresponding to the carrier state comprises: in the case that the preset crane enters the load state from the parking state, determining that the preset detection picture corresponding to the target detection item comprises: a peripheral view picture and a top view picture, wherein the peripheral view picture is an image of the preset crane collected in a third-person perspective, and the top view picture is an image of a region between a carrier hook of the preset crane and the ground collected at the top of the preset crane; and detecting whether the peripheral view picture or the top view picture exists a base plate, wherein in the case that it is detected that the peripheral view picture or the top view picture exists the base plate, it is determined that the target detection item passes the safety detection.

[0129] In the above embodiment of the present application, after the preset crane moves to the working area, the base plate needs to be arranged at the supporting leg position of the preset crane, so that in the case that it is detected that the peripheral view picture or the top view picture exists the base plate, it is determined that the base plate has been provided for the preset crane, and further, it is determined that the preset crane passes the safety detection of the target detection item.

[0130] As an optional embodiment, from the plurality of preset detection items, determining the target detection item corresponding to the carrier state comprises: in the case that the preset crane is in the load state, determining that the preset detection picture corresponding to the target detection item comprises: a cab view picture; and detecting whether a target object in the cab view picture exists a target behavior, wherein in the case that it is detected that the target object exists the target behavior, it is determined that the target detection item does not pass the safety detection.

[0131] In the above embodiment of the present application, in the case that the preset crane is in the load state, the target object can be detected to exist the target behavior of violating the safety regulation through the cab view picture, and further, in the case that it is detected that the target object exists the target behavior, it is determined that the preset crane passes the safety detection of the target detection item.

[0132] Optionally, the target behavior can be a behavior of playing a mobile phone by the driver, and if the driver plays the mobile phone in the case that the preset crane is in the load state, the behavior does not conform to the safety operation requirement of the preset crane, and then an alarm information can be generated.

[0133] As an optional embodiment, from the plurality of preset detection items, determining the target detection item corresponding to the carrier state comprises: in the case that the preset crane is in the load state, determining that the preset detection picture corresponding to the target detection item comprises: a cab view picture; and detecting whether a target object exists in the cab view picture, wherein in the case that it is detected that the cab view picture does not exist the target object, it is determined that the target detection item does not pass the safety detection.

[0134] The above embodiment of the present application, in the case that the preset crane is in the load state, does not allow the driver to leave the cab, so that whether the target object is in the cab can be detected through the cab view picture, and further, in the case that the target object is not detected in the cab view picture, it is determined that the preset crane fails to pass the safety detection of the target detection item.

[0135] As an optional embodiment, from the plurality of preset detection items, the target detection item corresponding to the vehicle state is determined, including: in the case that the preset crane is in the load state, the preset detection picture corresponding to the target detection item includes: a top view picture, wherein the top view picture is an image of a region between a vehicle hook of the preset crane and the ground collected at the top of the preset crane; whether a human image exists in a second preset warning area of the top view picture is detected, wherein the second preset warning area is a region in the top view picture where the vehicle hook of the preset crane or the hoisted object has a falling risk, and in the case that the human image exists in the second preset warning area, it is determined that the target detection item fails to pass the safety detection.

[0136] The above embodiment of the present application, in the case that the preset crane is in the load state, in order to avoid the falling risk of the vehicle hook and the hoisted object, whether a person enters the second preset warning area where the vehicle hook and the hoisted object project can be detected through the top view picture.

[0137] Optionally, the second preset warning area is determined according to the projection area of the projection area of the vehicle hook and the hoisted object of the preset crane on the ground, the projection area of the projection area of the vehicle hook and the hoisted object on the ground is recognized in the top view picture, and then a warning line is set according to a preset distance, and the area surrounded by the warning line is the second preset warning area.

[0138] As an optional embodiment, from the plurality of preset detection items, the target detection item corresponding to the vehicle state is determined, including: in the case that the preset crane is in the load state, the preset detection picture corresponding to the target detection item includes: a peripheral view picture, wherein the peripheral view picture is an image of the preset crane collected in the third person view; whether a change ratio of a boom node of the preset crane in the peripheral view picture exceeds a second preset proportion threshold is detected, and in the case that the change ratio of the boom node exceeds the second preset proportion threshold, it is determined that the target detection item fails to pass the safety detection.

[0139] The above embodiment of the present application, in the case that the preset crane is in the load state, in order to avoid the falling risk of the hoisted object and the preset crane, the vehicle boom of the preset crane is not allowed to be adjusted, so that whether the change ratio of the boom node exceeds the second preset proportion threshold can be detected through the peripheral view picture, and whether the preset crane adjusts the vehicle boom in the load state can be determined.

[0140] As an optional embodiment, from the plurality of preset detection items, determining the target detection item corresponding to the carrier state comprises: in the case that the preset crane is in a load state, determining that the preset detection picture corresponding to the target detection item comprises a peripheral view picture, wherein the peripheral view picture is an image of the preset crane collected in a third-person perspective; and detecting whether the large hook and the small hook of the preset crane in the peripheral view picture have a sling, wherein in the case that the large hook and the small hook of the preset crane are detected to have a sling simultaneously, it is determined that the target detection item fails to pass the safety detection.

[0141] In the above embodiment of the present application, in the case that the large hook and the small hook of the preset crane are detected to have a sling simultaneously, it is indicated that the preset crane uses the small hook to hoist in the case that the sling of the large hook is not removed, and it is further determined that the preset crane fails to pass the safety detection of the target detection item.

[0142] As an optional embodiment, from the plurality of preset detection items, determining the target detection item corresponding to the carrier state comprises: in the case that the preset crane is in a load state, determining that the preset detection picture corresponding to the target detection item comprises a peripheral view picture, wherein the peripheral view picture is an image of the preset crane collected in a third-person perspective; and detecting whether the large hook and the small hook of the preset crane in the peripheral view picture have a sling, wherein in the case that the large hook and the small hook of the preset crane are detected to have a sling simultaneously, it is determined that the target detection item fails to pass the safety detection.

[0143] In the above embodiment of the present application, the indicator light is used to indicate whether the preset crane exceeds the working load, and it is further determined that the preset crane fails to pass the safety detection of the target detection item in the case that the indicator light indicates overload.

[0144] As an optional embodiment, from the plurality of preset detection items, determining the target detection item corresponding to the carrier state comprises: in the case that the preset crane is in a load state, determining that the preset detection picture corresponding to the target detection item comprises a peripheral view picture, wherein the peripheral view picture is an image of the preset crane collected in a third-person perspective; and detecting whether the large hook and the small hook of the preset crane in the peripheral view picture have a sling, wherein in the case that the large hook and the small hook of the preset crane are detected to have a sling simultaneously, it is determined that the target detection item fails to pass the safety detection.

[0145] In the above embodiment of the present application, in the case that the preset crane is in a load state, the hook and the sling of the preset crane are avoided from swinging to cause risks in the process of moving the crane, and therefore, whether the carrier hook has a sling can be detected through the peripheral view picture, and it is further determined that the preset crane fails to pass the safety detection of the target detection item in the case that the carrier hook is detected to have a sling.

[0146] Embodiment 3

[0147] As another preferred embodiment of the present application, referring to the accompanying drawings Figure 2 illustrated, the embodiment provides an intelligent identification system. Figure 2 is an optional intelligent identification system schematic diagram according to an embodiment of the present application, as shown Figure 2 by the internal view, top view, driver view and peripheral view, the carrier state determination and safety detection of the crane are realized.

[0148] Optionally, the peripheral view picture can be a third view picture of the preset crane.

[0149] Optionally, the top view picture can be an image of the area between the carrier hook and the ground collected at the top end of the jib of the preset crane.

[0150] Optionally, the internal view picture is used to collect the image of the cab of the preset crane.

[0151] Optionally, the driver view picture is used to collect the view image of the driver in the cab.

