Safety detection method and device of crane, storage medium and electronic equipment

Abstract

The invention discloses a safety detection method and device of a crane, a storage medium and electronic equipment, and relates to the technical field of crane safety. The method comprises the steps of obtaining a carrier picture of a preset crane; vehicle characteristics in the vehicle picture are recognized, the vehicle state of the preset crane is determined, and the vehicle state at least comprises the working state, the load state and the vehicle moving state; target detection items corresponding to the carrier states are determined from the multiple preset detection items, each carrier state is pre-configured with at least one preset detection item, the preset detection items correspond to at least one preset detection picture, and the preset detection items are used for carrying out safety detection on the preset crane according to the at least one preset detection picture; and when the target detection item does not pass the security detection, generating preset alarm information. Therefore, the technical effect of automatically detecting the safety of the crane according to the working state of the crane is achieved, and the technical problem that safety detection of the crane cannot be achieved according to the state of the crane is solved.

Description

Technical Field

[0001] The present invention relates to the field of crane safety technology, and more specifically to a crane safety detection method, device, storage medium and electronic equipment. Background Art

[0002] In the industrial production process, production safety is of vital importance. Traditional management is achieved through the guidance of managers at the management site. The quality and status of the managers themselves affect the final management effect and cannot effectively reduce the frequency of accidents. In particular, high-risk operations such as hoisting operations require all-round, real-time and accurate safety supervision.

[0003] However, since managers cannot continuously manage the work site and can only supervise some key areas, there will be inadequate supervision in some other work sites, and it is impossible to conduct comprehensive, real-time and accurate safety supervision of the operation process, which will increase the incidence of accidents.

[0004] For example, the invention patent application with publication number CN116129346A, publication date May 16, 2023, and titled "Safety monitoring system and method for detecting workers approaching a lotus crane based on a monocular camera" requires manual observation and experience to determine the rotation center and height of the crane, and to mark them. The monitoring system requires personnel to pay attention at all times. However, manual observation and experience to determine the rotation center and height of the crane have human uncertainties, which will lead to large errors in the detection results. Summary of the invention

[0005] In order to overcome the defects and deficiencies in the above-mentioned prior art, the present invention provides a crane safety detection method, device, storage medium and electronic equipment. The purpose of the present invention is to intelligently, accurately and efficiently identify the physical hidden dangers and unsafe behaviors of personnel in the operation process by real-time calculation and analysis of the video surveillance screen of the crane hoisting operation area, automatically identify the relevant unsafe behaviors and give timely voice alarm prompts to the on-site operators, and automatically store the relevant alarm videos and alarm records to timely and effectively stop the occurrence of unsafe behaviors. The present invention achieves the technical effect of automatically performing safety detection on the crane according to the working status of the crane, thereby solving the technical problem that the crane safety detection cannot be realized according to the state of the crane.

[0006] In order to solve the above problems existing in the prior art, the present invention is implemented through the following technical solutions.

[0007] A first aspect of the present invention provides a safety detection method for a crane, the detection method comprising the following steps: S1. Obtain at least one vehicle image of a preset crane; S2, identifying at least one vehicle feature in the vehicle image, and determining the vehicle state of the preset crane; the vehicle state at least includes a working state, a load state, and a vehicle moving state; S3. Determine a target detection item corresponding to the vehicle state from a plurality of preset detection items, wherein each vehicle state is pre-configured with at least one preset detection item, the preset detection item corresponds to at least one preset detection screen, and the preset detection item is used to perform safety detection on the preset crane according to at least one preset detection screen; S4. When the target detection item fails the safety detection, a preset alarm message is generated.

[0008] Further preferably, in step S2, the vehicle screen includes any one or more combinations of an internal perspective screen, a top perspective screen, a peripheral perspective screen and a driver perspective screen; the internal perspective screen is an image of a cab of the preset crane; the top perspective screen is an image of the area between the vehicle hook of the preset crane and the ground captured at the top of the preset crane; and the peripheral perspective screen is an image of the preset crane captured from a third-person perspective.

[0009] More preferably, the vehicle features in the top perspective image at least include a vehicle hook of the preset crane.

[0010] More preferably, the vehicle features in the peripheral perspective image at least include the preset crane, vehicle legs of the preset crane, a vehicle hook and / or vehicle wheels.

[0011] Further preferably, when the vehicle legs are identified in the peripheral perspective picture, it is detected whether there is a human image in the top perspective picture; when there is a human image in the top perspective picture, it is determined that the vehicle state of the preset crane is the working state.

[0012] More preferably, when it is recognized in the top perspective image that there is a physical connection between the carrier hook and the hanging object, and the peripheral perspective image detects that the position of the carrier hook has changed, the carrier state of the preset crane is determined to be the load state.

[0013] More preferably, when it is recognized in the top perspective image that there is a physical connection between the carrier hook and the hanging object, and the driver perspective image detects that the image is rotating, the carrier state of the preset crane is determined to be the load state.

[0014] More preferably, when the change amplitude of the intersection and intersection ratio of the preset crane and the vehicle wheels in the peripheral viewing angle image within a first preset time range is within a preset range, the vehicle state is determined to be the vehicle moving state.

[0015] More preferably, in step S3, determining the target detection item corresponding to the vehicle state from a plurality of preset detection items specifically refers to: When the preset crane is in the working state, it is determined that the preset detection screen corresponding to the target detection item includes a driver's perspective screen and a peripheral perspective screen, and it is detected whether there is a first preset object in the driver's perspective screen and the peripheral perspective screen. When it is detected that the first preset object does not exist in both the driver's perspective screen and the peripheral perspective screen, it is determined that the target detection item has failed the safety detection.

[0016] More preferably, the first preset object wears a command mark.

[0017] More preferably, in step S3, determining the target detection item corresponding to the vehicle state from a plurality of preset detection items specifically refers to: When the preset crane is in the working state, it is determined that the preset detection screen corresponding to the target detection item includes a driver's perspective screen and a peripheral perspective screen, and it is detected whether there is a second preset object in the driver's perspective screen and the peripheral perspective screen. When it is detected that the second preset object does not exist in both the driver's perspective screen and the peripheral perspective screen, it is determined that the target detection item has failed the safety detection.

[0018] More preferably, the second preset object has both a first guardianship identification and a second guardianship identification.

[0019] More preferably, in step S3, determining the target detection item corresponding to the vehicle state from a plurality of preset detection items specifically refers to: When the preset crane is in the working state, it is determined that the preset detection screen corresponding to the target detection item includes an internal perspective screen and a peripheral perspective screen, and it is detected whether there is a target object in the internal perspective screen. When the target object does not exist in the internal perspective screen, it is detected whether there is a target object with a third preset mark on its head in the peripheral perspective screen. When it is detected that the target object does not exist in the internal perspective screen and the target object with the third preset mark on its head does not exist in the peripheral perspective screen, it is determined that the target detection item has failed the safety detection.

[0020] More preferably, 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.

[0021] More preferably, in step S3, determining the target detection item corresponding to the vehicle state from a plurality of preset detection items specifically refers to: When the preset crane is in the working state, it is determined that the preset detection screen corresponding to the target detection item includes a top perspective screen, and it is detected whether there is a human image in a first preset warning area of ​​the top perspective screen. When the human image is detected in the first preset warning area, it is determined that the target detection item has failed the safety detection.

[0022] More preferably, the first preset warning area is an area pre-marked in the top perspective image where the carrier boom of the preset crane is at risk of falling.

[0023] More preferably, in step S3, determining the target detection item corresponding to the vehicle state from a plurality of preset detection items specifically refers to: When the preset crane is in the working state, it is determined that the preset detection screen corresponding to the target detection item includes a peripheral viewing angle screen, and whether the position changes of the vehicle legs and the corresponding pads of the preset crane in the peripheral viewing angle screen are consistent within the second preset time range. When it is detected that the position changes of the vehicle legs and the corresponding pads within the second preset time range are inconsistent, it is determined that the target detection item has failed the safety detection.

[0024] More preferably, the preset crane includes a plurality of carrier legs, each of the carrier legs is pre-configured with a corresponding pad, and the correspondence between the carrier legs and the pad is determined according to the distance between the carrier legs and the pad in the peripheral perspective image.

[0025] More preferably, in step S3, determining the target detection item corresponding to the vehicle state from a plurality of preset detection items specifically refers to: When the preset crane is in the working state, determine that the preset detection screen corresponding to the target detection item includes a driver's perspective screen and a peripheral perspective screen, detect whether the screen rotation occurs in the driver's perspective, and when the screen rotation occurs in the driver's perspective, detect whether the change ratio of the boom node of the preset crane in the peripheral perspective screen exceeds a first preset ratio threshold value. When it is detected that the screen rotation occurs in the driver's perspective and the change ratio of the boom node exceeds the first preset ratio threshold value, determine that the target detection item has not passed the safety detection.

[0026] More preferably, in step S3, determining the target detection item corresponding to the vehicle state from a plurality of preset detection items specifically refers to: When the preset crane enters the load state from the moving state, it is determined that the preset detection screen corresponding to the target detection item includes a peripheral viewing angle screen, and it is detected whether there is a target warning mark in the peripheral viewing angle screen. When it is detected that there is a target warning mark in the peripheral viewing angle screen, it is determined that the target detection item has passed the safety detection.

[0027] More preferably, in step S3, determining the target detection item corresponding to the vehicle state from a plurality of preset detection items specifically refers to: In the case where the preset crane enters the load state from the moving state, it is determined that the preset detection screen corresponding to the target detection item includes a peripheral perspective screen and a top perspective screen, and it is detected whether there is a pad in the peripheral perspective screen and the top perspective screen. When it is detected that there is a pad in the peripheral perspective screen or the top perspective screen, it is determined that the target detection item has passed the safety detection.

[0028] More preferably, in step S3, determining the target detection item corresponding to the vehicle state from a plurality of preset detection items specifically refers to: When the preset crane is in the load state, determine that the preset detection screen corresponding to the target detection item includes a cab perspective screen; detect whether the target object in the cab perspective screen has a target behavior, and when it is detected that the target object has a target behavior, determine that the target detection item has failed the safety detection.

[0029] More preferably, in step S3, determining the target detection item corresponding to the vehicle state from a plurality of preset detection items specifically refers to: When the preset crane is in the load state, determine that the preset detection screen corresponding to the target detection item includes a cab perspective screen; detect whether there is a target object in the cab perspective screen, and when it is detected that the target object does not exist in the cab perspective screen, determine that the target detection item has failed the safety detection.

[0030] More preferably, in step S3, determining the target detection item corresponding to the vehicle state from a plurality of preset detection items specifically refers to: When the preset crane is in the load state, it is determined that the preset detection screen corresponding to the target detection item includes a top perspective screen, and it is detected whether there is a human image in a second preset warning area of ​​the top perspective screen. When the human image is detected in the second preset warning area, it is determined that the target detection item has failed the safety detection.

[0031] More preferably, the second preset warning area is an area pre-marked in the top perspective image where there is a risk of falling of the carrier hook or hanging object of the preset crane.

[0032] More preferably, in step S3, determining the target detection item corresponding to the vehicle state from a plurality of preset detection items specifically refers to: When the preset crane is in the load state, it is determined that the preset detection screen corresponding to the target detection item includes a peripheral viewing angle screen, and it is detected whether the change ratio of the boom node of the preset crane in the peripheral viewing angle screen exceeds a second preset ratio threshold value. When it is detected that the change ratio of the boom node exceeds the second preset ratio threshold value, it is determined that the target detection item has failed the safety detection.

