Point location monitoring method, system and device in tower crane jacking process

Abstract

The invention discloses a point location monitoring method, system and device in a tower crane jacking process. Relates to the technical field of tower crane installation. The method comprises the steps that images of working point positions are obtained in real time, wherein the working point positions comprise one or more of a jacking oil cylinder, a standard knot upper pin shaft, a standard knot lifting frame, a standard knot lower pin shaft, a step changing supporting rod and a cross beam safety pin shaft; on the basis of a preset target detection model, key components in the image of the working point location are detected, and the working state of the working point location is obtained; and obtaining a monitoring result of the working point based on the working state of the working point. The point location monitoring method in the jacking process of the tower crane does not depend on a sensor, so that the installation and debugging of the sensor are not involved, the wiring difficulty and debugging steps are reduced, the point location monitoring efficiency in the jacking process of the tower crane is improved, and the point location monitoring in the jacking process of the tower crane is simpler and more convenient.

Description

Technical Field

[0001] The present application relates to the technical field of tower crane installation, and in particular to a method for monitoring a point during a tower crane lifting process, a system for monitoring a point during a tower crane lifting process, and a device for monitoring a point during a tower crane lifting process. Background Art

[0002] Tower crane is the abbreviation of tower crane. The process of lifting and lowering the tower crane is the most dangerous and prone to major accidents. If an accident occurs during the lifting process, it will usually cause the tower crane to collapse and be damaged, causing significant economic and personal safety losses.

[0003] In tower crane jacking accidents, most of the accidents are caused by improper operation of the installation workers. For example, the lifting beam begins to unload before it is hung on the step, the cylinder starts to push out before the support rod is firmly planted, etc. Therefore, monitoring each key point in the tower crane jacking process and operating it in place can greatly reduce the possibility of tower crane jacking accidents.

[0004] Existing tower crane lifting monitoring systems often use the method of installing corresponding sensors at key points to monitor whether the point is operated properly. However, there are many key points on tower cranes, and installing too many sensors will cause trouble in installation and wiring. At the same time, many sensors need to be debugged, and a lot of effort is required to debug each tower crane. Summary of the invention

[0005] The purpose of the embodiments of the present application is to provide a method for monitoring the position of a tower crane during the jacking process, a system for monitoring the position of a tower crane during the jacking process, and a device for monitoring the position of a tower crane during the jacking process, so as to solve the problem in the prior art that installing too many sensors will cause troubles in installation and wiring, and at the same time many sensors need to be debugged, and a lot of effort needs to be spent on debugging each tower crane.

[0006] In order to achieve the above-mentioned purpose, the first aspect of the present application provides a method for monitoring the position of a tower crane during the jacking process, comprising:

[0007] Acquire images of working points in real time, wherein the working points include one or more of a jacking cylinder, an upper pin shaft of a standard section, a lifting frame of a standard section, a lower pin shaft of a standard section, a step-changing support rod, and a crossbeam safety pin shaft;

[0008] Based on a preset target detection model, key components in the image of the working point are detected to obtain the working status of the working point;

[0009] Based on the working status of the working point, a monitoring result of the working point is obtained.

[0010] In the embodiment of the present application, the working point is a jacking cylinder and / or a standard section lifting frame on a tower crane;

[0011] The detecting of key components in the image of the working point based on a preset target detection model to obtain the working state of the working point includes:

[0012] Using a preset target detection model to recognize the image of the working point, and obtain a first recognition result;

[0013] Based on the first recognition result, determining whether there is a corresponding key component in the image of the working point, and obtaining first key component information;

[0014] Based on the first key component information, the working status of the working point is obtained.

[0015] In the embodiment of the present application, the working point is the upper pin shaft of the standard section and / or the lower pin shaft of the standard section on the tower crane;

[0016] The detecting of key components in the image of the working point based on a preset target detection model to obtain the working state of the working point includes:

[0017] Using a preset target detection model to recognize the image of the working point, and obtain a second recognition result;

[0018] Based on the second recognition result, determining whether there is a corresponding key component in the image of the working point, and obtaining second key component information;

[0019] Based on the second key component information, determining whether the corresponding key component meets a preset length requirement, and obtaining third key component information;

[0020] Based on the second key component information and the three key component information, the working status of the working point is obtained.