[0152] Optionally, the intelligent identification system is used to perform safety detection of the following steps: the crane driver drives the crane to the vicinity of the hoist object to be hoisted, then extends the crane outrigger and places the jack pad under the outrigger; after the outrigger is lowered, the driver enters the crane operation room, extends the jib and lowers the hook; the other workers on site put one end of the hoist sling on the hook and fix the other end of the hoist sling on the hoist object; after fixing the hoist sling, the workers exit the hoisting range, the crane driver raises the hook, operates the crane to hoist the hoist object to the designated location, and workers pull the traction rope to control the direction of the hoist object during hoisting; after the hoist object reaches the space above the designated location, the driver slowly lowers the hook, and when the hoist object approaches the ground, the workers enter the hoisting range to stabilize the direction and position of the hoist object, then the driver slowly lowers the hook until the hoist object is placed on the ground, the workers remove the sling at the end of the hoist object, and the hoisting is completed.

[0153] Optionally, after the hoist object at one position is hoisted, the driver retracts the jib, recovers the outrigger, drives the crane to the next position to be hoisted, and enters the next work flow.

[0154] Optionally, the carrier state at least includes: an unfolded state, a load state and a moving state, wherein the unfolded state is detected by the peripheral view when the outrigger is detected, indicating that the crane has started the unfolded state; the load state is detected by the top view when the hoist object is detected, the driver view detects the rotation of the picture or the peripheral view detects the change of the hook position up and down; the moving state is detected by the peripheral view, which matches the crane and the wheel using IOU; the current and previous frames are considered to be moving within a certain range when the IOU change of one wheel is within a certain range.

[0155] Optionally, in the above step S3, for different vehicle states, the safety detection of the preset crane can be realized through the following multiple preset detection items.

[0156] Optionally, no special person commands, the commander does not wear armband or does not wear warning clothes: in the case that the crane is in the unfolded state, the armband or the warning clothes is not detected in the driver's perspective picture, the preset crane fails to pass the safety detection.

[0157] Optionally, no guardian or guardian does not wear armband: in the case that the crane is in the unfolded state, the white safety helmet and the armband are not detected on the same person in the driver's perspective picture, the preset crane fails to pass the safety detection.

[0158] Optionally, no warning tape / fence / pile is pulled: the crane is moved to a position and enters the load state to start detection, and the detection is stopped when the target is detected.

[0159] Optionally, the driver leaves the operation room without a safety helmet: in the case that the crane is in the unfolded state, no person is detected in the operation room picture (i.e. the internal perspective picture), and the head is detected in the peripheral picture (i.e. the driver without a safety helmet is detected in the peripheral picture), the preset crane fails to pass the safety detection.

[0160] Optionally, the driver uses a mobile phone in the operation room: in the case that the crane is in the load state, the mobile phone is detected in the operation room picture (i.e. the driver plays the mobile phone in the load state), the preset crane fails to pass the safety detection.

[0161] Optionally, unauthorized entry into the warning area: in the case that the crane is in the load state, the top picture marks the danger range and the warning area around the hoist, and when the detection box of the person in the picture intersects with the warning area, it is determined that the person enters the warning area, the preset crane fails to pass the safety detection.

[0162] Optionally, personnel pass under the boom or hoist: in the case that the crane is in the unfolded state, the top picture marks the danger range and the warning area of the boom in the middle of the picture, and when the detection box of the person in the picture intersects with the warning area, it is determined that the person passes under the boom, the preset crane fails to pass the safety detection.

[0163] Optionally, the thousand jin base plate is bound with a steel wire rope on the crane support leg: when the crane enters the unfolded state, the sort tracking algorithm is used to obtain the IDs of the support leg and the base plate in the peripheral picture, and the support leg and the base plate with close positions are matched. When the crane is not in the load state, the positions of the support leg and the base plate in the front and rear frames of the peripheral picture change and the change amounts are consistent, it is considered that the thousand jin base plate is bound with a steel wire rope on the crane support leg.

[0164] Optionally, the hook is hung with a lifting appliance and the vehicle is moved: ResNet18 is used to perform binary classification on the picture around the hook in the peripheral picture, and if the binary classification result is that the lifting appliance is detected and the crane is moving, it is determined that the hook is hung with a lifting appliance and the vehicle is moved (i.e., it is assumed that the crane is moving in the load state).

[0165] Optionally, the crane is not used with a thousand jack plate: the crane is moved to a position and enters the load state to start detection, and the detection is closed until the jack plate is detected.

[0166] Optionally, the crane is in a load state, and the change in the position of the node on the boom is calculated, and if the change ratio reaches a certain threshold, it is determined that the crane is in a load state and the boom is extended, and it is assumed that the crane does not pass the safety detection.

[0167] Optionally, the slewing ring is rotated while the telescopic boom is operated: when the crane is in an expanded state and the driver's view picture detects picture rotation, the change in the position of the node on the boom is calculated, and if the change ratio reaches a certain threshold, it is determined that the slewing ring is rotated while the telescopic boom is operated, and it is assumed that the crane does not pass the safety detection.

[0168] Optionally, the crane is in a load state, and the change in the position of the node on the boom is calculated, and if the change ratio reaches a certain threshold, it is determined that the crane is in a load state and the boom is extended, and it is assumed that the crane does not pass the safety detection.

[0169] Optionally, the crane is in a load state, and the change in the position of the node on the boom is calculated, and if the change ratio reaches a certain threshold, it is determined that the crane is in a load state and the boom is extended, and it is assumed that the crane does not pass the safety detection.

[0170] Optionally, the crane is in a load state, and the change in the position of the node on the boom is calculated, and if the change ratio reaches a certain threshold, it is determined that the crane is in a load state and the boom is extended, and it is assumed that the crane does not pass the safety detection.

[0171] Embodiment 4

[0172] As another preferred embodiment of the present application, referring to the drawings in the specification Figure 3 It is to be noted that the crane safety detection device can be used to execute the crane safety detection method in the embodiment of the present application, and the crane safety detection method in the embodiment of the present application can be executed in the crane safety detection device.

[0173] Figure 3 is a schematic diagram of a safety detection device of a crane according to an embodiment of the present application, as shown in the figure, the device can comprise: an acquisition module 30, configured to acquire at least one carrier picture of a preset crane; an identification module 32, configured to identify a carrier feature in the at least one carrier picture, and determine a carrier state of the preset crane, wherein the carrier state at least comprises: a working state, a load state and a moving state; a determination module 34, configured to determine a target detection item corresponding to the carrier state from a plurality of preset detection items, wherein each carrier state is preconfigured with at least one preset detection item, the preset detection item corresponds to at least one preset detection picture, and the preset detection item is used for safety detection of the preset crane according to the at least one preset detection picture; and a generation module 36, configured to generate a preset alarm information in a case where the target detection item fails to pass the safety detection Figure 3

[0174] It should be noted that the acquisition module 30 in this embodiment can be used to execute step S1 in the embodiments of the present application, the identification module 32 in this embodiment can be used to execute step S2 in the embodiments of the present application, the determination module 34 in this embodiment can be used to execute step S3 in the embodiments of the present application, and the generation module 36 in this embodiment can be used to execute step S4 in the embodiments of the present application. The above modules have the same examples and application scenarios as the corresponding steps, but are not limited to the contents disclosed in the above embodiments.

[0175] In the embodiments of the present application, at least one carrier picture of a preset crane is acquired; a carrier feature in the at least one carrier picture is identified, and a carrier state of the preset crane is determined, wherein the carrier state at least comprises: a working state, a load state and a moving state; a target detection item corresponding to the carrier state is determined from a plurality of preset detection items, wherein each carrier state is preconfigured with at least one preset detection item, the preset detection item corresponds to at least one preset detection picture, and the preset detection item is used for safety detection of the preset crane according to the at least one preset detection picture; and a preset alarm information is generated in a case where the target detection item fails to pass the safety detection, thereby achieving the technical effect of automatically performing safety detection on the crane according to the working state of the crane, and further solving the technical problem that the crane safety detection cannot be implemented according to the state of the crane.