[0033] More preferably, in step S3, determining the target detection item corresponding to the vehicle state from a plurality of preset detection items specifically refers to: When the preset crane is in the load state, it is determined that the preset detection screen corresponding to the target detection item includes a peripheral viewing angle screen, and it is detected whether there are slings on the big hook and the small hook of the preset crane in the peripheral viewing angle screen. When it is detected that there are slings on both the big hook and the small hook of the preset crane, it is determined that the target detection item has not passed the safety detection.

[0034] More preferably, in step S3, determining the target detection item corresponding to the vehicle state from a plurality of preset detection items specifically refers to: When the preset crane is in the load state, it is determined that the preset detection screen corresponding to the target detection item includes a peripheral viewing angle screen, and the indicator light of the preset crane in the peripheral viewing angle screen is detected, wherein when it is detected that the indicator light indicates overload, it is determined that the target detection item has failed the safety detection.

[0035] More preferably, in step S3, determining the target detection item corresponding to the vehicle state from a plurality of preset detection items specifically refers to: When the preset crane is in the moving state, it is determined that the preset detection screen corresponding to the target detection item includes a peripheral viewing angle screen, and whether the carrier hook of the preset crane in the peripheral viewing angle screen is hung with a sling, and when it is detected that the carrier hook is hung with the sling, it is determined that the target detection item has failed the safety detection.

[0036] A second aspect of the present invention provides a safety detection device for a crane, the device comprising: An acquisition module, used to acquire at least one vehicle image of a preset crane; An identification module, used to identify at least one vehicle feature in the vehicle picture, and determine the vehicle state of the preset crane, wherein the vehicle state includes at least a working state, a load state, and a vehicle moving state; A determination module, used to determine a target detection item corresponding to the vehicle state from a plurality of preset detection items, wherein each vehicle state is pre-configured with at least one preset detection item, the preset detection item corresponds to at least one preset detection screen, and the preset detection item is used to perform safety detection on the preset crane according to at least one preset detection screen; The generating module is used to generate preset alarm information when the target detection item fails the safety detection.

[0037] A third aspect of the present invention provides a readable storage medium, which is used to store a program, wherein when the program is running, the readable storage medium is controlled to execute the crane safety detection method described in the first aspect of the present invention.

[0038] A fourth aspect of the present invention provides an electronic device, comprising a memory and a processor, wherein the processor is used to run a program stored in the processor, wherein the program, when running, executes the crane safety detection method described in the first aspect of the present invention.

[0039] In an embodiment of the present invention, at least one vehicle screen of a preset crane is obtained; vehicle features in at least one vehicle screen are identified to determine the vehicle state of the preset crane, wherein the vehicle state includes at least: working state, load state and moving state; a target detection item corresponding to the vehicle state is determined from a plurality of preset detection items, wherein each vehicle state is pre-configured with at least one preset detection item, the preset detection item corresponds to at least one preset detection screen, and the preset detection item is used to perform a safety detection on the preset crane according to at least one preset detection screen; in the case where the target detection item fails the safety detection, a preset alarm message is generated, thereby achieving the technical effect of automatically performing a safety detection on the crane according to the working state of the crane, thereby solving the technical problem of being unable to implement crane safety detection according to the crane state.

[0040] Compared with the prior art, the beneficial technical effects brought by the present invention are as follows: 1. According to the working status of the crane, the automatic safety detection of the crane operation process is realized intelligently, accurately and comprehensively.

[0041] 2. It realizes real-time intelligent identification and alarm prompts of the crane operation process, improves the current situation of relying on a large amount of manpower and material resources for risk control, improves the intelligence level of risk management at the operation site, and promotes the transformation of safety supervision methods from manual to intelligent. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 is a flow chart of a crane safety detection method according to an embodiment of the present invention; Figure 2 is a schematic diagram of an optional intelligent recognition system according to an embodiment of the present invention; Figure 3 is a schematic diagram of a safety detection device for a crane according to an embodiment of the present invention; Figure 4 It is a structural block diagram of a computer terminal according to an embodiment of the present invention. DETAILED DESCRIPTION

[0043] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0044] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0045] According to an embodiment of the present invention, an embodiment of a crane safety detection method is provided. It should be noted that the steps shown in the flowchart of the accompanying 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 can be executed in an order different from that shown here.

[0046] Example 1 As a preferred embodiment of the present invention, refer to the attached specification Figure 1 As shown, Figure 1 is a flow chart of a crane safety detection method according to an embodiment of the present invention, the method comprising the following steps: Step S1, obtaining at least one vehicle image of a preset crane; Step S2, identifying vehicle features in at least one vehicle image, and determining a vehicle state of a preset crane, wherein the vehicle state includes at least: a working state, a loading state, and a moving state; Step S3, determining a target detection item corresponding to the vehicle state from a plurality of preset detection items, wherein each vehicle state is pre-configured with at least one preset detection item, the preset detection item corresponds to at least one preset detection screen, and the preset detection item is used to perform safety detection on a preset crane according to the at least one preset detection screen; Step S4: if the target detection item fails the safety detection, a preset alarm message is generated.

[0047] In an embodiment of the present invention, at least one vehicle screen of a preset crane is obtained; vehicle features in at least one vehicle screen are identified to determine the vehicle state of the preset crane, wherein the vehicle state includes at least: working state, load state and moving state; a target detection item corresponding to the vehicle state is determined from a plurality of preset detection items, wherein each vehicle state is pre-configured with at least one preset detection item, the preset detection item corresponds to at least one preset detection screen, and the preset detection item is used to perform a safety detection on the preset crane according to at least one preset detection screen; in the case where the target detection item fails the safety detection, a preset alarm message is generated, thereby achieving the technical effect of automatically performing a safety detection on the crane according to the working state of the crane, thereby solving the technical problem of being unable to implement crane safety detection according to the crane state.

[0048] Example 2 As another preferred embodiment of the present invention, this embodiment is a further detailed elaboration and supplement to the technical solution of the present invention based on the above-mentioned embodiment 1. In this embodiment, in the above-mentioned step S2, the vehicle screen includes any one or more combinations of an internal perspective screen, a top perspective screen, a peripheral perspective screen and a driver perspective screen; the internal perspective screen is an image of the cab of the preset crane; the top perspective screen is an image of the area between the vehicle hook of the preset crane and the ground collected at the top of the preset crane; the peripheral perspective screen is an image of the preset crane collected from a third-person perspective. The driver perspective screen is an image of the driver's perspective in the cab.

[0049] In the above step S3, the preset detection pictures include: an internal viewing angle picture, a top viewing angle picture, a driver viewing angle picture, and a peripheral viewing angle picture.

[0050] As an example, the top perspective image is collected by a camera set at the top of the vehicle boom of a preset crane, and the camera is located on the same plumb line as the vehicle hook.

[0051] In the above step S2, the vehicle features include: a vehicle hook, a vehicle leg, a vehicle boom, a vehicle wheel, etc. of a preset crane.

[0052] In the above step S2, the vehicle state includes at least: working state, loading state and moving state. It is preset that the crane is in different vehicle states, and the judgment criteria of its safety detection are different.

[0053] For example, the preset crane can be moved with the lifting attachments folded away, or it can be deployed in a designated work area, and the preset crane can carry the load for lifting after it is deployed.

[0054] Optionally, the working status is used to indicate that the preset crane has arrived at the working area and is deployed, ready for subsequent lifting. The most notable feature of the working status is that the legs of the preset crane are deployed to increase the stability of the lifting. The working status of the preset crane can be determined based on the vehicle legs of the preset crane, and the vehicle characteristics used to determine the working status are the vehicle legs.

[0055] Optionally, the load state indicates that the preset crane has arrived at the working area and completed deployment, and there is a physical connection between the carrier hook of the preset crane and the suspended object. Then, on the basis that the preset crane has met the deployment state, it can be determined whether the preset crane is in a load state based on whether there is a physical connection between the carrier hook of the preset crane and the suspended object. The carrier feature used to determine the load state is the connection relationship between the carrier hook and the suspended object.

[0056] Optionally, the moving state is used to indicate that the preset crane is moved by means of vehicle wheels. In this state, the legs of the preset crane must be retracted, and the state of the vehicle wheels will change. Further, on the basis that the preset crane is not in the deployed state, it can be determined whether the preset crane is in the moving state according to the vehicle wheels of the preset crane; and further, it is determined that the vehicle characteristics of the moving state are the characteristics of the vehicle wheels, such as changes in the vehicle wheels, or changes in the intersection-combination ratio of the vehicle wheels and the preset crane.

[0057] In the above step S3, different vehicle states correspond to different preset detection items. By selecting at least one preset detection item corresponding to the vehicle state and detecting the target items one by one, accurate safety detection of the preset crane can be achieved, thereby ensuring the operation safety of the preset crane.

[0058] For example, when the preset crane is in a working state, the preset crane is allowed to adjust the length of the carrier boom after unfolding the carrier legs; while when the preset crane is in a loaded state, the preset crane is not allowed to adjust the length of the carrier boom. Therefore, the judgment criteria for the safety inspection of the preset crane are different when the preset crane is in different carrier states, and different preset inspection items can be selected according to the carrier state of the preset crane to carry out safety inspection on the preset crane.

[0059] Optionally, in the case of obtaining a peripheral perspective image of a preset crane, obtaining at least one vehicle image of the preset crane includes: obtaining a first preset operation image, wherein the first preset operation image includes multiple operation areas of the preset crane; performing image segmentation on the operation image to obtain multiple preset segmented areas; and identifying the preset segmented areas including the preset crane as the peripheral perspective image of the preset crane.

[0060] In the above-mentioned embodiment of the present invention, the first preset operation screen includes multiple operation areas of the preset crane, and each operation area allows the preset crane to be deployed and hoisted in the operation area. However, not all the multiple operation areas have the preset crane to work. Therefore, in the first preset operation screen, the operation area where the preset crane exists can be intercepted to determine the peripheral perspective screen, thereby realizing the determination of the peripheral perspective screen.

[0061] Optionally, in the case of obtaining a peripheral perspective picture of a preset crane, obtaining at least one vehicle picture of the preset crane includes: obtaining at least one second preset operation picture, wherein each second preset operation picture corresponds to an operation area, and the preset crane is allowed to be deployed in the operation area; identifying the existence of a preset operation picture of the preset crane as a peripheral perspective picture of the preset crane.

[0062] In the above-mentioned embodiment of the present invention, the pictures of multiple working areas are respectively obtained as the second preset working pictures. Each working area allows the preset crane to be deployed and lifted in the working area. However, multiple working areas do not necessarily have the preset crane to work. Therefore, among the multiple second preset working pictures, the second preset working picture with the preset crane can be selected as the peripheral perspective picture of the preset crane, thereby realizing the determination of the peripheral perspective picture.

[0063] As an optional embodiment, identifying vehicle features in at least one vehicle screen and determining the vehicle status of a preset crane includes: identifying a top perspective screen and a peripheral perspective screen in at least one vehicle screen, wherein the top perspective screen is an image of the area between a vehicle hook of the preset crane and the ground captured at the top of the preset crane, and the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; identifying vehicle features in the peripheral perspective screen, wherein the vehicle features include at least: vehicle legs of the preset crane; when the vehicle legs are identified in the peripheral perspective screen, detecting whether there is a human image in the top perspective screen; when there is a human image in the top perspective screen, determining that the vehicle status of the preset crane is a working status.

[0064] In the above-mentioned embodiment of the present invention, when the vehicle state is in the working state, the most notable feature is that the legs of the preset crane are unfolded to increase the stability of the lifting. The working state of the preset crane can be determined based on the vehicle legs of the preset crane, and then the vehicle legs of the preset crane are identified through the peripheral perspective image and the top perspective image. If the vehicle legs of the preset crane are identified, it means that the vehicle legs of the preset crane have been unfolded, and it can be determined that the preset crane is in the working state.