[0021] In the embodiment of the present application, the working point is a step-changing support rod on a tower crane, and the key components corresponding to the image of the working point include a support rod, a step, and a step support rod assembly;

[0022] The detecting of key components in the image of the working point based on a preset target detection model to obtain the working state of the working point includes:

[0023] Using a preset target detection model to recognize the image of the working point, and obtaining a third recognition result;

[0024] Based on the third recognition result, determining whether there are support rods, steps, and step support rod assemblies in the image of the working point;

[0025] In the case where it is determined that there are a support rod and a step in the image of the working point, it is determined that the working state of the step-changing support rod is that the support rod has not stepped into the step;

[0026] When it is determined that the step support rod assembly and the step exist in the image of the working point, it is determined that the working state of the step-changing support rod is that the support rod has stepped into the step.

[0027] In the embodiment of the present application, the working point is a beam safety pin on a tower crane, and the key components corresponding to the image of the working point include an ohmic ring, a pin ring, and a step;

[0028] The detecting of key components in the image of the working point based on a preset target detection model to obtain the working state of the working point includes:

[0029] Using a preset target detection model to recognize the image of the working point, and obtaining a fourth recognition result;

[0030] Based on the fourth recognition result, determining whether there is an ohmic ring, a pin ring, and a step in the image of the working point;

[0031] In the case where it is determined that an ohmic ring, a pin ring and a step exist in the image of the working point, judging whether the distance between the ohmic ring and the pin ring meets a preset threshold;

[0032] When it is determined that the distance between the ohmic ring and the pin ring meets a preset threshold, it is determined that the working state of the beam safety pin is that the beam safety pin is inserted.

[0033] In the embodiment of the present application, the key components in the image of the working point are detected based on a preset target detection model to obtain the working status of the working point, including:

[0034] Using a preset target detection model, key components in the image of the working point are identified to obtain information of multiple key components;

[0035] Based on the multiple key component information, matching key component information corresponding to different working points;

[0036] Based on the key component information corresponding to the different working points, the working status of the different working points is obtained.

[0037] In the embodiment of the present application, the process of constructing the preset target detection model includes:

[0038] Acquire training samples, wherein the training samples include key component information of multiple working points and corresponding working states;

[0039] The training samples are used to train the preset detection model to obtain the target detection model.

[0040] A second aspect of the present application provides a point monitoring system during the jacking process of a tower crane, comprising a camera and a monitoring host, wherein the camera is arranged on the tower crane;

[0041] The camera is used to obtain images of working points in real time, and the working points include one or more of a jacking cylinder, an upper pin shaft of a standard section, a lifting frame of a standard section, a lower pin shaft of a standard section, a step-changing support rod, and a crossbeam safety pin shaft;

[0042] The monitoring host is used to detect key components in the image of the working point based on a preset target detection model to obtain the working status of the working point; based on the working status of the working point, obtain the monitoring result of the working point.

[0043] In an embodiment of the present application, the position of the camera is determined according to the position of the working point.

[0044] A third aspect of the present application provides a point position monitoring device during the tower crane lifting process, comprising:

[0045] An acquisition module is used to acquire images of working points in real time, wherein the working points include one or more of a jacking cylinder, an upper pin shaft of a standard section, a lifting frame of a standard section, a lower pin shaft of a standard section, a step-changing support rod, and a crossbeam safety pin shaft;

[0046] A detection module, used to detect key components in the image of the working point based on a preset target detection model to obtain the working status of the working point;

[0047] The monitoring module is used to obtain the monitoring result of the working point based on the working status of the working point.

[0048] Through the above technical scheme, by acquiring the image of the working point in real time, the working point includes one or more of the jacking cylinder, the upper pin of the standard section, the lifting frame of the standard section, the lower pin of the standard section, the step-changing support rod and the crossbeam safety pin; based on the preset target detection model, the key components in the image of the working point are detected to obtain the working state of the working point; based on the working state of the working point, the monitoring result of the working point is obtained. By detecting the key components in the image of the working point through the preset target detection model, the working state of the working point can be quickly and accurately determined, and then the working point can be monitored, and visual monitoring and identification of all key points in the tower crane jacking process can be realized. The point monitoring method in the tower crane jacking process does not rely on sensors, and does not involve the installation and debugging of sensors, reduces the wiring difficulty and debugging steps, improves the efficiency of point monitoring in the tower crane jacking process, and makes the point monitoring in the tower crane jacking process simpler and more convenient.

[0049] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present application, but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings:

[0051] Figure 1 A schematic diagram of a flow chart of a method for monitoring a point position during the jacking process of a tower crane according to an embodiment of the present application is shown;

[0052] Figure 2 A schematic diagram of the structure of a point monitoring device during the jacking process of a tower crane according to an embodiment of the present application is shown;

[0053] Figure 3 The internal structure diagram of a computer device according to an embodiment of the present application is schematically shown.