[0176] ​As an optional embodiment, the identification module comprises: a first identification unit configured to identify a top view picture and a peripheral view picture in the at least one vehicle picture, wherein the top view picture is an image of a region between a vehicle hook of the preset crane and the ground collected at the top of the preset crane, and the peripheral view picture is an image of the preset crane collected in a third-person view; a second identification unit configured to identify a vehicle feature in the peripheral view picture, wherein the vehicle feature at least comprises a vehicle outrigger of the preset crane; a detection unit configured to, in a case where the vehicle outrigger is identified in the peripheral view picture, detect whether a human image exists in the top view picture; and a first determination unit configured to, in a case where the human image exists in the top view picture, determine that the vehicle state of the preset crane is a working state.

[0177] As an optional embodiment, the identification module comprises: a third identification unit configured to identify a top view picture and a peripheral view picture in the at least one vehicle picture, wherein the top view picture is an image of a region between a vehicle hook of the preset crane and the ground collected at the top of the preset crane, and the peripheral view picture is an image of the preset crane collected in a third-person view; a fourth identification unit configured to identify a vehicle feature in the top view picture and the peripheral view picture, wherein the vehicle feature at least comprises the vehicle hook of the preset crane; and a second determination unit configured to, in a case where the vehicle hook is identified to have a physical connection with a hoisted object in the top view picture, and the position of the vehicle hook is detected to change in the peripheral view picture, determine that the vehicle state of the preset crane is a load state.

[0178] As an optional embodiment, the identification module comprises: a fifth identification unit configured to identify a top view picture and a driver view picture in the at least one vehicle picture, wherein the top view picture is an image of a region between a vehicle hook of the preset crane and the ground collected at the top of the preset crane; a sixth identification unit configured to identify a vehicle feature in the top view picture, wherein the vehicle feature at least comprises the vehicle hook of the preset crane; and a third determination unit configured to, in a case where the vehicle hook is identified to have a physical connection with a hoisted object in the top view picture, and the picture is detected to rotate in the driver view picture, determine that the vehicle state of the preset crane is a load state.

[0179] As an optional embodiment, the identification module comprises: a seventh identification unit configured to identify a peripheral view picture in the at least one vehicle picture, wherein the peripheral view picture is an image of the preset crane collected in a third-person view; an eighth identification unit configured to identify a vehicle feature in the peripheral view picture, wherein the vehicle feature at least comprises the preset crane and a vehicle wheel of the preset crane; and a fourth determination unit configured to, in a case where a variation range of an intersection-over-union of the preset crane and the vehicle wheel in the peripheral view picture is within a preset range in a first preset time range, determine that the vehicle state is a moving state.

[0180] As an optional embodiment, the determining module comprises: a first determining submodule, configured to determine, in a case where the preset crane is in a working state, that the preset detection picture corresponding to the target detection item comprises a driver perspective picture and a peripheral perspective picture, wherein the peripheral perspective picture is an image of the preset crane collected in a third-person perspective; and a first detecting submodule, configured to detect whether the driver perspective picture and the peripheral perspective picture exist a first preset object, wherein the first preset object is provided with a command identifier, and in a case where it is detected that the driver perspective picture and the peripheral perspective picture do not exist the first preset object, it is determined that the target detection item fails to pass the safety detection.

[0181] As an optional embodiment, the determining module comprises: a second determining submodule, configured to determine, in a case where the preset crane is in a working state, that the preset detection picture corresponding to the target detection item comprises a driver perspective picture and a peripheral perspective picture, wherein the peripheral perspective picture is an image of the preset crane collected in a third-person perspective; and a second detecting submodule, configured to detect whether the driver perspective picture and the peripheral perspective picture exist a second preset object, wherein the second preset object is provided with both a first guardian identifier and a second guardian identifier, and in a case where it is detected that the driver perspective picture and the peripheral perspective picture do not exist the second preset object, it is determined that the target detection item fails to pass the safety detection.

[0182] As an optional embodiment, the determining module comprises: a third determining submodule, configured to determine, in a case where the preset crane is in a working state, that the preset detection picture corresponding to the target detection item comprises an internal perspective picture and a peripheral perspective picture, wherein the peripheral perspective picture is an image of the preset crane collected in a third-person perspective; and a third detecting submodule, configured to detect whether the internal perspective picture exists a target object, and in a case where the internal perspective picture does not exist the target object, detect whether the peripheral perspective picture exists a target object with a third preset identifier on the head, wherein the target object represents an image of a driver of the preset crane, and the third preset identifier represents a safety helmet worn by the driver, and in a case where it is detected that the internal perspective picture does not exist the target object, and the peripheral perspective picture does not exist the target object with the third preset identifier on the head, it is determined that the target detection item fails to pass the safety detection.

[0183] As an optional embodiment, the determining module comprises: a fourth determining submodule, configured to determine, in a case where the preset crane is in a working state, that the preset detection picture corresponding to the target detection item comprises a top view picture, wherein the top view picture is an image of a region between a carrier hook of the preset crane and the ground collected at a top of the preset crane; and a fourth detecting submodule, configured to detect whether a human image exists in a first preset warning region of the top view picture, wherein the first preset warning region is a region in which a carrier boom of the preset crane has a falling risk and is pre-labeled in the top view picture, and in a case where it is detected that the human image exists in the first preset warning region, determine that the target detection item fails to pass the safety detection.

[0184] As an optional embodiment, the determining module comprises: a fifth determining submodule, configured to determine, in a case where the preset crane is in a working state, that the preset detection picture corresponding to the target detection item comprises a peripheral view picture, wherein the peripheral view picture is an image of the preset crane collected in a third-person perspective; and a fifth detecting submodule, configured to detect whether a position change amount of a carrier support leg of the preset crane and a corresponding pad within a second preset time range is consistent, wherein the preset crane comprises a plurality of carrier support legs, each of which is pre-configured with a corresponding pad, a corresponding relationship between the carrier support leg and the pad is determined according to a distance between the carrier support leg and the pad in the peripheral view picture, and in a case where it is detected that the position change amount of the carrier support leg and the corresponding pad within the second preset time range is inconsistent, determine that the target detection item fails to pass the safety detection.

[0185] As an optional embodiment, the determining module comprises: a sixth determining submodule, configured to determine, in a case where the preset crane is in a working state, that the preset detection picture corresponding to the target detection item comprises a driver view picture and a peripheral view picture, wherein the peripheral view picture is an image of the preset crane collected in a third-person perspective; and a sixth detecting submodule, configured to detect whether a picture rotation occurs in the driver view picture, and in a case where it is detected that the picture rotation occurs in the driver view picture, detect whether a change ratio of a boom node of the preset crane in the peripheral view picture exceeds a first preset ratio threshold, and in a case where it is detected that the picture rotation occurs in the driver view picture and the change ratio of the boom node exceeds the first preset ratio threshold, determine that the target detection item fails to pass the safety detection.

[0186] As an optional embodiment, the determining module comprises: a seventh determining submodule, configured to determine that the preset detection picture corresponding to the target detection item comprises a peripheral view picture in a case where the preset crane enters the load state from the moving state, wherein the peripheral view picture is an image of the preset crane collected in a third-person view; and a seventh detecting submodule, configured to detect whether the target warning mark exists in the peripheral view picture, and determine that the target detection item passes the safety detection in a case where it is detected that the target warning mark exists in the peripheral view picture.

[0187] As an optional embodiment, the determining module comprises: an eighth determining submodule, configured to determine that the preset detection picture corresponding to the target detection item comprises a peripheral view picture and a top view picture in a case where the preset crane enters the load state from the moving state, wherein the peripheral view picture is an image of the preset crane collected in a third-person view, and the top view picture is an image of a region between the carrier hook of the preset crane and the ground collected at the top of the preset crane; and an eighth detecting submodule, configured to detect whether the skid exists in the peripheral view picture and the top view picture, and determine that the target detection item passes the safety detection in a case where it is detected that the skid exists in the peripheral view picture or the top view picture.