[0065] As an optional embodiment, identifying vehicle features in at least one vehicle screen and determining the vehicle state of a preset crane includes: identifying a top perspective screen and a peripheral perspective screen in at least one vehicle screen, wherein the top perspective screen is an image of the area between a vehicle hook of the preset crane and the ground captured at the top of the preset crane, and the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; identifying vehicle features in the top perspective screen and the peripheral perspective screen, wherein the vehicle features include at least: a vehicle hook of the preset crane; when it is recognized in the top perspective screen that there is a physical connection between the vehicle hook and the suspended object, and the peripheral perspective screen detects that the position of the vehicle hook has changed, determining that the vehicle state of the preset crane is a load state.

[0066] In the above-mentioned embodiment of the present invention, when the preset crane is in a loaded state, the preset crane will bear the weight of the suspended object and move the suspended object. If the preset crane is to bear the weight of the suspended object, there needs to be a physical connection between the suspended object and the carrier hook of the preset crane. During the movement of the suspended object, the carrier hook will also move with the suspended object. Therefore, by detecting the connection relationship between the carrier hook of the preset crane and the suspended object, as well as the movement of the carrier hook, it can be determined whether the preset crane is in a loaded state.

[0067] Optionally, the change in the position of the carrier hook includes: the carrier hook moving up and down relative to the ground, the carrier hook swinging, and the carrier hook rotating relative to a preset rotation center of the crane.

[0068] Optionally, when the carrier hook swings or rotates relative to a preset rotation center of the crane, the hanging object connected to the carrier hook will appear to move left and right in the peripheral perspective image.

[0069] As an optional embodiment, identifying vehicle features in at least one vehicle screen and determining the vehicle state of a preset crane includes: identifying a top perspective screen and a driver perspective screen in at least one vehicle screen, wherein the top perspective screen is an image of the area between a vehicle hook of the preset crane and the ground captured at the top of the preset crane; identifying vehicle features in the top perspective screen, wherein the vehicle features include at least: a vehicle hook of the preset crane; and determining that the vehicle state of the preset crane is a load state when a physical connection between the vehicle hook and the suspended object is identified in the top perspective screen and the driver perspective screen detects that the screen is rotated.

[0070] In the above-mentioned embodiment of the present invention, when the preset crane is in a loaded state, the preset crane will bear the weight of the suspended object and move the suspended object. If the preset crane is to bear the weight of the suspended object, there needs to be a physical connection between the suspended object and the carrier hook of the preset crane. During the movement of the suspended object, the carrier hook will also move with the suspended object. Furthermore, when the carrier boom of the preset crane is rotated, the suspended object connected to the carrier hook may also move. During the rotation of the carrier boom, the driver's perspective screen will rotate. Therefore, by detecting the connection relationship between the carrier hook of the preset crane and the suspended object, and whether the driver's perspective screen rotates, it can be determined whether the preset crane is in a loaded state.

[0071] Optionally, in the top perspective image, it can be identified whether there is a hanging object between the hook and the ground. If there is no hanging object, it means that there is no physical connection between the hanging object and the carrier hook. If there is a hanging object, the connecting parts (such as slings) between the hanging object and the carrier hook are detected in the hook image. If no connecting parts are detected, it means that there is no physical connection between the hanging object and the carrier hook. Otherwise, it can be determined that there is a physical connection between the hanging object and the carrier hook.

[0072] As an optional embodiment, identifying vehicle features in at least one vehicle screen and determining the vehicle state of a preset crane includes: identifying a peripheral perspective screen in at least one vehicle screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; identifying vehicle features in the peripheral perspective screen, wherein the vehicle features include at least: a preset crane and vehicle wheels of the preset crane; and determining that the vehicle state is a moving state when the amplitude of the intersection and intersection ratio of the preset crane and the vehicle wheels in the peripheral perspective screen within a first preset time range is within a preset range.

[0073] In the above-mentioned embodiment of the present invention, when the change amplitude of the intersection-and-joint ratio of the preset crane and the vehicle wheels in the peripheral perspective picture within the first preset time range is within a preset range, determining that the vehicle state is the vehicle moving state includes: acquiring a first time sequence picture of the peripheral perspective picture, and identifying the preset crane and the vehicle wheels of the preset crane in the first time sequence picture; acquiring the peripheral perspective picture of the preset crane at a preset time interval to obtain a second time sequence picture; identifying the preset crane and the vehicle wheels of the preset crane in the second time sequence picture; determining that the vehicle state is the vehicle moving state when the change amplitude of the intersection-and-joint ratio of the preset crane and the vehicle wheels of the preset crane in the first time sequence picture and the second time sequence picture is within a preset range, thereby realizing the determination of the vehicle moving state.

[0074] Optionally, the preset time interval is one frame.

[0075] Optionally, when the preset crane is in the state of moving, the preset crane can be moved by means of carrier wheels. For example, the preset crane can be moved from a first working area to a second working area. In the process of moving, the carrier boom and carrier legs of the preset crane must be recovered, and the preset crane needs to open the carrier legs first when deploying, and will finally retract the carrier legs when recovering. Therefore, if the carrier legs of the preset crane are not detected, it means that the preset crane is very likely to be in a moving state, and then the characteristics of the carrier wheels of the preset crane can be extracted, and it can be judged whether the preset crane is in the state of moving according to the changes in the characteristics of the carrier wheels.

[0076] Optionally, Intersection over Union (IOU) is a concept used in target detection. IOU calculates the overlap rate of the "predicted bounding box" and the "real bounding box", that is, the ratio of their intersection and union. Through the peripheral perspective images captured at different times at a fixed position, if the preset crane moves, the IOU of the preset crane and the vehicle wheels at different times will change, and then according to the change of the IOU of the vehicle wheels and the preset crane at different times, it can be judged whether the preset crane is in a moving state, wherein the IOU of the vehicle wheels and the preset crane at different times can be determined based on multiple vehicle images in a chronological order.

[0077] As an optional embodiment, determining the target detection item corresponding to the vehicle status from multiple preset detection items includes: when a preset crane is in a working state, determining that the preset detection screen corresponding to the target detection item includes: a driver's perspective screen and a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; detecting whether there is a first preset object in the driver's perspective screen, wherein the first preset object wears a command mark, and when it is detected that the first preset object exists in both the driver's perspective screen and the peripheral perspective screen, determining that the target detection item has passed the safety detection.

[0078] In the above-mentioned embodiment of the present invention, during the crane operation process, it is necessary to configure a commander for the preset crane, and it is necessary to ensure that the commander is within the field of vision of the driver of the preset crane. Therefore, by detecting whether there is a first preset object wearing a command mark in the driver's perspective screen and the peripheral perspective screen, it is possible to detect whether a commander is configured for the preset crane. Further, when it is detected that there is no first preset object wearing a command mark in both the driver's perspective screen and the peripheral perspective screen, it is determined that no commander is configured for the preset crane, and further it is determined that the target crane has failed the safety detection of the target detection item.

[0079] Optionally, the first preset object is a commander, and the command identifier is a modification watch worn by the commander or a warning symbol worn by the commander.

[0080] As an optional embodiment, determining the target detection item corresponding to the vehicle status from multiple preset detection items includes: when a preset crane is in a working state, determining the preset detection screen corresponding to the target detection item includes: a driver's perspective screen and a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; detecting whether there is a second preset object in both the driver's perspective screen and the peripheral perspective screen, wherein the second preset object has both a first monitoring identifier and a second monitoring identifier, and when it is detected that the second preset object does not exist in both the driver's perspective screen and the peripheral perspective screen, determining that the target detection item has failed the safety detection.

[0081] In the above-mentioned embodiment of the present invention, during the crane operation process, it is necessary to configure a supervisor for the preset crane, and it is necessary to ensure that the supervisor is within the field of vision of the driver of the preset crane. Therefore, by detecting whether there is a second preset object having both the first supervisory identification and the second supervisory identification in the driver's perspective screen and the peripheral perspective screen, it is possible to detect whether a supervisor is configured for the preset crane. Further, when it is detected that there is no second preset object in both the driver's perspective screen and the peripheral perspective screen, it is determined that no supervisor is configured for the preset crane, and further, it is determined that the target crane has failed the safety detection of the target detection item.

[0082] Optionally, the second preset object is a guardian, the first guardianship identification can be a safety helmet worn by the guardian, such as a white safety helmet, the second guardianship identification can be a guardianship armband worn by the guardian, and the guardian needs to wear both the safety helmet and the guardianship armband at the same time.

[0083] As an optional embodiment, determining the target detection item corresponding to the vehicle state from multiple preset detection items includes: when a preset crane is in a working state, determining that the preset detection screen corresponding to the target detection item includes: an internal perspective screen and a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; detecting whether there is a target object in the internal perspective screen, and when there is no target object in the internal perspective screen, detecting whether there is a target object with a third preset mark on its head in the peripheral perspective screen, wherein the target object represents an image of a driver of the preset crane, and the third preset mark represents a helmet worn by the driver, and when it is detected that there is no target object in the internal perspective screen, and when there is no target object with the third preset mark on its head in the peripheral perspective screen, determining that the target detection item has failed the safety inspection.

[0084] In the above-mentioned embodiment of the present invention, when the preset crane is in working condition, 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 working condition, it is possible to detect whether the driver is in the cab through the cab perspective image, and further, when it is detected that the driver is not in the cab, it is possible to detect whether the driver is wearing a safety helmet when leaving the cab through the peripheral perspective image.

[0085] As an optional embodiment, determining, from multiple preset detection items, a target detection item corresponding to the vehicle status includes: when a preset crane is in working condition, determining a preset detection screen corresponding to the target detection item includes: a top perspective screen, wherein the top perspective screen is an image of the area between a vehicle 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 first preset warning area of ​​the top perspective screen, wherein the first preset warning area is an area pre-marked in the top perspective screen where the vehicle boom of the preset crane is at risk of falling, and when a human image is detected in the first preset warning area, determining that the target detection item has failed the safety detection.

[0086] In the above embodiment of the present invention, when the preset crane is in working condition, the carrier boom of the preset crane will be adjusted. In order to avoid the risk of falling during the adjustment of the carrier boom, the top perspective image can be used to detect whether there is a person entering the first preset warning area projected by the carrier boom.

[0087] Optionally, the first preset warning area is determined based on the projection area of ​​a preset crane on the projection area of ​​the carrier boom on the ground, the projection area of ​​the carrier boom on the ground is identified in the top perspective image, and then a warning line is set for the projection area at a preset distance, and the area surrounded by the warning line is the first preset warning area.

[0088] As an optional embodiment, determining the target detection item corresponding to the vehicle state from multiple preset detection items includes: when a preset crane is in a working state, determining the preset detection screen corresponding to the target detection item includes: a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; detecting whether the position changes of the vehicle legs and the corresponding pads of the preset crane in the peripheral perspective screen are consistent within a second preset time range, wherein the preset crane includes multiple vehicle legs, each vehicle leg is pre-configured with a corresponding pad, and the correspondence between the vehicle legs and the pads is determined according to the distance between the vehicle legs and the pads in the peripheral perspective screen; when it is detected that the position changes of the vehicle legs and the corresponding pads within the second preset time range are inconsistent, it is determined that the target detection item has failed the safety detection.

[0089] In the above embodiment of the present invention, when the preset crane is in working state, the carrier legs and the pads need to be tied together by steel wire ropes. If the position changes of the carrier legs and the corresponding pads are inconsistent within the second preset time range, it means that the carrier legs and the pads are not tied together by steel wire ropes.

[0090] Optionally, the second preset time may be determined by a preset state for the crane to return from a load state to a working state.