[0054] Description of Reference Numerals

[0055] 410 - acquisition module; 420 - detection module; 430 - monitoring module; A01 - processor; A02 - network interface; A03 - internal memory; A04 - display screen; A05 - input device; A06 - non-volatile storage medium; B01 - operating system; B02 - computer program. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0057] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of national laws and regulations. In the embodiments of this application, some existing solutions in the industry such as certain software, components, and models may be mentioned, which should be considered as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.

[0058] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back...), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0059] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0060] Figure 1 The following schematically shows a flow chart of a method for monitoring the position of a tower crane during the lifting process according to an embodiment of the present application. Figure 1 As shown, the embodiment of the present application provides a method for monitoring the position of a tower crane during the jacking process, comprising the following steps:

[0061] Step 210: acquiring images of working points in real time, wherein the working points include one or more of a jacking cylinder, an upper pin shaft of a standard section, a lifting frame of a standard section, a lower pin shaft of a standard section, a step-changing support rod, and a crossbeam safety pin shaft;

[0062] In this embodiment, the image of the working point refers to an image of the working conditions of the working point obtained in real time during the tower crane lifting process. It can be obtained by installing a camera at the corresponding position of the working point and shooting it in real time. In specific implementation, the installation position of the camera can be set and adjusted according to actual conditions.

[0063] For example, for the working point of the jacking cylinder, a camera may be set on the crossbeam of the tower crane, and the image of the jacking cylinder may be obtained by reading the picture collected by the camera. For the working point of the upper pin of the standard section, a camera may be set on the upper pin plane, and the image of the upper pin of the standard section may be obtained by reading the picture of the camera installed on the upper pin plane. For the working point of the standard section lifting frame, a camera may be set on the upper pin plane, and the image of the standard section lifting frame may be obtained by reading the picture of the camera installed on the upper pin plane, and the image of the standard section lifting frame may be used to judge the hanging of the standard section lifting frame. A camera may also be installed on the bottom walking net of the upper installation, and the image of the standard section lifting frame may be obtained by reading the picture of the camera installed on the bottom walking net of the upper installation, and the image of the standard section lifting frame may be used to judge the introduction and exit of the standard section lifting frame. For the working point of the lower pin of the standard section, a camera may also be installed on the bottom walking net of the upper installation, and the image of the lower pin of the standard section may be obtained by reading the picture of the camera installed on the bottom walking net of the upper installation. For the step-changing support rod working point, a camera can be installed on the bottom walking net of the upper body, and the image of the step-changing support rod can be obtained by reading the camera image installed on the bottom walking net of the upper body. For the crossbeam safety pin working point, a camera can be set on the crossbeam of the tower crane, and the image of the crossbeam safety pin can be obtained by reading the image collected by the camera. It can be seen that the image of the corresponding working point can be obtained by installing cameras on the crossbeam of the tower crane, the upper pin plane, and the bottom walking net of the upper body.

[0064] Step 220: Based on a preset target detection model, detect key components in the image of the working point to obtain the working status of the working point;

[0065] In this embodiment, the preset target detection model may be a pre-trained target detection model, which is used for target detection of key components in the image of the working point, and the state of the working point is determined by detecting the information of the key components, so as to detect the working state of the current working point. Different working points may have different corresponding key components, which may be determined according to actual conditions.

[0066] For example: the key component corresponding to the working point of the lifting cylinder can be the cylinder sleeve, the key component corresponding to the working point of the upper pin of the standard section can be the pin, the key component corresponding to the working point of the standard section lifting frame can be the standard section lifting frame, the key component corresponding to the working point of the lower pin of the standard section can be the pin, the key component corresponding to the working point of the step-changing support rod can be the support rod, the step and the combination of the step support rod, the key component corresponding to the crossbeam safety pin can be the ohm ring, the pin ring, the handle and the step. When the working point is the lifting cylinder, its corresponding working state includes the retraction and extension of the lifting cylinder; when the working point is the upper pin of the standard section, its corresponding working state includes the insertion and withdrawal of the upper pin of the standard section; when the working point is the standard section lifting frame, its corresponding working state includes the hanging in, the introduction and withdrawal of the standard section lifting frame; when the working point is the lower pin of the standard section, its corresponding working point includes the insertion and withdrawal of the lower pin of the standard section; when the working point is the step-changing support rod, its corresponding working point includes whether the step-changing support rod is stepped on the step; when the working point is the crossbeam safety pin, its corresponding working point includes the insertion and withdrawal of the crossbeam safety pin.