[0188] As an optional embodiment, the determining module comprises: a ninth determining submodule, configured to determine that the preset detection picture corresponding to the target detection item comprises a cab view picture in a case where the preset crane is in the load state; and a ninth detecting submodule, configured to detect whether the target behavior exists in the target object in the cab view picture, and determine that the target detection item does not pass the safety detection in a case where it is detected that the target behavior exists in the target object.

[0189] As an optional embodiment, the determining module comprises: a tenth determining submodule, configured to determine that the preset detection picture corresponding to the target detection item comprises a cab view picture in a case where the preset crane is in the load state; and a tenth detecting submodule, configured to detect whether the target object exists in the cab view picture, and determine that the target detection item does not pass the safety detection in a case where it is detected that the target object does not exist in the cab view picture.

[0190] As an optional embodiment, the determining module comprises: an eleventh determining sub-module, in the case that the preset crane is in the load state, the preset detection picture corresponding to the target detection item comprises a top view picture, wherein the top view picture is an image of a region between a carrier hook of the preset crane and the ground collected at the top of the preset crane; and an eleventh detecting sub-module, configured to detect whether a human image exists in a second preset alert region in the top view picture, wherein the second preset alert region is a region in which the carrier hook of the preset crane or a hoisted object has a falling risk and is pre-labeled in the top view picture, and in the case that the human image exists in the second preset alert region, it is determined that the target detection item fails to pass the safety detection.

[0191] As an optional embodiment, the determining module comprises: a twelfth determining sub-module, in the case that the preset crane is in the load state, the preset detection picture corresponding to the target detection item comprises a peripheral view picture, wherein the peripheral view picture is an image of the preset crane collected in a third-person view; and a twelfth detecting sub-module, configured to detect whether a change ratio of a boom node of the preset crane in the peripheral view picture exceeds a second preset ratio threshold, and in the case that the change ratio of the boom node exceeds the second preset ratio threshold, it is determined that the target detection item fails to pass the safety detection.

[0192] As an optional embodiment, the determining module comprises: a thirteenth determining sub-module, in the case that the preset crane is in the load state, the preset detection picture corresponding to the target detection item comprises a peripheral view picture, wherein the peripheral view picture is an image of the preset crane collected in a third-person view; and a thirteenth detecting sub-module, configured to detect whether a sling exists in a large hook and a small hook of the preset crane in the peripheral view picture, and in the case that the sling exists in the large hook and the small hook of the preset crane simultaneously, it is determined that the target detection item fails to pass the safety detection.

[0193] As an optional embodiment, the determining module comprises: a fourteenth determining sub-module, in the case that the preset crane is in the load state, the preset detection picture corresponding to the target detection item comprises a peripheral view picture, wherein the peripheral view picture is an image of the preset crane collected in a third-person view; and a fourteenth detecting sub-module, configured to detect a pilot lamp of the preset crane in the peripheral view picture, and in the case that the pilot lamp indicates overload, it is determined that the target detection item fails to pass the safety detection.

[0194] As an optional embodiment, the determining module comprises: a fifteenth determining sub-module, configured to determine that the preset detection picture corresponding to the target detection item comprises a peripheral view picture in a case that the preset crane is in the moving state, wherein the peripheral view picture is an image of the preset crane collected in a third-person view angle; and a fifteenth detecting sub-module, configured to detect whether the carrier hook of the preset crane is hung with the hoisting sling in the peripheral view picture, wherein in a case that the carrier hook is detected to be hung with the hoisting sling, it is determined that the target detection item fails to pass the safety detection.

[0195] Embodiment 5

[0196] The embodiment of the present application can provide a computer terminal, which can be any computer terminal device in a computer terminal group. Alternatively, in the embodiment, the computer terminal can be replaced by a mobile terminal or other terminal device.

[0197] Alternatively, in the embodiment, the computer terminal can be located in at least one network device of a plurality of network devices of a computer network.

[0198] In the embodiment, the computer terminal can execute program codes of the following steps in the safety detection method of the crane: acquiring at least one carrier picture of the preset crane; identifying carrier features in the at least one carrier picture to determine a carrier state of the preset crane, wherein the carrier state at least comprises a working state, a load state and a moving state; determining a target detection item corresponding to the carrier state from a plurality of preset detection items, wherein each carrier state is pre-configured with at least one preset detection item, the preset detection item corresponds to at least one preset detection picture, and the preset detection item is used for safety detection of the preset crane according to the at least one preset detection picture; and generating preset alarm information in a case that the target detection item fails to pass the safety detection.

[0199] Alternatively, Figure 4 is a structural block diagram of a computer terminal according to an embodiment of the present application. As shown in Figure 4 the computer terminal 40 can include one or more (only one is shown in the figure) processors 42 and a memory 44.

[0200] The memory can be used to store software programs and modules, such as program instructions / modules corresponding to the safety detection method and device of the crane in the embodiments of the present application. The processor executes various functions and data processing by running the software programs and modules stored in the memory, that is, implements the safety detection method of the crane. The memory can include a high-speed random access memory, and can also include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some examples, the memory can further include a memory remotely arranged with respect to the processor, which can be connected to the terminal 40 through a network. Examples of the network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0201] The processor can call information and applications stored in the memory through the transmission device to perform the following steps: acquiring at least one carrier picture of a preset crane; identifying a carrier feature in the at least one carrier picture to determine a carrier state of the preset crane, wherein the carrier state at least includes a working state, a load state, and a moving state; determining a target detection item corresponding to the carrier state from a plurality of preset detection items, wherein each carrier state is pre-configured with at least one preset detection item, the preset detection item corresponds to at least one preset detection picture, and the preset detection item is used for safety detection of the preset crane according to the at least one preset detection picture; and generating a preset alarm information in a case where the target detection item fails to pass the safety detection.

[0202] Optionally, the processor can further execute program codes of the following steps: identifying a top view picture and a peripheral view picture in the at least one carrier picture, wherein the top view picture is an image of a region between a carrier hook of the preset crane and the ground collected at the top of the preset crane, and the peripheral view picture is an image of the preset crane collected in a third-person view; identifying a carrier feature in the peripheral view picture, wherein the carrier feature at least includes a carrier outrigger of the preset crane; detecting whether there is a human image in the top view picture in a case where the carrier outrigger is identified in the peripheral view picture; and determining that the carrier state of the preset crane is the working state in a case where there is a human image in the top view picture.

[0203] Optionally, the processor can further execute program codes of the following steps: identifying a top view picture and a peripheral view picture in at least one vehicle picture, wherein the top view picture is an image of a region between a vehicle hook of the preset crane and the ground collected at the top of the preset crane, and the peripheral view picture is an image of the preset crane collected in a third-person view; identifying a vehicle feature in the top view picture and the peripheral view picture, wherein the vehicle feature at least includes the vehicle hook of the preset crane; and determining that the vehicle state of the preset crane is in the load state in a case where the vehicle hook is identified to have a physical connection with a hoisted object in the top view picture, and the position of the vehicle hook is detected to change in the peripheral view picture.

[0204] Optionally, the processor can further execute program codes of the following steps: identifying a top view picture and a driver view picture in at least one vehicle picture, wherein the top view picture is an image of a region between a vehicle hook of the preset crane and the ground collected at the top of the preset crane; identifying a vehicle feature in the top view picture, wherein the vehicle feature at least includes the vehicle hook of the preset crane; and determining that the vehicle state of the preset crane is in the load state in a case where the vehicle hook is identified to have a physical connection with a hoisted object in the top view picture, and the picture is detected to rotate in the driver view picture.

[0205] Optionally, the processor can further execute program codes of the following steps: identifying a peripheral view picture in at least one vehicle picture, wherein the peripheral view picture is an image of the preset crane collected in a third-person view; identifying a vehicle feature in the peripheral view picture, wherein the vehicle feature at least includes the preset crane and a vehicle wheel of the preset crane; and determining that the vehicle state is in the moving state in a case where the variation range of the intersection-over-union of the preset crane and the vehicle wheel in the peripheral view picture is within a preset range in a first preset time range.