[0091] As an optional embodiment, determining the target detection item corresponding to the vehicle status from multiple preset detection items includes: when a preset crane is in a working state, determining the preset detection screen corresponding to the target detection item includes: a driver's perspective screen and a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; detecting whether the screen rotates from the driver's perspective, and when the screen rotates from the driver's perspective, detecting whether the change ratio of the boom node of the preset crane in the peripheral perspective screen exceeds a first preset ratio threshold; when it is detected that the screen rotates from the driver's perspective and the change ratio of the boom node exceeds the first preset ratio threshold, determining that the target detection item has failed the safety detection.

[0092] In the above embodiment of the present invention, when it is detected that the image rotation occurs in the driver's perspective and the change ratio of the boom node exceeds the first preset ratio threshold, it means that the turntable rotates and the telescopic arm operates at the same time, and therefore, it does not meet the safety detection requirements.

[0093] As an optional embodiment, determining, from multiple preset detection items, a target detection item corresponding to the vehicle state includes: when a preset crane enters a loading state from a moving state, determining a preset detection screen corresponding to the target detection item includes: a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; detecting whether there is a target warning sign in the peripheral perspective screen, wherein, when a target warning sign is detected in the peripheral perspective screen, determining that the target detection item has passed the safety detection.

[0094] In the above-mentioned embodiment of the present invention, after the preset crane moves to the working area, it is necessary to arrange target warning signs such as warning tapes / fences / piles in the working area, and then when the presence of target warning signs is detected in the peripheral perspective image, it is determined that the preset crane meets the safety requirements, and then it is determined that the preset crane has passed the safety inspection of the target detection item.

[0095] As an optional embodiment, determining, from multiple preset detection items, a target detection item corresponding to the vehicle state includes: when a preset crane enters a loading state from a moving state, determining that a preset detection screen corresponding to the target detection item includes: a peripheral perspective screen and a top perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective, and the top perspective screen is an image of the area between the vehicle hook of the preset crane and the ground captured at the top of the preset crane; detecting whether there is a pad in the peripheral perspective screen or the top perspective screen, wherein when it is detected that there is a pad in the peripheral perspective screen or the top perspective screen, determining that the target detection item has passed the safety detection.

[0096] In the above embodiment of the present invention, after the preset crane moves to the working area, it is necessary to arrange pads at the leg positions of the preset crane. Therefore, when the presence of pads is detected in the peripheral perspective image or the top perspective image, it is determined that the pads have been provided for the preset crane, and then it is determined that the preset crane has passed the safety inspection of the target detection item.

[0097] As an optional embodiment, determining, from a plurality of preset detection items, a target detection item corresponding to the vehicle state includes: when the preset crane is in a load state, determining a preset detection screen corresponding to the target detection item includes: a cab perspective screen; detecting whether the target object in the cab perspective screen has a target behavior, wherein, when it is detected that the target object has a target behavior, determining that the target detection item has failed the safety detection.

[0098] In the above-mentioned embodiment of the present invention, when the preset crane is in a loaded state, the target behavior of the target object that violates the safety regulations can be detected through the cab perspective image, and then when the target behavior of the target object is detected, it is determined that the preset crane has passed the safety inspection of the target detection item.

[0099] Optionally, the target behavior may be the driver's behavior of playing with a mobile phone. If the driver plays with the mobile phone when the preset crane is in a loaded state, this behavior does not meet the safety operation requirements of the preset crane, and an alarm message may be generated.

[0100] As an optional embodiment, determining, from multiple preset detection items, a target detection item corresponding to the vehicle state includes: when the preset crane is in a load state, determining a preset detection screen corresponding to the target detection item includes: a cab perspective screen; detecting whether there is a target object in the cab perspective screen, wherein, when it is detected that there is no target object in the cab perspective screen, determining that the target detection item has failed the safety detection.

[0101] In the above-mentioned embodiment of the present invention, when the preset crane is in a loaded state, the driver is not allowed to leave the cab. Therefore, it is possible to detect whether the target object is in the cab through the cab perspective screen, and then determine that the preset crane has not passed the safety detection of the target detection item when it is detected that the target object does not exist in the cab perspective screen.

[0102] As an optional embodiment, determining, from multiple preset detection items, a target detection item corresponding to the vehicle state includes: when a preset crane is in a loaded state, determining a preset detection screen corresponding to the target detection item includes: a top perspective screen, wherein the top perspective screen is an image of the area between a vehicle hook of the preset crane and the ground captured at the top of the preset crane; detecting whether there is a human image in a second preset warning area of ​​the top perspective screen, wherein the second preset warning area is a pre-marked area in the top perspective screen where there is a risk of falling of the vehicle hook of the preset crane or the suspended object, and when a human image is detected in the second preset warning area, determining that the target detection item has failed the safety detection.

[0103] In the above embodiment of the present invention, when the preset crane is in a loaded state, in order to avoid the risk of falling of the vehicle hook and the hanging object, the top perspective image can be used to detect whether there is a person entering the second preset warning area projected by the vehicle hook and the hanging object.

[0104] Optionally, the second preset warning area is determined based on the projection area of ​​the projection area of ​​the carrier hook and the hanging object of the preset crane on the ground, and the projection area of ​​the projection area of ​​the carrier hook and the hanging object on the ground is identified in the top perspective picture, and then a warning line is set for the projection area according to a preset distance, and the area surrounded by the warning line is the second preset warning area.

[0105] As an optional embodiment, determining, from multiple preset detection items, a target detection item corresponding to the vehicle state includes: when a preset crane is in a load state, determining a preset detection screen corresponding to the target detection item includes: a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; detecting whether a change ratio of a boom node of the preset crane in the peripheral perspective screen exceeds a second preset ratio threshold, and when it is detected that the change ratio of the boom node exceeds the second preset ratio threshold, determining that the target detection item has failed the safety detection.

[0106] In the above-mentioned embodiment of the present invention, when the preset crane is in a loaded state, in order to avoid the risk of hanging objects falling and the preset crane tipping over, it is not allowed to adjust the carrier boom of the preset crane. Therefore, by detecting whether the change ratio of the boom node exceeds a second preset ratio threshold through the peripheral perspective image, it can be determined whether the preset crane adjusts the carrier boom under the loaded state.

[0107] As an optional embodiment, determining, from multiple preset detection items, a target detection item corresponding to the vehicle state includes: when a preset crane is in a loaded state, determining a preset detection screen corresponding to the target detection item includes: a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; detecting whether there are slings on the big hook and the small hook of the preset crane in the peripheral perspective screen, wherein, when it is detected that both the big hook and the small hook of the preset crane have slings, determining that the target detection item has failed the safety inspection.

[0108] In the above embodiment of the present invention, when it is detected that the large hook and the small hook of the preset crane have slings at the same time, it means that the slings on the large hook of the preset crane have not been removed, and the small hook is used for lifting, thereby determining that the preset crane has not passed the safety inspection of the target detection item.

[0109] As an optional embodiment, determining, from a plurality of preset detection items, a target detection item corresponding to the vehicle status includes: when a preset crane is in a load state, determining a preset detection screen corresponding to the target detection item includes: a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; detecting an indicator light of the preset crane in the peripheral perspective screen, wherein, when it is detected that the indicator light indicates overload, determining that the target detection item has failed the safety detection.

[0110] In the above embodiment of the present invention, the indicator light is used to indicate whether the preset crane exceeds the working load, and then when it is detected that the indicator light indicates overload, it is determined that the preset crane has not passed the safety detection of the target detection item.

[0111] As an optional embodiment, determining, from multiple preset detection items, a target detection item corresponding to the vehicle status includes: when a preset crane is in a moving state, determining a preset detection screen corresponding to the target detection item includes: a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; detecting whether a vehicle hook of the preset crane in the peripheral perspective screen is hung with a sling, wherein, when it is detected that the vehicle hook is hung with a sling, determining that the target detection item has failed the safety inspection.

[0112] The above-mentioned embodiment of the present invention can avoid the risk of the hook and sling of the preset crane swinging during the moving process when the preset crane is in the state of being moved. Therefore, it can be detected through the peripheral perspective image whether the carrier hook is hung with the sling, and then when it is detected that the carrier hook is hung with the sling, it is determined that the preset crane has not passed the safety inspection of the target detection item.

[0113] Example 3 As another preferred embodiment of the present invention, refer to the attached specification Figure 2 As shown, this embodiment provides an intelligent recognition system. Figure 2 is a schematic diagram of an optional intelligent recognition system according to an embodiment of the present invention, such as Figure 2 As shown, the vehicle status of the crane can be determined and safety detected through internal perspective, top perspective, driver perspective and peripheral perspective.

[0114] Optionally, the peripheral perspective picture may be a third perspective picture of a preset crane.

[0115] Optionally, the top perspective image may be an image of the area between the vehicle hook and the ground captured at the top of the boom of a preset crane.

[0116] Optionally, the internal perspective picture is used to capture the image of the cab of a preset crane.

[0117] Optionally, the driver's perspective picture is used to capture the driver's perspective image in the cab.

[0118] Optionally, the intelligent identification system is used to perform the following safety checks: the crane driver drives the crane to the vicinity of the object to be hoisted, then extends the crane legs and places jack pads under the legs; after lowering the legs, the driver enters the crane operating room, extends the boom, and lowers the hook; other workers on site put one end of the sling on the hook and fix the other end of the sling on the object; after fixing the sling, the workers exit the hoisting range, the crane driver raises the hook, operates the crane to hoist the object to the designated location, and during the hoisting process, a worker pulls the traction rope to control the direction of the object; after the object reaches the designated location above the air, the driver slowly lowers the hook, and when the object is close to the ground, the worker enters the hoisting range to stabilize the direction and position of the object, and then the driver slowly lowers the hook until the object is placed on the ground, the worker removes the rigging at the end of the object, and the hoisting is completed.

[0119] Optionally, after all the objects at one location are hoisted, the driver retracts the boom, retracts the outriggers, drives the crane to the next location where hoisting is required, and enters the next work process.

[0120] Optionally, the vehicle state includes at least: an unfolded state, a load state and a moving state, wherein, in the unfolded state, when the peripheral perspective detects the outriggers, it means that the crane has opened the unfolded state; load state: when the top picture detects the hanging object, the driver's perspective detects that the picture rotates or the peripheral picture detects that the hook position changes up and down; moving state: the peripheral picture detects the crane and the wheels, and uses IOU to match the crane and the wheels; when the IOU change of one wheel in the current and rear frames is within a certain range, it is considered that the crane is moving.

[0121] Optionally, in the above step S3, according to different vehicle states, the safety detection of the preset crane can be implemented through the following multiple preset detection items.

[0122] Optionally, there is no dedicated person in charge, and the commander is not wearing an armband or warning clothing: when the crane is in the deployed state, if the armband or warning clothing is not detected in the driver's perspective, it is assumed that the crane has failed the safety inspection.

[0123] Optionally, no supervisor is arranged or the supervisor does not wear an armband: when the crane is in the deployed state, if the driver's perspective does not detect that a white safety helmet and an armband appear on the same person at the same time, it is assumed that the crane has failed the safety inspection.

[0124] Optionally, if the warning tape / fence / pile is not pulled: the crane moves to a position once and enters a load state to start detection, and stops detection when the target is detected.

[0125] Optionally, the driver leaves the operating room without wearing a helmet: when the crane is in the deployed state, the operating room screen (i.e., the internal perspective screen) does not detect a person, and the peripheral screen detects a head (i.e., the peripheral screen detects a driver without a helmet), then it is assumed that the crane has failed the safety inspection.

[0126] Optionally, the driver uses a mobile phone in the operator's cab: when the crane is in a loaded state, if the mobile phone is detected on the operator's cab screen (i.e., the driver is playing with the mobile phone while in a loaded state), it is assumed that the crane has failed the safety inspection.