[0067] In some embodiments, the process of constructing the preset target detection model may include:

[0068] First, a training sample is obtained, wherein the training sample includes key component information of multiple working points and corresponding working states;

[0069] In this embodiment, the training samples may be obtained through historical tower crane lifting process data, including key component information of the working point and the corresponding working status.

[0070] Then, the training samples are used to train the preset detection model to obtain the target detection model.

[0071] In this embodiment, the preset detection model may be a model pre-built based on a target detection algorithm, including a Yolov10-based target detection algorithm, a Transformer-based target detection algorithm, etc. The construction of the preset detection model belongs to the prior art and will not be described in detail here.

[0072] By using training samples to train the preset detection model, an accurate target detection model can be obtained to facilitate accurate detection of key components.

[0073] In some embodiments, when the working point is a lifting cylinder and / or a standard section lifting frame on a tower crane, accordingly, based on a preset target detection model, detecting key components in the image of the working point to obtain the working state of the working point includes the following steps:

[0074] Firstly, a preset target detection model is used to identify the image of the working point to obtain a first recognition result;

[0075] In this embodiment, the image of the working point may be recognized by a target detection model, and the target detection model may be a model pre-trained based on a target detection algorithm for recognizing various key components.

[0076] Then, based on the first recognition result, it is determined whether there is a corresponding key component in the image of the working point, and first key component information is obtained;

[0077] In this embodiment, the above judgment can be to compare the first recognition result with the key component of the preset working point to determine whether the first recognition result includes the key component. The obtained first key component information includes key component information corresponding to the working point and key component information not corresponding to the working point.

[0078] Finally, based on the first key component information, the working status of the working point is obtained.

[0079] In this embodiment, the working status of the working point can be determined according to whether the key component in the first key component information exists.

[0080] For example, when the working point is a lifting cylinder on a tower crane, the image from a camera placed on the beam can be read, and a preset target detection model can be used to identify whether a cylinder sleeve exists in the image to determine whether the cylinder is retracted.

[0081] For example, when the working point is the standard section lifting frame on the tower crane, the image of the camera installed on the upper pin plane is read, and the target detection model is used to identify whether the standard section lifting frame exists in the image to determine whether the standard section lifting frame is hung in. The image of the camera installed on the bottom walking net of the upper installation can also be read, and the target detection model is used to identify whether the standard section lifting frame exists in the image to determine whether the standard section lifting frame is introduced and exited.

[0082] It should be noted that the image of the working point may include both the image of the jacking cylinder and the image of the standard section lifting frame. When performing key component inspection, the two images may be inspected separately according to the above steps to obtain the working status of the jacking cylinder and the working status of the standard section lifting frame respectively, which will not be repeated here.

[0083] By identifying whether there are corresponding key components in the image of the working point, the working status of the jacking cylinder and the working status of the standard section lifting frame can be determined quickly and accurately.

[0084] In some embodiments, when the working point is a standard section upper pin and / or a standard section lower pin on a tower crane, correspondingly, detecting key components in the image of the working point based on a preset target detection model to obtain the working state of the working point includes the following steps:

[0085] Firstly, a preset target detection model is used to identify the image of the working point to obtain a second recognition result;

[0086] In this embodiment, the image of the working point may be recognized by a target detection model, and the target detection model may be a model pre-trained based on a target detection algorithm for recognizing various key components.

[0087] Then, based on the second recognition result, it is determined whether there is a corresponding key component in the image of the working point, and the second key component information is obtained;

[0088] In this embodiment, the above judgment can be to compare the second recognition result with the key component of the preset working point to determine whether the second recognition result includes the key component. The obtained second key component information includes key component information corresponding to the working point and key component information not corresponding to the working point.

[0089] Then, based on the second key component information, it is determined whether the corresponding key component meets the preset length requirement, and the third key component information is obtained;

[0090] In this embodiment, when the second key component information includes key component information corresponding to the working point, it is further determined whether the corresponding key component meets the preset length requirement, and the preset length requirement can be preset according to actual conditions, and can refer to the length requirement of the key component. The third key component information includes whether the corresponding key component meets the preset length requirement and whether the corresponding key component does not meet the preset length requirement.

[0091] Finally, based on the second key component information and the three key component information, the working status of the working point is obtained.

[0092] In this embodiment, the working status of the working point is finally determined by combining the second key component information and the third key component information.

[0093] For example: when the working point is the upper pin of the standard section, the image of the camera installed on the upper pin plane can be read, and the target detection model can be used to identify whether there is a short pin in the image to determine the insertion and extraction of the upper pin of the standard section of the cylinder. The above-mentioned identification of whether there is a short pin can be to first identify whether there is a pin, and then further identify whether the length of the pin in the image meets the preset length requirement. If so, it means that there is a short pin, otherwise it is considered that the upper pin has become longer.