[0206] Optionally, the processor can further execute program codes of the following steps: in a case where the preset crane is in a working state, determining that a preset detection picture corresponding to a target detection item includes a driver view picture and a peripheral view picture, wherein the peripheral view picture is an image of the preset crane collected in a third-person view; detecting whether a first preset object exists in the driver view picture and the peripheral view picture, wherein the first preset object is provided with a command identification; and determining that the target detection item fails in the safety detection in a case where the first preset object is not detected in the driver view picture and the peripheral view picture.

[0207] Optionally, the processor can further execute program codes of the following steps: in the case that the preset crane is in a working state, determining the preset detection picture corresponding to the target detection item comprises: a driver perspective picture and a peripheral perspective picture, wherein the peripheral perspective picture is an image of the preset crane collected in a third-person perspective; detecting whether the second preset object exists in the driver perspective picture and the peripheral perspective picture, wherein the second preset object has both the first guardian mark and the second guardian mark, and in the case that the second preset object does not exist in both the driver perspective picture and the peripheral perspective picture, determining that the target detection item fails to pass the safety detection.

[0208] Optionally, the processor can further execute program codes of the following steps: in the case that the preset crane is in a working state, determining the preset detection picture corresponding to the target detection item comprises: an internal perspective picture and a peripheral perspective picture, wherein the peripheral perspective picture is an image of the preset crane collected in a third-person perspective; detecting whether the target object exists in the internal perspective picture, and in the case that the target object does not exist in the internal perspective picture, detecting whether the target object with the third preset mark on the head exists in the peripheral perspective picture, wherein the target object represents an image of a driver of the preset crane, and the third preset mark represents a safety helmet worn by the driver, and in the case that the target object does not exist in the internal perspective picture and the target object with the third preset mark on the head does not exist in the peripheral perspective picture, determining that the target detection item fails to pass the safety detection.

[0209] Optionally, the processor can further execute program codes of the following steps: in the case that the preset crane is in a working state, determining the preset detection picture corresponding to the target detection item comprises: a top perspective picture, wherein the top perspective picture is an image of a region between a carrier hook of the preset crane and the ground collected at the top of the preset crane; detecting whether a human image exists in a first preset warning region of the top perspective picture, wherein the first preset warning region is a region in the top perspective picture in which a carrier hook arm of the preset crane is at a falling risk, and in the case that the human image exists in the first preset warning region, determining that the target detection item fails to pass the safety detection.

[0210] Optionally, the processor can further execute program codes of the following steps: in the case that the preset crane is in a working state, determining that the preset detection picture corresponding to the target detection item comprises: a peripheral view picture, wherein the peripheral view picture is an image of the preset crane collected in a third-person view; detecting whether the position change amount of the carrier support leg and the corresponding pad of the preset crane in a second preset time range in the peripheral view picture is consistent, wherein the preset crane comprises a plurality of carrier support legs, each carrier support leg is pre-configured with a corresponding pad, the correspondence between the carrier support leg and the pad is determined according to the distance between the carrier support leg and the pad in the peripheral view picture, and in the case that the position change amount of the carrier support leg and the corresponding pad in the second preset time range is detected to be inconsistent, determining that the target detection item fails the safety detection.

[0211] Optionally, the processor can further execute program codes of the following steps: in the case that the preset crane is in a working state, determining that the preset detection picture corresponding to the target detection item comprises: a driver view picture and a peripheral view picture, wherein the peripheral view picture is an image of the preset crane collected in a third-person view; detecting whether the picture rotation occurs in the driver view, and in the case that the picture rotation is detected to occur in the driver view, detecting whether the change ratio of the boom node of the preset crane in the peripheral view picture exceeds a first preset ratio threshold, and in the case that the picture rotation is detected to occur in the driver view and the change ratio of the boom node exceeds the first preset ratio threshold, determining that the target detection item fails the safety detection.

[0212] Optionally, the processor can further execute program codes of the following steps: in the case that the preset crane is in a working state, determining that the preset detection picture corresponding to the target detection item comprises: a driver view picture and a peripheral view picture, wherein the peripheral view picture is an image of the preset crane collected in a third-person view; detecting whether the picture rotation occurs in the driver view, and in the case that the picture rotation is detected to occur in the driver view, detecting whether the change ratio of the boom node of the preset crane in the peripheral view picture exceeds a first preset ratio threshold, and in the case that the picture rotation is detected to occur in the driver view and the change ratio of the boom node exceeds the first preset ratio threshold, determining that the target detection item fails the safety detection.

[0213] Optionally, the processor can further execute program codes of the following steps: in the case that the preset crane is in a working state, determining that the preset detection picture corresponding to the target detection item comprises: a driver view picture and a peripheral view picture, wherein the peripheral view picture is an image of the preset crane collected in a third-person view; detecting whether the picture rotation occurs in the driver view, and in the case that the picture rotation is detected to occur in the driver view, detecting whether the change ratio of the boom node of the preset crane in the peripheral view picture exceeds a first preset ratio threshold, and in the case that the picture rotation is detected to occur in the driver view and the change ratio of the boom node exceeds the first preset ratio threshold, determining that the target detection item fails the safety detection.

[0214] Optionally, the processor can further execute program codes of the following steps: in the case that the preset crane is in a load state, determining that the preset detection picture corresponding to the target detection item comprises a cab perspective picture; detecting whether the target object in the cab perspective picture has a target behavior, wherein, in the case that the target object is detected to have the target behavior, determining that the target detection item fails to pass the safety detection.

[0215] Optionally, the processor can further execute program codes of the following steps: in the case that the preset crane is in a load state, determining that the preset detection picture corresponding to the target detection item comprises a cab perspective picture; detecting whether the target object in the cab perspective picture has a target behavior, wherein, in the case that the target object is detected to have the target behavior, determining that the target detection item fails to pass the safety detection.

[0216] Optionally, the processor can further execute program codes of the following steps: in the case that the preset crane is in a load state, determining that the preset detection picture corresponding to the target detection item comprises a top perspective picture, wherein the top perspective picture is an image of a region between a carrier hook of the preset crane and the ground collected at the top of the preset crane; detecting whether a human image exists in a second preset warning area of the top perspective picture, wherein the second preset warning area is an area in the top perspective picture in which the carrier hook of the preset crane or the hoisted object has a falling risk, and in the case that the human image is detected to exist in the second preset warning area, determining that the target detection item fails to pass the safety detection.

[0217] Optionally, the processor can further execute program codes of the following steps: in the case that the preset crane is in a load state, determining that the preset detection picture corresponding to the target detection item comprises a peripheral perspective picture, wherein the peripheral perspective picture is an image of the preset crane collected in a third-person perspective; detecting whether a change ratio of a boom node of the preset crane in the peripheral perspective picture exceeds a second preset ratio threshold, and in the case that the change ratio of the boom node is detected to exceed the second preset ratio threshold, determining that the target detection item fails to pass the safety detection.

[0218] Optionally, the processor can further execute program codes of the following steps: in the case that the preset crane is in a load state, determining that the preset detection picture corresponding to the target detection item comprises a peripheral perspective picture, wherein the peripheral perspective picture is an image of the preset crane collected in a third-person perspective; detecting whether a change ratio of a boom node of the preset crane in the peripheral perspective picture exceeds a second preset ratio threshold, and in the case that the change ratio of the boom node is detected to exceed the second preset ratio threshold, determining that the target detection item fails to pass the safety detection.

[0219] Optionally, the processor can further execute program codes of the following steps: in the case that the preset crane is in the load state, determining that the preset detection picture corresponding to the target detection item comprises a peripheral view picture, wherein the peripheral view picture is an image of the preset crane collected in a third-person view; and detecting a pilot lamp of the preset crane in the peripheral view picture, wherein in the case that the pilot lamp indicates overload, it is determined that the target detection item fails to pass the safety detection.