[0127] Optionally, unauthorized entry into the warning area: When the crane is in a loaded state, the top screen marks the danger range and warning area around the suspended object. When the detection frame of the person in the screen intersects with the warning area, it is determined that the person has entered the warning area, and the crane is assumed to have failed the safety inspection.

[0128] Optionally, personnel pass under the boom or suspended objects: when the crane is in the deployed state, the top screen marks the danger range and warning area of ​​the boom in the middle of the screen. When the detection box of the person in the screen and the warning area intersect, it is determined that the person is passing under the boom, and the crane is assumed to have failed the safety inspection.

[0129] Optionally, the jack pad is tied to the crane leg with a steel wire rope: when the crane enters the deployed state, the IDs of the legs and pads in the peripheral image are obtained using the sort tracking algorithm, and the legs and pads that are close in position are matched. When the crane is not in a loaded state, if the positions of the legs and pads in the previous and next frames of the peripheral image change and the amount of change is consistent, it is considered that the jack pad is tied to the crane leg with a steel wire rope.

[0130] Optionally, a lifting device is hung on the hook to move the vehicle: ResNet18 is used to perform binary classification on the image around the hook in the peripheral image. If the binary classification result is that there is a lifting device and the crane is detected to be moving, it is determined that a lifting device is hung on the hook to move the vehicle (that is, it is assumed that the crane has moved under the load state).

[0131] Optionally, without using jack pads: the crane moves to a position once and enters the load state to open the detection until the pad closing detection is detected.

[0132] Optionally, crane load arm extension operation: when the crane is in a loaded state, the peripheral image is calculated to detect whether the node position on the boom has changed. If the change ratio reaches a certain threshold, it is determined to be a crane load arm extension operation, and the crane is preset to have failed the safety test.

[0133] Optionally, the turntable rotates and the telescopic arm operates at the same time: when the crane is in the deployed state and the driver's perspective image detects that the image is rotating, the peripheral image detects whether the node position on the boom has changed. If the change ratio reaches a certain threshold, it is determined that the turntable rotates and the telescopic arm operates at the same time, and it is preset that the crane has not passed the safety test.

[0134] Optionally, the suspended object is suspended in the air and the driver leaves the operating room: when the crane is in a loaded state, if no person is detected in the operating room screen, it is determined that the suspended object is suspended in the air and the driver leaves the operating room, and it is assumed that the crane has failed the safety inspection.

[0135] Optionally, the sling of the crane's large hook is not removed, and a small hook is used for lifting: when the crane is in a loaded state, ResNet18 is used to perform binary classification on the image around the hook in the peripheral image. If the classification structure of the large hook and the small hook are both with slings, it is determined that the sling of the crane's large hook has not been removed, and a small hook is used for lifting, and it is assumed that the crane has not passed the safety test.

[0136] Optionally, the lifting system is overloaded: when the crane is in a loaded state, ResNet18 is used to classify the three-color indicator light area of ​​the crane in the peripheral image into six categories. If the classification result is that the indicator light shows an overload, the lifting system is determined to be overloaded, and the crane is preset to have failed the safety test.

[0137] Example 4 As another preferred embodiment of the present invention, refer to the attached specification Figure 3 As shown, this embodiment discloses a safety detection device for a crane. It should be noted that the safety detection device for the crane can be used to execute the safety detection method for the crane in the embodiment of the present invention, and the safety detection method for the crane in the embodiment of the present invention can be executed in the safety detection device for the crane.

[0138] Figure 3 is a schematic diagram of a safety detection device for a crane according to an embodiment of the present invention. Figure 3As shown, the device may include: an acquisition module 30, used to acquire at least one vehicle image of a preset crane; an identification module 32, used to identify vehicle features in at least one vehicle image, and determine the vehicle state of the preset crane, wherein the vehicle state includes at least: working state, load state and vehicle moving state; a determination module 34, used to determine a target detection item corresponding to the vehicle state from a plurality of preset detection items, wherein each vehicle state is pre-configured with at least one preset detection item, the preset detection item corresponds to at least one preset detection image, and the preset detection item is used to perform safety detection on the preset crane according to at least one preset detection image; a generation module 36, used to generate a preset alarm information when the target detection item fails the safety detection It should be noted that the acquisition module 30 in this embodiment can be used to execute step S1 in the embodiment of the present application, the identification module 32 in this embodiment can be used to execute step S2 in the embodiment of the present application, the determination module 34 in this embodiment can be used to execute step S3 in the embodiment of the present application, and the generation module 36 in this embodiment can be used to execute step S4 in the embodiment of the present application. The examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the contents disclosed in the above embodiments.

[0139] In an embodiment of the present invention, at least one vehicle screen of a preset crane is obtained; vehicle features in at least one vehicle screen are identified to determine the vehicle state of the preset crane, wherein the vehicle state includes at least: working state, load state and moving state; a target detection item corresponding to the vehicle state is determined from a plurality of preset detection items, wherein each vehicle state is pre-configured with at least one preset detection item, the preset detection item corresponds to at least one preset detection screen, and the preset detection item is used to perform a safety detection on the preset crane according to at least one preset detection screen; in the case where the target detection item fails the safety detection, a preset alarm message is generated, thereby achieving the technical effect of automatically performing a safety detection on the crane according to the working state of the crane, thereby solving the technical problem of being unable to implement crane safety detection according to the crane state.

[0140] As an optional embodiment, the recognition module includes: a first recognition unit, used to recognize a top perspective image and a peripheral perspective image in at least one vehicle image, wherein the top perspective image is an image of the area between a vehicle hook of a preset crane and the ground captured at the top of the preset crane, and the peripheral perspective image is an image of the preset crane captured from a third-person perspective; a second recognition unit, used to recognize vehicle features in the peripheral perspective image, wherein the vehicle features include at least: vehicle legs of the preset crane; a detection unit, used to detect whether there is a human image in the top perspective image when the vehicle legs are recognized in the peripheral perspective image; a first determination unit, used to determine that the vehicle state of the preset crane is a working state when there is a human image in the top perspective image.

[0141] As an optional embodiment, the recognition module includes: a third recognition unit, used to recognize a top perspective picture and a peripheral perspective picture in at least one vehicle picture, wherein the top perspective picture is an image of the area between a vehicle hook of a preset crane and the ground captured at the top of the preset crane, and the peripheral perspective picture is an image of the preset crane captured from a third-person perspective; a fourth recognition unit, used to recognize vehicle features in the top perspective picture and the peripheral perspective picture, wherein the vehicle features include at least: a vehicle hook of the preset crane; a second determination unit, used to determine that the vehicle state of the preset crane is a load state when recognizing in the top perspective picture that there is a physical connection between the vehicle hook and the suspended object, and the peripheral perspective picture detects that the position of the vehicle hook has changed.

[0142] As an optional embodiment, the recognition module includes: a fifth recognition unit, used to recognize a top perspective image and a driver perspective image in at least one vehicle image, wherein the top perspective image is an image of the area between a vehicle hook of a preset crane and the ground collected at the top of the preset crane; a sixth recognition unit, used to recognize vehicle features in the top perspective image, wherein the vehicle features include at least: a vehicle hook of the preset crane; a third determination unit, used to recognize that in the top perspective image, there is a physical connection between the vehicle hook and the suspended object, and when the driver perspective image detects that the image is rotated, determine that the vehicle state of the preset crane is a load state.

[0143] As an optional embodiment, the recognition module includes: a seventh recognition unit, used to recognize a peripheral perspective picture in at least one vehicle picture, wherein the peripheral perspective picture is an image of a preset crane captured from a third-person perspective; an eighth recognition unit, used to recognize vehicle features in the peripheral perspective picture, wherein the vehicle features include at least: a preset crane and vehicle wheels of the preset crane; and a fourth determination unit, used to determine that the vehicle state is a moving state when the change amplitude of the intersection and intersection ratio of the preset crane and the vehicle wheels in the peripheral perspective picture within a first preset time range is within a preset range.

[0144] As an optional embodiment, the determination module includes: a first determination submodule, used to determine, when a preset crane is in working condition, that the preset detection screen corresponding to the target detection item includes: a driver's perspective screen and a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; a first detection submodule, used to detect whether there is a first preset object in the driver's perspective screen and the peripheral perspective screen, wherein the first preset object wears a command mark, and when it is detected that the first preset object does not exist in both the driver's perspective screen and the peripheral perspective screen, it is determined that the target detection item has failed the safety detection.

[0145] As an optional embodiment, the determination module includes: a second determination submodule, used to determine, when the preset crane is in working state, that the preset detection screen corresponding to the target detection item includes: a driver's perspective screen and a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; a second detection submodule, used to detect whether there is a second preset object in the driver's perspective screen and the peripheral perspective screen, wherein the second preset object has both a first monitoring identifier and a second monitoring identifier, and when it is detected that the second preset object does not exist in both the driver's perspective screen and the peripheral perspective screen, it is determined that the target detection item has failed the safety detection.

[0146] As an optional embodiment, the determination module includes: a third determination submodule, used to determine, when the preset crane is in working state, that the preset detection screen corresponding to the target detection item includes: an internal perspective screen and a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; a third detection submodule, used to detect whether there is a target object in the internal perspective screen, and when there is no target object in the internal perspective screen, detect whether there is a target object with a third preset mark on its head in the peripheral perspective screen, 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 when it is detected that there is no target object in the internal perspective screen and there is no target object with the third preset mark on its head in the peripheral perspective screen, it is determined that the target detection item has failed the safety detection.

[0147] As an optional embodiment, the determination module includes: a fourth determination submodule, used to determine, when the preset crane is in working condition, that the preset detection screen corresponding to the target detection item includes: a top perspective screen, wherein the top perspective screen is an image of the area between the carrier hook of the preset crane and the ground collected at the top of the preset crane; a fourth detection submodule, used to detect whether there is a human image in the first preset warning area of ​​the top perspective screen, wherein the first preset warning area is an area pre-marked in the top perspective screen where the carrier boom of the preset crane is at risk of falling, and when a human image is detected in the first preset warning area, it is determined that the target detection item has failed the safety detection.

[0148] As an optional embodiment, the determination module includes: a fifth determination submodule, used to determine, when the preset crane is in working condition, that the preset detection screen corresponding to the target detection item includes: a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; a fifth detection submodule, used to detect whether the position changes of the vehicle legs and the corresponding pads of the preset crane in the peripheral perspective screen are consistent within a second preset time range, wherein the preset crane includes a plurality of vehicle legs, each vehicle leg is pre-configured with a corresponding pad, and the correspondence between the vehicle legs and the pads is determined according to the distance between the vehicle legs and the pads in the peripheral perspective screen, and when it is detected that the position changes of the vehicle legs and the corresponding pads within the second preset time range are inconsistent, it is determined that the target detection item has failed the safety detection.

[0149] As an optional embodiment, the determination module includes: a sixth determination submodule, used to determine, when the preset crane is in working state, that the preset detection screen corresponding to the target detection item includes: a driver's perspective screen and a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; a sixth detection submodule, used to detect whether the screen rotates from the driver's perspective, and when the screen rotates from the driver's perspective, detect whether the change ratio of the boom node of the preset crane in the peripheral perspective screen exceeds a first preset ratio threshold value; when it is detected that the screen rotates from the driver's perspective and the change ratio of the boom node exceeds the first preset ratio threshold value, it is determined that the target detection item has failed the safety detection.

[0150] As an optional embodiment, the determination module includes: a seventh determination sub-module, which is used to determine, when a preset crane enters a loading state from a moving state, that a preset detection screen corresponding to the target detection item includes: a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; a seventh detection sub-module, which is used to detect whether there is a target warning sign in the peripheral perspective screen, wherein, when a target warning sign is detected in the peripheral perspective screen, it is determined that the target detection item has passed the safety detection.