[0094] It should be noted that the upper pins that have been inserted or pulled out can also be counted. When an upper pin point is determined to be inserted or pulled out, the camera will move to the next upper pin point to shoot, and then perform the above target detection. When all four upper pins are inserted or pulled out, the step of checking the upper pins is completed.

[0095] For example: when the working point is the lower pin of the standard section, the image of the camera installed on the walking net at the bottom of the upper installation can be read, and the target detection model can be used to identify whether there is a short pin in the image to determine the insertion and extraction of the lower pin of the standard section of the cylinder. The above-mentioned identification of whether there is a short pin can first identify whether there is a pin, and then further identify whether the length of the pin in the image meets the preset length requirement. If it does, it means that there is a short pin, otherwise it is considered that the lower pin has become longer.

[0096] It should be noted that the lower pins that have been inserted or pulled out can also be counted. When all the lower pins in a picture are judged to be inserted or pulled out, the camera will move to the next lower pin point to shoot, and then perform the above-mentioned target detection algorithm. When all four lower pins are inserted or pulled out, the step of checking the lower pins is completed.

[0097] It should be noted that the image of the working point may include both the image of the upper pin of the standard section and the image of the lower pin of the standard section. When performing key component inspection, the two images may be inspected separately according to the above steps to obtain the working status of the upper pin of the standard section and the working status of the lower pin of the standard section respectively. This will not be repeated here.

[0098] By identifying whether there is a corresponding key component in the image of the working point, and further judging whether the corresponding key component meets the preset length requirement, the working status of the upper pin shaft of the standard section and the working status of the lower pin shaft of the standard section can be determined quickly and accurately.

[0099] In some embodiments, the working point is a step-changing support rod on a tower crane, and the key components corresponding to the image of the working point include a support rod, a step, and a step support rod assembly;

[0100] Accordingly, the method of detecting key components in the image of the working point based on a preset target detection model to obtain the working status of the working point includes the following steps:

[0101] First, a preset target detection model is used to recognize the image of the working point to obtain a third recognition result;

[0102] In this embodiment, the image of the working point may be recognized by a target detection model, and the target detection model may be a model pre-trained based on a target detection algorithm for recognizing various key components.

[0103] Then, based on the third recognition result, it is determined whether there are support rods, steps, and step support rod assemblies in the image of the working point respectively;

[0104] In this embodiment, the above determination may be to determine whether the third recognition result includes the existence of a support rod, a step, and a step support rod assembly.

[0105] Then, when it is determined that there are a support rod and a step in the image of the working point, it is determined that the working state of the step-changing support rod is that the support rod has not stepped into the step;

[0106] Then, when it is determined that the step support rod assembly and the step exist in the image of the working point, it is determined that the working state of the step-changing support rod is that the support rod has stepped into the step.

[0107] In this embodiment, if there are a support rod and a step, it means that the working state of the step-changing support rod is that the support rod has not stepped into the step; if there is a step support rod assembly and a step, it means that the working state of the step-changing support rod is that the support rod has stepped into the step; when the support rod, the step and the step support rod assembly exist at the same time, it means that an abnormal situation has occurred.

[0108] For example: when the working point is the step-changing support rod on the tower crane, the image of the camera installed on the walking net at the bottom of the upper installation can be read, and the target detection model can be used to identify whether there are support rods, steps, and a combination of step support rods in the image to determine whether the step-changing support rod is stepped into the step.

[0109] By respectively identifying whether the support rod, the step and the step support rod assembly exist in the image of the working point, it is possible to quickly and accurately detect whether the step-changing support rod is stepped into the step.

[0110] In some embodiments, the working point is a beam safety pin on a tower crane, and the key components corresponding to the image of the working point include an ohmic ring, a pin ring, and a step;

[0111] Accordingly, the method of detecting key components in the image of the working point based on a preset target detection model to obtain the working status of the working point includes the following steps:

[0112] First, using a preset target detection model, the image of the working point is recognized to obtain a fourth recognition result;

[0113] In this embodiment, the image of the working point may be recognized by a target detection model, and the target detection model may be a model pre-trained based on a target detection algorithm for recognizing various key components.

[0114] Then, based on the fourth recognition result, it is determined whether an ohmic ring, a pin ring, and a step are present in the image of the working point;

[0115] Then, when it is determined that an ohmic ring, a pin ring and a step exist in the image of the working point, it is determined whether the distance between the ohmic ring and the pin ring meets a preset threshold;

[0116] Then, when it is determined that the distance between the ohmic ring and the pin ring meets a preset threshold, it is determined that the working state of the beam safety pin is that the beam safety pin is inserted.