[0220] Optionally, the processor can further execute program codes of the following steps: in the case that the preset crane is in the load state, determining that the preset detection picture corresponding to the target detection item comprises a peripheral view picture, wherein the peripheral view picture is an image of the preset crane collected in a third-person view; and detecting a pilot lamp of the preset crane in the peripheral view picture, wherein in the case that the pilot lamp indicates overload, it is determined that the target detection item fails to pass the safety detection.

[0221] In the embodiment of the present application, at least one carrier picture of the preset crane is acquired; a carrier feature in the at least one carrier picture is recognized to determine a carrier state of the preset crane, wherein the carrier state at least includes a working state, a load state and a moving state; from a plurality of preset detection items, a target detection item corresponding to the carrier state is determined, wherein each carrier state is pre-configured with at least one preset detection item, the preset detection item corresponds to at least one preset detection picture, and the preset detection item is used for safety detection of the preset crane according to the at least one preset detection picture; in the case that the target detection item fails to pass the safety detection, preset alarm information is generated, thereby realizing the technical effect of automatically performing safety detection of the crane according to the working state of the crane, and further solving the technical problem that the crane safety detection cannot be realized according to the crane state.

[0222] Those skilled in the art can understand that, Figure 4 The structure shown is only schematic, and the computer terminal can also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a palm computer, a Mobile Internet Device (MID), a PAD, and the like. Figure 4 It does not limit the structure of the electronic device. For example, the computer terminal 40 can further include more or fewer components (such as a network interface, a display device, etc.) than Figure 4 shown, or have a different configuration than Figure 4 shown.

[0223] Those skilled in the art can understand that all or part of the steps of various methods in the above embodiments can be completed by instructing the terminal device related hardware through a program, and the program can be stored in a computer readable readable storage medium, which can include a flash disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0224] Embodiment 6

[0225] The embodiments of the present application also provide a readable storage medium. Optionally, in the present embodiment, the readable storage medium can be used to save the program code executed by the safety detection method of the crane provided by the above embodiments.

[0226] Optionally, in the present embodiment, the readable storage medium can be located in any one of the computer terminals in the computer terminal group in the computer network, or in any one of the mobile terminals in the mobile terminal group.

[0227] Optionally, in the present embodiment, the readable storage medium is configured to store program code for performing the following steps: obtaining at least one carrier picture of a preset crane; identifying a carrier feature in the at least one carrier picture, and determining a carrier state of the preset crane, wherein the carrier state at least includes a working state, a load state and a moving state; determining a target detection item corresponding to the carrier state from a plurality of preset detection items, wherein each carrier state is pre-configured with at least one preset detection item, the preset detection item corresponds to at least one preset detection picture, and the preset detection item is used for safety detection of the preset crane according to the at least one preset detection picture; and generating a preset alarm information in the case that the target detection item fails to pass the safety detection.

[0228] Optionally, in the present embodiment, the readable storage medium is configured to store program code for performing the following steps: identifying a top view picture and a peripheral view picture in the at least one carrier picture, wherein the top view picture is an image of a region between a carrier hook of the preset crane and the ground collected at the top of the preset crane, and the peripheral view picture is an image of the preset crane collected in a third person view; identifying a carrier feature in the peripheral view picture, wherein the carrier feature at least includes a carrier support leg of the preset crane; detecting whether there is a human image in the top view picture in the case that the carrier support leg is identified in the peripheral view picture; and determining that the carrier state of the preset crane is the working state in the case that there is a human image in the top view picture.

[0229] Optionally, in the embodiment, the readable storage medium is configured to store program code for performing the following steps: identifying a top view picture and a peripheral view picture in at least one vehicle picture, wherein the top view picture is an image of a region between a vehicle hook of the preset crane and the ground collected at the top of the preset crane, and the peripheral view picture is an image of the preset crane collected in a third-person perspective; identifying a vehicle feature in the top view picture and the peripheral view picture, wherein the vehicle feature at least includes the vehicle hook of the preset crane; and determining that a vehicle state of the preset crane is a load state in a case where the vehicle hook is identified to have a physical connection with a hoisted object in the top view picture, and the position of the vehicle hook is detected to change in the peripheral view picture.

[0230] Optionally, in the embodiment, the readable storage medium is configured to store program code for performing the following steps: identifying a top view picture and a driver view picture in at least one vehicle picture, wherein the top view picture is an image of a region between a vehicle hook of the preset crane and the ground collected at the top of the preset crane; identifying a vehicle feature in the top view picture, wherein the vehicle feature at least includes the vehicle hook of the preset crane; and determining that a vehicle state of the preset crane is a load state in a case where the vehicle hook is identified to have a physical connection with a hoisted object in the top view picture, and the driver view picture detects a picture rotation.

[0231] Optionally, in the embodiment, the readable storage medium is configured to store program code for performing the following steps: identifying a peripheral view picture in at least one vehicle picture, wherein the peripheral view picture is an image of the preset crane collected in a third-person perspective; identifying a vehicle feature in the peripheral view picture, wherein the vehicle feature at least includes the preset crane and a vehicle wheel of the preset crane; and determining that a vehicle state is a moving state in a case where a variation range of an intersection-over-union of the preset crane and the vehicle wheel in the peripheral view picture is within a preset range in a first preset time range.

[0232] Optionally, in the embodiment, the readable storage medium is configured to store program code for performing the following steps: in a case where the preset crane is in a working state, determining that a preset detection picture corresponding to a target detection item includes a driver view picture and a peripheral view picture, wherein the peripheral view picture is an image of the preset crane collected in a third-person perspective; detecting whether a first preset object exists in the driver view picture and the peripheral view picture, wherein the first preset object is provided with a command identification; and determining that the target detection item fails to pass a safety detection in a case where the first preset object is not detected in the driver view picture and the peripheral view picture.

[0233] Optionally, in the embodiment, the readable storage medium is configured to store program code for performing the following steps: in the case that the preset crane is in a working state, determining that the preset detection picture corresponding to the target detection item comprises a driver perspective picture and a peripheral perspective picture, wherein the peripheral perspective picture is an image of the preset crane collected in a third-person perspective; detecting whether the second preset object exists in the driver perspective picture and the peripheral perspective picture, wherein the second preset object has both the first guardian mark and the second guardian mark, and in the case that the second preset object is detected not to exist in the driver perspective picture and the peripheral perspective picture, determining that the target detection item fails to pass the safety detection.

[0234] Optionally, in the embodiment, the readable storage medium is configured to store program code for performing the following steps: in the case that the preset crane is in a working state, determining that the preset detection picture corresponding to the target detection item comprises an internal perspective picture and a peripheral perspective picture, wherein the peripheral perspective picture is an image of the preset crane collected in a third-person perspective; detecting whether the target object exists in the internal perspective picture, and in the case that the target object is detected not to exist in the internal perspective picture, detecting whether the target object with the third preset mark on the head exists in the peripheral perspective picture, wherein the target object represents an image of a driver of the preset crane, and the third preset mark represents a safety helmet worn by the driver, and in the case that the target object is detected not to exist in the internal perspective picture and the target object with the third preset mark on the head is detected not to exist in the peripheral perspective picture, determining that the target detection item fails to pass the safety detection.

[0235] Optionally, in the embodiment, the readable storage medium is configured to store program code for performing the following steps: in the case that the preset crane is in a working state, determining that the preset detection picture corresponding to the target detection item comprises a top perspective picture, wherein the top perspective picture is an image of a region between a carrier hook of the preset crane and the ground collected at the top of the preset crane; detecting whether a human image exists in a first preset alert region of the top perspective picture, wherein the first preset alert region is a region in the top perspective picture in which a carrier hook arm of the preset crane is at a falling risk, and in the case that the human image is detected to exist in the first preset alert region, determining that the target detection item fails to pass the safety detection.