[0151] As an optional embodiment, the determination module includes: an eighth determination sub-module, which, when a preset crane enters a loading state from a moving state, determines that the preset detection screen corresponding to the target detection item includes: a peripheral perspective screen and a top perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective, and the top perspective screen is an image of the area between the carrier hook of the preset crane and the ground captured at the top of the preset crane; an eighth detection sub-module, which is used to detect whether there is a pad in the peripheral perspective screen and the top perspective screen, wherein when a pad is detected in the peripheral perspective screen or the top perspective screen, it is determined that the target detection item has passed the safety detection.

[0152] As an optional embodiment, the determination module includes: a ninth determination sub-module, which, when the preset crane is in a loaded state, determines that the preset detection screen corresponding to the target detection item includes: a cab perspective screen; a ninth detection sub-module, which is used to detect whether the target object in the cab perspective screen has a target behavior, wherein, when it is detected that the target object has a target behavior, it is determined that the target detection item has failed the safety detection.

[0153] As an optional embodiment, the determination module includes: a tenth determination sub-module, which, when the preset crane is in a loaded state, determines that the preset detection screen corresponding to the target detection item includes: a cab perspective screen; a tenth detection sub-module, which is used to detect whether there is a target object in the cab perspective screen, wherein, when it is detected that there is no target object in the cab perspective screen, it is determined that the target detection item has failed the safety detection.

[0154] As an optional embodiment, the determination module includes: an eleventh determination sub-module, which, when the preset crane is in a loaded state, determines that the preset detection screen corresponding to the target detection item includes: a top perspective screen, wherein the top perspective screen is an image of the area between the vehicle hook of the preset crane and the ground collected at the top of the preset crane; an eleventh detection sub-module, which is used to detect whether there is a human image in a second preset warning area of ​​the top perspective screen, wherein the second preset warning area is a pre-marked area in the top perspective screen where there is a risk of falling of the vehicle hook of the preset crane or the suspended object, and when a human image is detected in the second preset warning area, it is determined that the target detection item has failed the safety detection.

[0155] As an optional embodiment, the determination module includes: a twelfth determination sub-module, which, when a preset crane is in a load state, determines that the preset detection screen corresponding to the target detection item includes: a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; a twelfth detection sub-module, which is used to detect whether the change ratio of the boom node of the preset crane in the peripheral perspective screen exceeds a second preset ratio threshold, and when it is detected that the change ratio of the boom node exceeds the second preset ratio threshold, it is determined that the target detection item has not passed the safety detection.

[0156] As an optional embodiment, the determination module includes: a thirteenth determination sub-module, which, when the preset crane is in a loaded state, determines that the preset detection screen corresponding to the target detection item includes: a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; a thirteenth detection sub-module, which is used to detect whether there are slings on the big hook and the small hook of the preset crane in the peripheral perspective screen, wherein, when it is detected that both the big hook and the small hook of the preset crane have slings, it is determined that the target detection item has not passed the safety inspection.

[0157] As an optional embodiment, the determination module includes: a fourteenth determination sub-module, which, when a preset crane is in a load state, determines that the preset detection screen corresponding to the target detection item includes: a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; a fourteenth detection sub-module, which is used to detect the indicator light of the preset crane in the peripheral perspective screen, wherein, when it is detected that the indicator light indicates overload, it is determined that the target detection item has failed the safety detection.

[0158] As an optional embodiment, the determination module includes: a fifteenth determination sub-module, which, when a preset crane is in a moving state, determines that the preset detection screen corresponding to the target detection item includes: a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; a fifteenth detection sub-module, which is used to detect whether the vehicle hook of the preset crane in the peripheral perspective screen is hung with a sling, wherein, when it is detected that the vehicle hook is hung with a sling, it is determined that the target detection item has not passed the safety test.

[0159] Example 5 The embodiment of the present invention can provide a computer terminal, which can be any computer terminal device in a computer terminal group. Optionally, in this embodiment, the computer terminal can also be replaced by a terminal device such as a mobile terminal.

[0160] Optionally, in this embodiment, the computer terminal may be located in at least one network device among a plurality of network devices of the computer network.

[0161] In this embodiment, the above-mentioned computer terminal can execute the program code of the following steps in the safety detection method of the crane: obtaining at least one vehicle screen of a preset crane; identifying vehicle features in at least one vehicle screen, and determining the vehicle state of the preset crane, wherein the vehicle state includes at least: working state, load state and moving state; determining the target detection item corresponding to the vehicle state from multiple preset detection items, wherein each vehicle state is pre-configured with at least one preset detection item, the preset detection item corresponds to at least one preset detection screen, and the preset detection item is used to perform safety detection on the preset crane according to at least one preset detection screen; if the target detection item fails the safety detection, a preset alarm information is generated.

[0162] Optionally, Figure 4 is a structural block diagram of a computer terminal according to an embodiment of the present invention. Figure 4 As shown, the computer terminal 40 may include: one or more (only one is shown in the figure) processors 42 , and a memory 44 .

[0163] Among them, the memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the crane safety detection method and device in the embodiment of the present invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the above-mentioned crane safety detection method. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory may further include a memory remotely arranged relative to the processor, and these remote memories can be connected to the terminal 40 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0164] The processor can call the information and application programs stored in the memory through the transmission device to perform the following steps: obtain at least one vehicle screen of a preset crane; identify vehicle features in at least one vehicle screen, and determine the vehicle status of the preset crane, wherein the vehicle status includes at least: working status, load status, and vehicle moving status; determine the target detection item corresponding to the vehicle status from multiple preset detection items, wherein each vehicle status is pre-configured with at least one preset detection item, the preset detection item corresponds to at least one preset detection screen, and the preset detection item is used to perform safety detection on the preset crane according to at least one preset detection screen; if the target detection item fails the safety detection, a preset alarm information is generated.

[0165] Optionally, the processor may also execute program code for the following steps: identifying a top perspective image and a peripheral perspective image in at least one vehicle image, wherein the top perspective image is an image of the area between a vehicle hook of a preset crane and the ground captured at the top of the preset crane, and the peripheral perspective image is an image of the preset crane captured from a third-person perspective; identifying vehicle features in the peripheral perspective image, wherein the vehicle features include at least: vehicle legs of the preset crane; when the vehicle legs are identified in the peripheral perspective image, detecting whether there is a human image in the top perspective image; when there is a human image in the top perspective image, determining that the vehicle state of the preset crane is a working state.

[0166] Optionally, the processor may also execute program code for the following steps: identifying a top perspective image and a peripheral perspective image in at least one vehicle image, wherein the top perspective image is an image of the area between a vehicle hook of a preset crane and the ground captured at the top of the preset crane, and the peripheral perspective image is an image of the preset crane captured from a third-person perspective; identifying vehicle features in the top perspective image and the peripheral perspective image, wherein the vehicle features include at least: a vehicle hook of the preset crane; determining that the vehicle state of the preset crane is a load state when it is recognized in the top perspective image that there is a physical connection between the vehicle hook and the suspended object, and the peripheral perspective image detects that the position of the vehicle hook has changed.

[0167] Optionally, the processor may also execute program code for the following steps: identifying a top perspective image and a driver perspective image in at least one vehicle image, wherein the top perspective image is an image of the area between a vehicle hook of a preset crane and the ground captured at the top of the preset crane; identifying vehicle features in the top perspective image, wherein the vehicle features include at least: a vehicle hook of the preset crane; and determining that the vehicle state of the preset crane is a load state when it is identified in the top perspective image that there is a physical connection between the vehicle hook and the suspended object and the driver perspective image detects that the image is rotating.

[0168] Optionally, the processor may also execute program codes of the following steps: identifying a peripheral perspective picture in at least one vehicle picture, wherein the peripheral perspective picture is an image of a preset crane captured from a third-person perspective; identifying vehicle features in the peripheral perspective picture, wherein the vehicle features include at least: a preset crane and vehicle wheels of the preset crane; and determining that the vehicle state is a moving state when the change amplitude of the intersection and intersection ratio of the preset crane and the vehicle wheels in the peripheral perspective picture within a first preset time range is within a preset range.

[0169] Optionally, the processor may also execute the program code of the following steps: when a preset crane is in working condition, determining that the preset detection screen corresponding to the target detection item includes: a driver's perspective screen and a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; detecting whether a first preset object exists in the driver's perspective screen and the peripheral perspective screen, wherein the first preset object wears a command mark, and when it is detected that the first preset object does not exist in both the driver's perspective screen and the peripheral perspective screen, determining that the target detection item has failed the safety detection.

[0170] Optionally, the processor may also execute the program code of the following steps: when the preset crane is in working state, determining that the preset detection screen corresponding to the target detection item includes: a driver's perspective screen and a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; detecting whether there is a second preset object in the driver's perspective screen and the peripheral perspective screen, wherein the second preset object has both a first monitoring identifier and a second monitoring identifier, and when it is detected that the second preset object does not exist in both the driver's perspective screen and the peripheral perspective screen, determining that the target detection item has failed the safety detection.

[0171] Optionally, the processor may also execute the program code of the following steps: when the preset crane is in working state, determine that the preset detection screen corresponding to the target detection item includes: an internal perspective screen and a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; detect whether there is a target object in the internal perspective screen, and when there is no target object in the internal perspective screen, detect whether there is a target object with a third preset mark on its head in the peripheral perspective screen, 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 when it is detected that there is no target object in the internal perspective screen and there is no target object with the third preset mark on its head in the peripheral perspective screen, determine that the target detection item has failed the safety detection.

[0172] Optionally, the processor may also execute the program code of the following steps: when the preset crane is in working condition, determining that the preset detection screen corresponding to the target detection item includes: a top perspective screen, wherein the top perspective screen is an image of the area 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 the first preset warning area of ​​the top perspective screen, wherein the first preset warning area is an area pre-marked in the top perspective screen where the carrier boom of the preset crane is at risk of falling, and when a human image is detected in the first preset warning area, determining that the target detection item has failed the safety detection.

[0173] Optionally, the processor may also execute the program code of the following steps: when the preset crane is in working condition, determining that the preset detection screen corresponding to the target detection item includes: a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; detecting whether the position changes of the vehicle legs and the corresponding pads of the preset crane in the peripheral perspective screen are consistent within a second preset time range, wherein the preset crane includes a plurality of vehicle legs, each vehicle leg is pre-configured with a corresponding pad, determining the correspondence between the vehicle legs and the pads according to the distance between the vehicle legs and the pads in the peripheral perspective screen, and when it is detected that the position changes of the vehicle legs and the corresponding pads within the second preset time range are inconsistent, determining that the target detection item has failed the safety inspection.

[0174] Optionally, the processor may also execute the program code of the following steps: when the preset crane is in working state, determining that the preset detection screen corresponding to the target detection item includes: a driver's perspective screen and a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; detecting whether the screen rotates from the driver's perspective, and when the screen rotates from the driver's perspective, detecting whether the change ratio of the boom node of the preset crane in the peripheral perspective screen exceeds a first preset ratio threshold value; when it is detected that the screen rotates from the driver's perspective and the change ratio of the boom node exceeds the first preset ratio threshold value, determining that the target detection item has failed the safety detection.

[0175] Optionally, the processor may also execute the program code of the following steps: when a preset crane enters a loading state from a moving state, determining that the preset detection screen corresponding to the target detection item includes: a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; detecting whether there is a target warning sign in the peripheral perspective screen, wherein, when a target warning sign is detected in the peripheral perspective screen, determining that the target detection item has passed the safety detection.