[0117] In this embodiment, the above-mentioned preset threshold value can be preset according to the actual situation, and can be specifically input into the algorithm by experimental measurement before the model is run. The camera image installed on the beam is read, and the ohmic ring, pin ring and step in the image are identified by the target detection algorithm. The judgment condition for the insertion of the beam safety pin is: when the step exists, the distance between the center of the square frame of the ohmic ring and the center of the square frame of the pin ring is less than the preset threshold value, otherwise it is judged that the beam safety pin is not inserted.

[0118] It should be noted that for some tower cranes, there is no pin ring, and the pin ring can be replaced by identifying the crossbeam latch operating handle.

[0119] By judging whether an ohmic ring, a pin ring and a step exist in the image of the working point, and further judging whether the distance between the ohmic ring and the pin ring meets a preset threshold when an ohmic ring, a pin ring and a step exist in the image of the working point, it is possible to quickly and accurately detect whether the crossbeam safety pin is in an inserted working state or a pulled out working state.

[0120] Step 230: Based on the working status of the working point, a monitoring result of the working point is obtained.

[0121] In this embodiment, after the working state of the working point is obtained, the working state can be used as the monitoring result of the working point. Thus, key point monitoring in the tower crane jacking process based on the visual recognition algorithm is realized. It should be noted that when the method is implemented, it can be carried in the tower crane safety jacking monitoring system, so as to realize artificial intelligence (AI) visual monitoring of the tower crane jacking process.

[0122] In the above implementation process, by acquiring the image of the working point in real time, the working point includes one or more of the jacking cylinder, the upper pin of the standard section, the lifting frame of the standard section, the lower pin of the standard section, the step-changing support rod and the crossbeam safety pin; based on the preset target detection model, the key components in the image of the working point are detected to obtain the working state of the working point; based on the working state of the working point, the monitoring result of the working point is obtained. By detecting the key components in the image of the working point by the preset target detection model, the working state of the working point can be quickly and accurately determined, and then the working point can be monitored, and visual monitoring and identification of all key points in the tower crane jacking process can be realized. The point monitoring method in the tower crane jacking process does not rely on sensors, and does not involve the installation and debugging of sensors, reduces the wiring difficulty and debugging steps, improves the efficiency of point monitoring in the tower crane jacking process, and makes the point monitoring in the tower crane jacking process simpler and more convenient. In this method, only the AI ​​algorithm of target detection is called, which requires less computing power and saves computing power resources.

[0123] In some embodiments, the detecting of key components in the image of the working point based on a preset target detection model to obtain the working status of the working point includes:

[0124] Firstly, a preset target detection model is used to identify key components in the image of the working point to obtain information of multiple key components;

[0125] In this embodiment, the image of the working point may include key components corresponding to multiple working points, and accordingly, the obtained key component information may include multiple key components.

[0126] Then, based on the multiple key component information, key component information corresponding to different working points is matched;

[0127] In this embodiment, corresponding working points can be pre-set for different key component information, and the above matching can be performed according to pre-set rules. For example, the image of the working point taken includes four key component information of the cylinder sleeve, ohm ring, pin ring and step, among which the working point corresponding to the cylinder sleeve is the jacking cylinder, and the working point corresponding to the ohm ring, pin ring and step is the crossbeam safety pin.

[0128] Finally, based on the key component information corresponding to the different working points, the working status of the different working points is obtained.

[0129] In this embodiment, the working state of the corresponding working point can be determined by the key component information corresponding to different working points. The process of determining the working state of the corresponding working point is the same as the process of determining the working state of each working point, which will not be repeated here.

[0130] By matching the key component information corresponding to different working points based on the multiple key component information, and obtaining the working status of the different working points based on the key component information corresponding to the different working points, it is possible to detect the situation where an image of a working point includes key components corresponding to multiple working points, which helps to improve the reliability of determining the working status of the working points.

[0131] This embodiment provides a point monitoring system during the tower crane lifting process, including a camera and a monitoring host, wherein the camera is arranged on the tower crane;

[0132] The camera is used to obtain images of working points in real time, and the working points include one or more of a jacking cylinder, an upper pin shaft of a standard section, a lifting frame of a standard section, a lower pin shaft of a standard section, a step-changing support rod, and a crossbeam safety pin shaft;

[0133] The monitoring host is used to detect key components in the image of the working point based on a preset target detection model to obtain the working status of the working point; based on the working status of the working point, obtain the monitoring result of the working point.