[0236] Optionally, in the embodiment, the readable storage medium is configured to store program code for performing the following steps: in the case that the preset crane is in a working state, determining that the preset detection picture corresponding to the target detection item comprises: a peripheral view picture, wherein the peripheral view picture is an image of the preset crane collected in a third-person perspective; detecting whether the position change amount of the carrier support leg and the corresponding pad of the preset crane in a second preset time range in the peripheral view picture is consistent, wherein the preset crane comprises a plurality of carrier support legs, each carrier support leg is pre-configured with a corresponding pad, the correspondence between the carrier support leg and the pad is determined according to the distance between the carrier support leg and the pad in the peripheral view picture, and in the case that the position change amount of the carrier support leg and the corresponding pad in the second preset time range is inconsistent, it is determined that the target detection item fails the safety detection.

[0237] Optionally, in the embodiment, the readable storage medium is configured to store program code for performing the following steps: in the case that the preset crane is in a working state, determining that the preset detection picture corresponding to the target detection item comprises: a driver view picture and a peripheral view picture, wherein the peripheral view picture is an image of the preset crane collected in a third-person perspective; detecting whether the picture rotation occurs in the driver view, and in the case that the picture rotation occurs in the driver view, detecting whether the change ratio of the boom node of the preset crane in the peripheral view picture exceeds a first preset ratio threshold, and in the case that the picture rotation occurs in the driver view and the change ratio of the boom node exceeds the first preset ratio threshold, it is determined that the target detection item fails the safety detection.

[0238] Optionally, in the embodiment, the readable storage medium is configured to store program code for performing the following steps: in the case that the preset crane enters a load state from a moving state, determining that the preset detection picture corresponding to the target detection item comprises: a peripheral view picture, wherein the peripheral view picture is an image of the preset crane collected in a third-person perspective; detecting whether the target warning mark exists in the peripheral view picture, wherein in the case that the target warning mark exists in the peripheral view picture, it is determined that the target detection item passes the safety detection.

[0239] Optionally, in the embodiment, the readable storage medium is configured to store program code for performing the following steps: in the case that the preset crane enters a load state from a moving state, determining that the preset detection picture corresponding to the target detection item comprises: a peripheral view picture and a top view picture, wherein the peripheral view picture is an image of the preset crane collected in a third-person perspective, and the top view picture is an image of a region between the carrier hook of the preset crane and the ground collected at the top of the preset crane; detecting whether the pad exists in the peripheral view picture and the top view picture, wherein in the case that the pad exists in the peripheral view picture or the top view picture, it is determined that the target detection item passes the safety detection.

[0240] Optionally, in the embodiment, the readable storage medium is configured to store program code for performing the following steps: in the case that the preset crane is in the load state, determining that the preset detection picture corresponding to the target detection item includes the cab perspective picture; detecting whether the target object in the cab perspective picture has the target behavior, wherein, in the case that the target object is detected to have the target behavior, determining that the target detection item fails to pass the safety detection.

[0241] Optionally, in the embodiment, the readable storage medium is configured to store program code for performing the following steps: in the case that the preset crane is in the load state, determining that the preset detection picture corresponding to the target detection item includes the cab perspective picture; detecting whether the target object in the cab perspective picture has the target behavior, wherein, in the case that the target object is detected to have the target behavior, determining that the target detection item fails to pass the safety detection.

[0242] Optionally, in the embodiment, the readable storage medium is configured to store program code for performing the following steps: in the case that the preset crane is in the load state, determining that the preset detection picture corresponding to the target detection item includes the top perspective picture, wherein, the top perspective picture is an image of a region between the carrier hook of the preset crane and the ground collected at the top of the preset crane; detecting whether there is a human image in a second preset warning area of the top perspective picture, wherein, the second preset warning area is a region in the top perspective picture in which the carrier hook of the preset crane or the hoisted object has a falling risk, and in the case that the human image in the second preset warning area is detected, determining that the target detection item fails to pass the safety detection.

[0243] Optionally, in the embodiment, the readable storage medium is configured to store program code for performing the following steps: in the case that the preset crane is in the load state, determining that the preset detection picture corresponding to the target detection item includes the peripheral perspective picture, wherein, the peripheral perspective picture is an image of the preset crane collected in the third person perspective; detecting whether the change ratio of the boom node of the preset crane in the peripheral perspective picture exceeds a second preset ratio threshold, and in the case that the change ratio of the boom node exceeds the second preset ratio threshold is detected, determining that the target detection item fails to pass the safety detection.

[0244] Optionally, in the embodiment, the readable storage medium is configured to store program code for performing the following steps: in the case that the preset crane is in the load state, determining that the preset detection picture corresponding to the target detection item comprises a peripheral view picture, wherein the peripheral view picture is an image of the preset crane collected in the third person view; and detecting whether the large hook and the small hook of the preset crane in the peripheral view picture have the sling, wherein in the case that the large hook and the small hook of the preset crane are detected to have the sling simultaneously, it is determined that the target detection item fails to pass the safety detection.

[0245] Optionally, in the embodiment, the readable storage medium is configured to store program code for performing the following steps: in the case that the preset crane is in the load state, determining that the preset detection picture corresponding to the target detection item comprises a peripheral view picture, wherein the peripheral view picture is an image of the preset crane collected in the third person view; and detecting the indicator light of the preset crane in the peripheral view picture, wherein in the case that the indicator light indicates overload, it is determined that the target detection item fails to pass the safety detection.

[0246] Optionally, in the embodiment, the readable storage medium is configured to store program code for performing the following steps: in the case that the preset crane is in the load state, determining that the preset detection picture corresponding to the target detection item comprises a peripheral view picture, wherein the peripheral view picture is an image of the preset crane collected in the third person view; and detecting the indicator light of the preset crane in the peripheral view picture, wherein in the case that the indicator light indicates overload, it is determined that the target detection item fails to pass the safety detection.

[0247] The above-mentioned serial numbers of the embodiments of the application are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0248] In the above-mentioned embodiments of the application, the description of each embodiment has its own emphasis, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0249] In several embodiments provided in the present application, it should be understood that the disclosed technical contents can be implemented by other manners. Among them, the above-mentioned device embodiments are only schematic, for example, the division of the units can be a logical function division, and in actual implementation, there can be another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be indirect coupling or communication connection through some interfaces, units or modules, which can be electrical or other forms.

[0250] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0251] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0252] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application, essentially or the part that contributes to the prior art, or all or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to make a computer device (which can be a personal computer, a server or a network device, etc.) execute all or part of the steps of the method described in each embodiment of the present application. The foregoing storage medium includes: a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and various program code storage media.

[0253] The above is only the preferred embodiment of the present application, it should be noted that for those skilled in the art, without departing from the principles of the present application, can make a number of improvements and refinements, these improvements and refinements should also be considered as the protection scope of the present application.

Claims

1. A safety detection method for a crane, characterized by: The detection method The method comprises the following steps, S1, acquiring at least one carrier picture of a preset crane; S2, identifying carrier features in at least one carrier picture to determine a carrier state of the preset crane; the carrier state at least includes a working state, a load state and a moving state; S3, from a plurality of preset detection items, determining a target detection item corresponding to the carrier state, wherein each carrier state is pre-configured with at least one preset detection item, the preset detection item corresponds to at least one preset detection picture, and the preset detection item is used for safety detection of the preset crane according to at least one preset detection picture; S4, in the case that the target detection item fails to pass the safety detection, generating a preset alarm information.

2. A method of safety checking a crane as claimed in claim 1, characterized in that: In the S2 step, the carrier picture includes any one or a combination of multiple kinds of pictures, such as an internal perspective picture, a top perspective picture, a peripheral perspective picture and a driver perspective picture; the internal perspective picture is a driver cabin image of the preset crane; the top perspective picture is an image of a region between a carrier hook of the preset crane and the ground collected at the top of the preset crane; and the peripheral perspective picture is an image of the preset crane collected in a third person perspective.

3. A method of safety checking a crane as claimed in claim 2, characterised in that: The carrier features in the top perspective picture at least include the carrier hook of the preset crane; and the carrier features in the peripheral perspective picture at least include the preset crane, a carrier outrigger of the preset crane, the carrier hook and / or a carrier wheel.