[0176] Optionally, the processor may also execute the program code of the following steps: when a preset crane enters a loading state from a moving state, determining that the preset detection screen corresponding to the target detection item includes: a peripheral perspective screen and a top perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective, and the top perspective screen is an image of the area between the carrier hook of the preset crane and the ground captured at the top of the preset crane; detecting whether there is a pad in the peripheral perspective screen and the top perspective screen, wherein when it is detected that there is a pad in the peripheral perspective screen or the top perspective screen, determining that the target detection item has passed the safety detection.

[0177] Optionally, the processor may also execute the program code of the following steps: when the preset crane is in a loaded state, determining that the preset detection screen corresponding to the target detection item includes: a cab perspective screen; detecting whether the target object in the cab perspective screen has a target behavior, wherein, when it is detected that the target object has a target behavior, determining that the target detection item has failed the safety detection.

[0178] Optionally, the processor may also execute the program code of the following steps: when the preset crane is in a loaded state, determining that the preset detection screen corresponding to the target detection item includes: a cab perspective screen; detecting whether there is a target object in the cab perspective screen, wherein, when it is detected that there is no target object in the cab perspective screen, determining that the target detection item has failed the safety detection.

[0179] Optionally, the processor may also execute the program code of the following steps: when the preset crane is in a loaded state, determining that the preset detection screen corresponding to the target detection item includes: a top perspective screen, wherein the top perspective screen is an image of the area 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 the second preset warning area of ​​the top perspective screen, wherein the second preset warning area is a pre-marked area in the top perspective screen where there is a risk of falling of the carrier hook of the preset crane or the suspended object, and when a human image is detected in the second preset warning area, determining that the target detection item has failed the safety detection.

[0180] Optionally, the processor may also execute the program code of the following steps: when the preset crane is in a loaded state, determining that the preset detection screen corresponding to the target detection item includes: a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; detecting whether the change ratio of the boom node of the preset crane in the peripheral perspective screen exceeds a second preset ratio threshold, and when it is detected that the change ratio of the boom node exceeds the second preset ratio threshold, determining that the target detection item has failed the safety detection.

[0181] Optionally, the processor may also execute the program code of the following steps: when the preset crane is in a loaded state, determining that the preset detection screen corresponding to the target detection item includes: a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; detecting whether there are slings on the large hook and the small hook of the preset crane in the peripheral perspective screen, wherein, when it is detected that both the large hook and the small hook of the preset crane have slings, determining that the target detection item has not passed the safety inspection.

[0182] Optionally, the processor may also execute the program code of the following steps: when a preset crane is in a loaded state, determining that a preset detection screen corresponding to the target detection item includes: a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; detecting an indicator light of the preset crane in the peripheral perspective screen, wherein, when it is detected that the indicator light indicates an overload, determining that the target detection item has failed the safety test.

[0183] Optionally, the processor may also execute the program code of the following steps: when a preset crane is in a moving state, determining that the preset detection screen corresponding to the target detection item includes: a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; detecting whether the vehicle hook of the preset crane in the peripheral perspective screen is hung with a sling, wherein, when it is detected that the vehicle hook is hung with a sling, determining that the target detection item has failed the safety inspection.

[0184] In an embodiment of the present invention, at least one vehicle screen of a preset crane is obtained; vehicle features in at least one vehicle screen are identified to determine the vehicle state of the preset crane, wherein the vehicle state includes at least: working state, load state and moving state; a target detection item corresponding to the vehicle state is determined from a plurality of preset detection items, wherein each vehicle state is pre-configured with at least one preset detection item, the preset detection item corresponds to at least one preset detection screen, and the preset detection item is used to perform a safety detection on the preset crane according to at least one preset detection screen; in the case where the target detection item fails the safety detection, a preset alarm message is generated, thereby achieving the technical effect of automatically performing a safety detection on the crane according to the working state of the crane, thereby solving the technical problem of being unable to implement crane safety detection according to the crane state.

[0185] It can be understood by those skilled in the art that Figure 4 The structure shown is for illustration only, and the computer terminal may also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a handheld computer, a mobile Internet device (Mobile Internet Devices, MID), a PAD, or other terminal devices. Figure 4 The structure of the electronic device is not limited. For example, the computer terminal 40 may also include Figure 4 More or fewer components (such as network interfaces, display devices, etc.) shown in, or with Figure 4 Different configurations shown.

[0186] A person of ordinary skill in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing the hardware related to the terminal device through a program, and the program may be stored in a computer-readable storage medium, and the computer-readable storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0187] Example 6 The embodiment of the present invention further provides a readable storage medium. Optionally, in this embodiment, the readable storage medium can be used to store the program code executed by the crane safety detection method provided in the above embodiment.

[0188] Optionally, in this embodiment, the readable storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0189] Optionally, in this embodiment, the readable storage medium is configured to store program codes for executing the following steps: obtaining at least one vehicle screen of a preset crane; identifying vehicle features in at least one vehicle screen, and determining a vehicle state of the preset crane, wherein the vehicle state includes at least: a working state, a load state, and a moving state; determining a target detection item corresponding to the vehicle state from a plurality of preset detection items, wherein each vehicle state is pre-configured with at least one preset detection item, the preset detection item corresponds to at least one preset detection screen, and the preset detection item is used to perform a safety detection on the preset crane according to at least one preset detection screen; and generating a preset alarm message when the target detection item fails the safety detection.

[0190] Optionally, in this embodiment, the readable storage medium is configured to store program code for executing the following steps: identifying a top perspective picture and a peripheral perspective picture in at least one vehicle picture, wherein the top perspective picture is an image of the area between a vehicle hook of a preset crane and the ground captured at the top of the preset crane, and the peripheral perspective picture is an image of the preset crane captured from a third-person perspective; identifying vehicle features in the peripheral perspective picture, wherein the vehicle features include at least: vehicle legs of the preset crane; when the vehicle legs are identified in the peripheral perspective picture, detecting whether there is a human image in the top perspective picture; when there is a human image in the top perspective picture, determining that the vehicle state of the preset crane is a working state.

[0191] Optionally, in this embodiment, the readable storage medium is configured to store program codes for executing the following steps: identifying a top perspective image and a peripheral perspective image in at least one vehicle image, wherein the top perspective image is an image of the area between a vehicle hook of a preset crane and the ground captured at the top of the preset crane, and the peripheral perspective image is an image of the preset crane captured from a third-person perspective; identifying vehicle features in the top perspective image and the peripheral perspective image, wherein the vehicle features include at least: a vehicle hook of the preset crane; determining that the vehicle state of the preset crane is a load state when it is recognized in the top perspective image that there is a physical connection between the vehicle hook and the suspended object, and the peripheral perspective image detects that the position of the vehicle hook has changed.

[0192] Optionally, in this embodiment, the readable storage medium is configured to store program code for executing the following steps: identifying a top perspective image and a driver perspective image in at least one vehicle image, wherein the top perspective image is an image of the area between a vehicle hook of a preset crane and the ground captured at the top of the preset crane; identifying vehicle features in the top perspective image, wherein the vehicle features include at least: a vehicle hook of the preset crane; and determining that the vehicle state of the preset crane is a load state when a physical connection between the vehicle hook and the suspended object is identified in the top perspective image and the driver perspective image detects that the image is rotated.

[0193] Optionally, in this embodiment, the readable storage medium is configured to store program codes for executing the following steps: identifying a peripheral perspective picture in at least one vehicle picture, wherein the peripheral perspective picture is an image of a preset crane captured from a third-person perspective; identifying vehicle features in the peripheral perspective picture, wherein the vehicle features include at least: a preset crane and vehicle wheels of the preset crane; determining that the vehicle state is a moving state when the amplitude of the intersection and intersection ratio of the preset crane and the vehicle wheels in the peripheral perspective picture within a first preset time range is within a preset range.

[0194] Optionally, in this embodiment, the readable storage medium is configured to store program codes for executing the following steps: when a preset crane is in working condition, determining that a preset detection screen corresponding to the target detection item includes: a driver's perspective screen and a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; detecting whether a first preset object exists in the driver's perspective screen and the peripheral perspective screen, wherein the first preset object wears a command mark, and when it is detected that the first preset object does not exist in both the driver's perspective screen and the peripheral perspective screen, determining that the target detection item has failed the safety detection.

[0195] Optionally, in this embodiment, the readable storage medium is configured to store program codes for executing the following steps: when a preset crane is in working condition, determining that a preset detection screen corresponding to the target detection item includes: a driver's perspective screen and a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; detecting whether a second preset object exists in the driver's perspective screen and the peripheral perspective screen, wherein the second preset object has both a first monitoring identifier and a second monitoring identifier, and when it is detected that the second preset object does not exist in both the driver's perspective screen and the peripheral perspective screen, determining that the target detection item has failed the safety detection.

[0196] Optionally, in this embodiment, the readable storage medium is configured to store program codes for executing the following steps: when a preset crane is in working condition, determining that a preset detection screen corresponding to the target detection item includes: an internal perspective screen and a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; detecting whether there is a target object in the internal perspective screen, and when there is no target object in the internal perspective screen, detecting whether there is a target object with a third preset mark on its head in the peripheral perspective screen, 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 when it is detected that there is no target object in the internal perspective screen and there is no target object with the third preset mark on its head in the peripheral perspective screen, determining that the target detection item has failed the safety detection.

[0197] Optionally, in this embodiment, the readable storage medium is configured to store program codes for executing the following steps: when the preset crane is in working condition, determining that the preset detection screen corresponding to the target detection item includes: a top perspective screen, wherein the top perspective screen is an image of the area between the vehicle hook of the preset crane and the ground captured at the top of the preset crane; detecting whether there is a human image in a first preset warning area of ​​the top perspective screen, wherein the first preset warning area is an area in the top perspective screen where the vehicle boom of the preset crane is pre-marked as being at risk of falling, and when a human image is detected in the first preset warning area, determining that the target detection item has failed the safety detection.

[0198] Optionally, in this embodiment, the readable storage medium is configured to store program codes for executing the following steps: when a preset crane is in working condition, determining that a preset detection screen corresponding to the target detection item includes: a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; detecting whether the position changes of the vehicle legs and the corresponding pads of the preset crane in the peripheral perspective screen are consistent within a second preset time range, wherein the preset crane includes a plurality of vehicle legs, each vehicle leg is pre-configured with a corresponding pad, determining the correspondence between the vehicle legs and the pads according to the distance between the vehicle legs and the pads in the peripheral perspective screen, and when it is detected that the position changes of the vehicle legs and the corresponding pads within the second preset time range are inconsistent, determining that the target detection item has failed the safety detection.

[0199] Optionally, in this embodiment, the readable storage medium is configured to store program codes for executing the following steps: when a preset crane is in working condition, determining that a preset detection screen corresponding to the target detection item includes: a driver's perspective screen and a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; detecting whether screen rotation occurs from the driver's perspective, and when screen rotation occurs from the driver's perspective, detecting whether a change ratio of a boom node of the preset crane in the peripheral perspective screen exceeds a first preset ratio threshold; when it is detected that screen rotation occurs from the driver's perspective and a change ratio of the boom node exceeds the first preset ratio threshold, determining that the target detection item has failed the safety detection.

[0200] Optionally, in this embodiment, the readable storage medium is configured to store program codes for executing the following steps: when a preset crane enters a load state from a moving state, determining that a preset detection screen corresponding to the target detection item includes: a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; detecting whether there is a target warning sign in the peripheral perspective screen, wherein, when a target warning sign is detected in the peripheral perspective screen, determining that the target detection item has passed the safety detection.