[0134] In this embodiment, the camera can be a detachable camera, and the number of cameras is determined according to actual conditions. The monitoring host can be a computer or a device with a computing and processing function.

[0135] Wherein, the position of the camera is determined according to the position of the working point.

[0136] In this embodiment, the camera can be set according to different working points, such as: for the working point of the upper pin of the standard section, the camera can be set on the upper pin plane, and the image of the upper pin of the standard section can be obtained by reading the picture of the camera installed on the upper pin plane. For the working point of the standard section lifting frame, the camera can also be set on the upper pin plane, and the image of the standard section lifting frame can be obtained by reading the picture of the camera installed on the upper pin plane. The image of the standard section lifting frame can be used to judge the hanging of the standard section lifting frame. The camera can also be installed on the bottom walking net of the upper body, and the image of the standard section lifting frame can be obtained by reading the picture of the camera installed on the bottom walking net of the upper body, and the image of the standard section lifting frame can be used to judge the introduction and exit of the standard section lifting frame. For the working point of the lower pin of the standard section, the camera can also be installed on the bottom walking net of the upper body, and the image of the lower pin of the standard section can be obtained by reading the picture of the camera installed on the bottom walking net of the upper body. For the working point of the step-changing support rod, the camera can also be installed on the bottom walking net of the upper body, and the image of the step-changing support rod can be obtained by reading the picture of the camera installed on the bottom walking net of the upper body. For the working point of the beam safety pin, a camera can be set on the beam of the tower crane, and the image of the beam safety pin can be obtained by reading the picture collected by the camera. It can be seen that the image of the corresponding working point can be obtained by installing cameras on the beam of the tower crane, the upper pin plane, and the upper bottom walking net.

[0137] In the above implementation process, by setting a camera on the tower crane, the camera acquires the image of the working point in real time, and the working point includes one or more of the jacking cylinder, the upper pin of the standard section, the lifting frame of the standard section, the lower pin of the standard section, the step-changing support rod and the crossbeam safety pin; the monitoring host detects the key components in the image of the working point based on the preset target detection model to obtain the working state of the working point; based on the working state of the working point, the monitoring result of the working point is obtained. By detecting the key components in the image of the working point through the preset target detection model, the working state of the working point can be quickly and accurately determined, and then the working point can be monitored, so as to realize the visual monitoring and identification of all key points in the tower crane jacking process. The system does not need to install sensors, so it will not involve the installation and debugging of sensors, which reduces the wiring difficulty and debugging steps, improves the efficiency of point monitoring during the tower crane jacking process, and makes the point monitoring during the tower crane jacking process simpler and more convenient. In the monitoring of this system, only the AI ​​algorithm of target detection is called, which requires less computing power and saves computing power resources.

[0138] Please see Figure 2 , Figure 2The schematic diagram of the structure of a point monitoring device during the tower crane lifting process according to an embodiment of the present application is schematically shown. This embodiment provides a point monitoring device during the tower crane lifting process, including an acquisition module 410, a detection module 420 and a monitoring module 430, wherein:

[0139] An acquisition module 410 is used to acquire images of working points in real time, wherein the working points include one or more of a jacking cylinder, an upper pin of a standard section, a lifting frame of a standard section, a lower pin of a standard section, a step-changing support rod, and a crossbeam safety pin;

[0140] A detection module 420 is used to detect key components in the image of the working point based on a preset target detection model to obtain the working status of the working point;

[0141] The monitoring module 430 is used to obtain the monitoring result of the working point based on the working status of the working point.

[0142] The point monitoring device during the tower crane lifting process includes a processor and a memory. The acquisition module 410, the detection module 420 and the monitoring module 430 are all stored in the memory as program units, and the processor executes the program units stored in the memory to realize the corresponding functions.

[0143] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the position monitoring of the tower crane during the lifting process can be achieved by adjusting the kernel parameters.

[0144] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0145] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 3As shown. The computer device includes a processor A01, a network interface A02, a display screen A04, an input device A05 and a memory (not shown in the figure) connected through a system bus. Among them, the processor A01 of the computer device is used to provide computing and control capabilities. The memory of the computer device includes an internal memory A03 and a non-volatile storage medium A06. The non-volatile storage medium A06 stores an operating system B01 and a computer program B02. The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 in the non-volatile storage medium A06. The network interface A02 of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor A01, a method for monitoring points during the lifting process of a tower crane is implemented. The display screen A04 of the computer device can be a liquid crystal display or an electronic ink display, and the input device A05 of the computer device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse.