4. A method of safety checking a crane as claimed in claim 3, characterized in that: In the case that the carrier outrigger is identified in the peripheral perspective picture, it is detected whether there is a human image in the top perspective picture; in the case that there is a human image in the top perspective picture, it is determined that the carrier state of the preset crane is the working state.

5. A method of safety checking of a crane as claimed in claim 3, characterized in that: In the case that the carrier hook and a hoisted object are physically connected in the top perspective picture, and the position of the carrier hook changes in the peripheral perspective picture, it is determined that the carrier state of the preset crane is the load state.

6. A method of safety checking of a crane as claimed in claim 3, characterized in that: In the case that the carrier hook and a hoisted object are physically connected in the top perspective picture, and the picture rotates in the driver perspective picture, it is determined that the carrier state of the preset crane is the load state.

7. A method of safety checking of a crane as claimed in claim 3, wherein: In the case that a variation range of an intersection and union ratio of the preset crane and the carrier wheel in the peripheral perspective picture is within a preset range in a first preset time range, it is determined that the carrier state is the moving state.

8. A method of safety monitoring of a crane according to any one of claims 1-7, characterized in that: In the S3 step, from a plurality of preset detection items, the target detection item corresponding to the carrier state is determined, specifically, In the case that the preset crane is in the working state, it is determined that the preset detection picture corresponding to the target detection item includes a driver perspective picture and a peripheral perspective picture, it is detected whether there is a first preset object in the driver perspective picture and the peripheral perspective picture, in the case that there is no first preset object in the driver perspective picture and the peripheral perspective picture, it is determined that the target detection item fails to pass the safety detection; the first preset object wears a command identification.

9. A method of safety monitoring of a crane according to any one of claims 1-7, characterized in that: In the S3 step, the target detection item corresponding to the carrier state is determined from a plurality of preset detection items, specifically, In the case where the preset crane is in the working state, the preset detection picture corresponding to the target detection item includes an internal view picture and a peripheral view picture, whether the target object exists in the internal view picture is detected, and in the case where the target object does not exist in the internal view picture, whether the target object with a third preset mark on the head exists in the peripheral view picture is detected, in the case where the target object does not exist in the internal view picture and the target object with the third preset mark on the head does not exist in the peripheral view picture, it is determined that the target detection item fails to pass the safety detection; the target object represents the image of the driver of the preset crane, and the third preset mark represents the safety helmet worn by the driver.

10. A method of safety monitoring of a crane as claimed in any one of claims 1 to 7, wherein: In the S3 step, the target detection item corresponding to the carrier state is determined from a plurality of preset detection items, specifically, In the case where the preset crane is in the working state, the preset detection picture corresponding to the target detection item includes an internal view picture and a peripheral view picture, whether the target object exists in the internal view picture is detected, and in the case where the target object does not exist in the internal view picture, whether the target object with a third preset mark on the head exists in the peripheral view picture is detected, in the case where the target object does not exist in the internal view picture and the target object with the third preset mark on the head does not exist in the peripheral view picture, it is determined that the target detection item fails to pass the safety detection; the target object represents the image of the driver of the preset crane, and the third preset mark represents the safety helmet worn by the driver.

11. A method of safety monitoring of a crane according to any one of claims 1-7, characterized in that: In the S3 step, the target detection item corresponding to the carrier state is determined from a plurality of preset detection items, specifically, In the case where the preset crane is in the working state, the preset detection picture corresponding to the target detection item includes an internal view picture and a peripheral view picture, whether the target object exists in the internal view picture is detected, and in the case where the target object does not exist in the internal view picture, whether the target object with a third preset mark on the head exists in the peripheral view picture is detected, in the case where the target object does not exist in the internal view picture and the target object with the third preset mark on the head does not exist in the peripheral view picture, it is determined that the target detection item fails to pass the safety detection; the target object represents the image of the driver of the preset crane, and the third preset mark represents the safety helmet worn by the driver.

12. A method of safety monitoring of a crane according to any one of claims 1-7, characterized in that: In the S3 step, the target detection item corresponding to the carrier state is determined from a plurality of preset detection items, specifically, In the case where the preset crane is in the working state, the preset detection picture corresponding to the target detection item includes an internal view picture and a peripheral view picture, whether the target object exists in the internal view picture is detected, and in the case where the target object does not exist in the internal view picture, whether the target object with a third preset mark on the head exists in the peripheral view picture is detected, in the case where the target object does not exist in the internal view picture and the target object with the third preset mark on the head does not exist in the peripheral view picture, it is determined that the target detection item fails to pass the safety detection; the target object represents the image of the driver of the preset crane, and the third preset mark represents the safety helmet worn by the driver.

13. A method of safety monitoring of a crane according to any one of claims 1-7, characterized in that: In the S3 step, the target detection item corresponding to the carrier state is determined from a plurality of preset detection items, specifically, In a case where the preset crane enters the load state from the moving state, the preset detection picture corresponding to the target detection item is determined to include a peripheral view picture and a top view picture, and whether there is a skid plate in the peripheral view picture and the top view picture is detected. In a case where it is detected that there is a skid plate in the peripheral view picture or the top view picture, it is determined that the target detection item passes the safety detection.

14. A method of safety monitoring of a crane according to any one of claims 1-7, characterized in that: In the S3 step, the target detection item corresponding to the carrier state is determined from a plurality of preset detection items, specifically, In a case where the preset crane is in the load state, the preset detection picture corresponding to the target detection item is determined to include a cab view picture, and whether there is a target behavior of a target object in the cab view picture is detected. In a case where it is detected that there is a target behavior of a target object, it is determined that the target detection item fails to pass the safety detection.

15. A method of safety monitoring of a crane according to any one of claims 1-7, characterized in that: In the S3 step, the target detection item corresponding to the carrier state is determined from a plurality of preset detection items, specifically, In a case where the preset crane is in the load state, the preset detection picture corresponding to the target detection item is determined to include a cab view picture, and whether there is a target object in the cab view picture is detected. In a case where it is detected that there is no target object in the cab view picture, it is determined that the target detection item fails to pass the safety detection.

16. A method of safety monitoring of a crane according to any one of claims 1-7, characterized in that: In the S3 step, the target detection item corresponding to the carrier state is determined from a plurality of preset detection items, specifically, In a case where the preset crane is in the load state, the preset detection picture corresponding to the target detection item is determined to include a peripheral view picture, and whether there are sling gears in large hooks and small hooks of the preset crane in the peripheral view picture is detected. In a case where it is detected that there are sling gears in the large hooks and the small hooks of the preset crane, it is determined that the target detection item fails to pass the safety detection.

17. A method of safety monitoring of a crane according to any one of claims 1-7, characterized in that: In the S3 step, the target detection item corresponding to the carrier state is determined from a plurality of preset detection items, specifically, In a case where the preset crane is in the moving state, the preset detection picture corresponding to the target detection item is determined to include a peripheral view picture, and whether there are sling gears hung on a carrier hook of the preset crane in the peripheral view picture is detected. In a case where it is detected that there are sling gears hung on the carrier hook, it is determined that the target detection item fails to pass the safety detection.

18. A safety detection device for a crane, characterized by: The device comprises An acquisition module is configured to acquire at least one carrier picture of a preset crane; An identification module is configured to identify a carrier feature in at least one carrier picture, and determine a carrier state of the preset crane, wherein the carrier state at least includes a working state, a load state, and a moving state. A determination module is configured to determine a target detection item corresponding to the carrier state from a plurality of preset detection items, wherein each carrier state is preconfigured with at least one preset detection item, the preset detection item corresponds to at least one preset detection picture, and the preset detection item is used for safety detection of the preset crane according to at least one preset detection picture. A generating module is configured to generate preset alarm information when the target detection item fails to pass the safety detection.

19. A readable storage medium, the readable storage medium being used to store a program, characterized in that: The program is configured to control the readable storage medium to perform the safety detection method of the crane according to any one of claims 1-17.

20. An electronic device, comprising a memory and a processor, the processor being configured to run a program stored in the processor, characterized in that: The program is configured to perform the safety detection method of the crane according to any one of claims 1-17.

Images