[0201] Optionally, in this embodiment, the readable storage medium is configured to store program codes for executing the following steps: when a preset crane enters a loading state from a moving state, determining that the preset detection screen corresponding to the target detection item includes: a peripheral perspective screen and a top perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective, and the top perspective screen is an image of the area between the carrier hook of the preset crane and the ground captured at the top of the preset crane; detecting whether there is a pad in the peripheral perspective screen and the top perspective screen, wherein when it is detected that there is a pad in the peripheral perspective screen or the top perspective screen, determining that the target detection item passes the safety detection.

[0202] Optionally, in this embodiment, the readable storage medium is configured to store program codes for executing the following steps: in a case where the preset crane is in a loaded state, determining that the preset detection screen corresponding to the target detection item includes: a cab perspective screen; detecting whether the target object in the cab perspective screen has a target behavior, wherein, when it is detected that the target object has a target behavior, determining that the target detection item has failed the safety detection.

[0203] Optionally, in this embodiment, the readable storage medium is configured to store program codes for executing the following steps: in a case where the preset crane is in a loaded state, determining that the preset detection screen corresponding to the target detection item includes: a cab perspective screen; detecting whether there is a target object in the cab perspective screen, wherein, when it is detected that there is no target object in the cab perspective screen, determining that the target detection item has failed the safety detection.

[0204] Optionally, in this embodiment, the readable storage medium is configured to store program codes for executing the following steps: when the preset crane is in a loaded state, determining that the preset detection screen corresponding to the target detection item includes: a top perspective screen, wherein the top perspective screen is an image of the area between the vehicle hook of the preset crane and the ground captured at the top of the preset crane; detecting whether there is a human image in a second preset warning area of ​​the top perspective screen, wherein the second preset warning area is a pre-marked area in the top perspective screen where there is a risk of falling of the vehicle hook of the preset crane or the suspended object, and when a human image is detected in the second preset warning area, determining that the target detection item has failed the safety detection.

[0205] Optionally, in this embodiment, the readable storage medium is configured to store program codes for executing the following steps: when a preset crane is in a loaded state, determining that a preset detection screen corresponding to the target detection item includes: a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; detecting whether a change ratio of a boom node of the preset crane in the peripheral perspective screen exceeds a second preset ratio threshold, and when it is detected that the change ratio of the boom node exceeds the second preset ratio threshold, determining that the target detection item has failed the safety detection.

[0206] Optionally, in this embodiment, the readable storage medium is configured to store program codes for executing the following steps: when a preset crane is in a loaded state, determining that a preset detection screen corresponding to the target detection item includes: a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; detecting whether there are slings on the large hook and the small hook of the preset crane in the peripheral perspective screen, wherein, when it is detected that both the large hook and the small hook of the preset crane have slings, determining that the target detection item has failed the safety test.

[0207] Optionally, in this embodiment, the readable storage medium is configured to store program codes for executing the following steps: when a preset crane is in a loaded state, determining that a preset detection screen corresponding to the target detection item includes: a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; detecting an indicator light of the preset crane in the peripheral perspective screen, wherein, when it is detected that the indicator light indicates overload, determining that the target detection item has failed the safety detection.

[0208] Optionally, in this embodiment, the readable storage medium is configured to store program codes for executing the following steps: when a preset crane is in a moving state, determining that a preset detection screen corresponding to the target detection item includes: a peripheral perspective screen, wherein the peripheral perspective screen is an image of the preset crane captured from a third-person perspective; detecting whether a vehicle hook of the preset crane in the peripheral perspective screen is hung with a sling, wherein, when it is detected that the vehicle hook is hung with a sling, determining that the target detection item has failed the safety test.

[0209] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0210] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0211] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0212] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0213] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0214] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), mobile hard disk, disk or optical disk, etc., which can store program code.

[0215] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A crane safety detection method, characterized in that: The detection method The following steps are included: S1. Obtain at least one vehicle image of a preset crane; S2, identifying at least one vehicle feature in the vehicle image, and determining the vehicle state of the preset crane; the vehicle state at least includes a working state, a load state, and a vehicle moving state; S3. Determine a target detection item corresponding to the vehicle state from a plurality of preset detection items, wherein each vehicle state is pre-configured with at least one preset detection item, the preset detection item corresponds to at least one preset detection screen, and the preset detection item is used to perform safety detection on the preset crane according to at least one preset detection screen; S4. When the target detection item fails the safety detection, a preset alarm message is generated.

2. A crane safety detection method as claimed in claim 1, characterized in that: In step S2, the vehicle screen includes any one or more combinations of an internal perspective screen, a top perspective screen, a peripheral perspective screen and a driver perspective screen; the internal perspective screen is an image of the cab of the preset crane; the top perspective screen is an image of the area between the vehicle hook of the preset crane and the ground captured at the top of the preset crane; the peripheral perspective screen is an image of the preset crane captured from a third-person perspective.

3. A crane safety detection method as claimed in claim 2, characterized in that: The vehicle features in the top perspective image at least include the vehicle hook of the preset crane; the vehicle features in the peripheral perspective image at least include the preset crane, the vehicle legs of the preset crane, the vehicle hook and / or the vehicle wheels.

4. A crane safety detection method as claimed in claim 3, characterized in that: When the vehicle legs are identified in the peripheral viewing angle picture, it is detected whether there is a human image in the top viewing angle picture; when there is a human image in the top viewing angle picture, it is determined that the vehicle state of the preset crane is the working state.

5. A crane safety detection method as claimed in claim 3, characterized in that: When it is recognized in the top perspective image that there is a physical connection between the carrier hook and the hanging object, and the peripheral perspective image detects that the position of the carrier hook changes, it is determined that the carrier state of the preset crane is the load state.

6. A crane safety detection method as claimed in claim 3, characterized in that: When it is recognized in the top perspective image that the carrier hook is physically connected to the hanging object, and the driver perspective image detects that the image is rotating, it is determined that the carrier state of the preset crane is the load state.

7. A crane safety detection method as claimed in claim 3, characterized in that: When the change amplitude of the intersection-and-joint ratio of the preset crane and the vehicle wheels in the peripheral viewing angle picture within a first preset time range is within a preset range, it is determined that the vehicle state is the vehicle moving state.

8. A crane safety detection method according to any one of claims 1 to 7, characterized in that: In step S3, the target detection item corresponding to the vehicle state is determined from a plurality of preset detection items, specifically, When the preset crane is in the working state, it is determined that the preset detection screen corresponding to the target detection item includes a driver's perspective screen and a peripheral perspective screen, and it is detected whether there is a first preset object in the driver's perspective screen and the peripheral perspective screen. When it is detected that the first preset object does not exist in both the driver's perspective screen and the peripheral perspective screen, it is determined that the target detection item has failed the safety detection; the first preset object wears a command mark.

9. A crane safety detection method according to any one of claims 1 to 7, characterized in that: In step S3, the target detection item corresponding to the vehicle state is determined from a plurality of preset detection items, specifically, When the preset crane is in the working state, it is determined that the preset detection screen corresponding to the target detection item includes a driver's perspective screen and a peripheral perspective screen, and it is detected whether there is a second preset object in the driver's perspective screen and the peripheral perspective screen. When it is detected that the second preset object does not exist in both the driver's perspective screen and the peripheral perspective screen, it is determined that the target detection item has failed the safety detection; the second preset object has both the first monitoring identifier and the second monitoring identifier.

10. A crane safety detection method according to any one of claims 1 to 7, characterized in that: In step S3, the target detection item corresponding to the vehicle state is determined from a plurality of preset detection items, specifically, When the preset crane is in the working state, determine that the preset detection screen corresponding to the target detection item includes an internal perspective screen and a peripheral perspective screen, detect whether there is a target object in the internal perspective screen, and when the target object does not exist in the internal perspective screen, detect whether there is the target object with a third preset mark on the head in the peripheral perspective screen, and when it is detected that the target object does not exist in the internal perspective screen and the target object with the third preset mark on the head does not exist in the peripheral perspective screen, determine that the target detection item has failed the safety inspection; 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 crane safety detection method according to any one of claims 1 to 7, characterized in that: In step S3, the target detection item corresponding to the vehicle state is determined from a plurality of preset detection items, specifically, When the preset crane is in the working state, it is determined that the preset detection screen corresponding to the target detection item includes a top perspective screen, and it is detected whether there is a human image in a first preset warning area of ​​the top perspective screen. When the human image is detected in the first preset warning area, it is determined that the target detection item has failed the safety detection; the first preset warning area is an area pre-marked in the top perspective screen where the carrier boom of the preset crane is at risk of falling.

12. A crane safety detection method according to any one of claims 1 to 7, characterized in that: In step S3, the target detection item corresponding to the vehicle state is determined from a plurality of preset detection items, specifically, When the preset crane enters the load state from the moving state, it is determined that the preset detection screen corresponding to the target detection item includes a peripheral viewing angle screen, and it is detected whether there is a target warning mark in the peripheral viewing angle screen. When it is detected that there is a target warning mark in the peripheral viewing angle screen, it is determined that the target detection item has passed the safety detection.

13. A crane safety detection method according to any one of claims 1 to 7, characterized in that: In step S3, the target detection item corresponding to the vehicle state is determined from a plurality of preset detection items, specifically, In the case where the preset crane enters the load state from the moving state, it is determined that the preset detection screen corresponding to the target detection item includes a peripheral perspective screen and a top perspective screen, and it is detected whether there is a pad in the peripheral perspective screen and the top perspective screen. When it is detected that there is a pad in the peripheral perspective screen or the top perspective screen, it is determined that the target detection item has passed the safety detection.

14. A crane safety detection method according to any one of claims 1 to 7, characterized in that: In step S3, the target detection item corresponding to the vehicle state is determined from a plurality of preset detection items, specifically, When the preset crane is in the load state, determine that the preset detection screen corresponding to the target detection item includes a cab perspective screen; detect whether the target object in the cab perspective screen has a target behavior, and when it is detected that the target object has a target behavior, determine that the target detection item has failed the safety detection.

15. A crane safety detection method according to any one of claims 1 to 7, characterized in that: In step S3, the target detection item corresponding to the vehicle state is determined from a plurality of preset detection items, specifically, When the preset crane is in the load state, determine that the preset detection screen corresponding to the target detection item includes a cab perspective screen; detect whether there is a target object in the cab perspective screen, and when it is detected that the target object does not exist in the cab perspective screen, determine that the target detection item has failed the safety detection.

16. A crane safety detection method according to any one of claims 1 to 7, characterized in that: In step S3, the target detection item corresponding to the vehicle state is determined from a plurality of preset detection items, specifically, When the preset crane is in the load state, it is determined that the preset detection screen corresponding to the target detection item includes a peripheral viewing angle screen, and it is detected whether there are slings on the big hook and the small hook of the preset crane in the peripheral viewing angle screen. When it is detected that there are slings on both the big hook and the small hook of the preset crane, it is determined that the target detection item has not passed the safety detection.

17. A crane safety detection method according to any one of claims 1 to 7, characterized in that: In step S3, the target detection item corresponding to the vehicle state is determined from a plurality of preset detection items, specifically, When the preset crane is in the moving state, it is determined that the preset detection screen corresponding to the target detection item includes a peripheral viewing angle screen, and whether the carrier hook of the preset crane in the peripheral viewing angle screen is hung with a sling, and when it is detected that the carrier hook is hung with the sling, it is determined that the target detection item has failed the safety detection.

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

19. A readable storage medium, the readable storage medium being used to store a program, characterized in that: When the program is running, the readable storage medium is controlled to execute the crane safety detection method as described in any one of claims 1-17.

20. An electronic device, comprising a memory and a processor, wherein the processor is used to run a program stored in the processor, characterized in that: When the program is running, the safety detection method for a crane as described in any one of claims 1-17 is executed.

Images