[0146] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0147] In one embodiment, the tower crane jacking process point monitoring device provided in the present application can be implemented in the form of a computer program. The computer program can be Figure 3 The computer device shown in the figure is run on the computer device. The memory of the computer device can store various program modules that constitute the point monitoring device during the tower crane lifting process, such as: Figure 2 The acquisition module 410, the detection module 420 and the monitoring module 430 are shown. The computer program composed of various program modules enables the processor to execute the steps of the method for monitoring the position of a tower crane during the jacking process of each embodiment of the present application described in this specification.

[0148] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0149] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0150] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0151] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0152] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0153] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0154] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0155] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0156] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for monitoring the position of a tower crane during its lifting process, characterized in that: include: Acquire images of working points in real time, wherein the working points include one or more of a jacking cylinder, an upper pin shaft of a standard section, a lifting frame of a standard section, a lower pin shaft of a standard section, a step-changing support rod, and a crossbeam safety pin shaft; Based on a preset target detection model, key components in the image of the working point are detected to obtain the working status of the working point; Based on the working status of the working point, a monitoring result of the working point is obtained.

2. The method according to claim 1, characterized in that: The working point is the jacking cylinder and / or standard section lifting frame on the tower crane; The detecting of key components in the image of the working point based on a preset target detection model to obtain the working state of the working point includes: Using a preset target detection model to recognize the image of the working point, and obtain a first recognition result; Based on the first recognition result, determining whether there is a corresponding key component in the image of the working point, and obtaining first key component information; Based on the first key component information, the working status of the working point is obtained.

3. The method according to claim 1, characterized in that: The working point is the upper pin shaft of the standard section and / or the lower pin shaft of the standard section on the tower crane; The detecting of key components in the image of the working point based on a preset target detection model to obtain the working state of the working point includes: Using a preset target detection model to recognize the image of the working point, and obtain a second recognition result; Based on the second recognition result, determining whether there is a corresponding key component in the image of the working point, and obtaining second key component information; Based on the second key component information, determining whether the corresponding key component meets a preset length requirement, and obtaining third key component information; Based on the second key component information and the three key component information, the working status of the working point is obtained.

4. The method according to claim 1, characterized in that: The working point is a step-changing support rod on a tower crane, and the key components corresponding to the image of the working point include a support rod, a step, and a step support rod assembly; The detecting of key components in the image of the working point based on a preset target detection model to obtain the working state of the working point includes: Using a preset target detection model to recognize the image of the working point, and obtaining a third recognition result; Based on the third recognition result, determining whether there are support rods, steps, and step support rod assemblies in the image of the working point; In the case where it is determined that there are a support rod and a step in the image of the working point, it is determined that the working state of the step-changing support rod is that the support rod has not stepped into the step; When it is determined that the step support rod assembly and the step exist in the image of the working point, it is determined that the working state of the step-changing support rod is that the support rod has stepped into the step.

5. The method according to claim 1, characterized in that The working point is a beam safety pin on a tower crane, and the key components corresponding to the image of the working point include an ohmic ring, a pin ring, and a step; The detecting of key components in the image of the working point based on a preset target detection model to obtain the working state of the working point includes: Using a preset target detection model to recognize the image of the working point, and obtaining a fourth recognition result; Based on the fourth recognition result, determining whether there is an ohmic ring, a pin ring, and a step in the image of the working point; In the case where it is determined that an ohmic ring, a pin ring and a step exist in the image of the working point, judging whether the distance between the ohmic ring and the pin ring meets a preset threshold; When it is determined that the distance between the ohmic ring and the pin ring meets a preset threshold, it is determined that the working state of the beam safety pin is that the beam safety pin is inserted.

6. The method according to claim 1, characterized in that The detecting of key components in the image of the working point based on a preset target detection model to obtain the working state of the working point includes: Using a preset target detection model, key components in the image of the working point are identified to obtain information of multiple key components; Based on the multiple key component information, matching key component information corresponding to different working points; Based on the key component information corresponding to the different working points, the working status of the different working points is obtained.

7. The method according to claim 1, characterized in that The construction process of the preset target detection model includes: Acquire training samples, wherein the training samples include key component information of multiple working points and corresponding working states; The training samples are used to train the preset detection model to obtain the target detection model.

8. A point monitoring system during the tower crane lifting process, characterized in that: It includes a camera and a monitoring host, wherein the camera is arranged on the tower crane; The camera is used to obtain images of working points in real time, and the working points include one or more of a jacking cylinder, an upper pin shaft of a standard section, a lifting frame of a standard section, a lower pin shaft of a standard section, a step-changing support rod, and a crossbeam safety pin shaft; The monitoring host is used to detect key components in the image of the working point based on a preset target detection model to obtain the working status of the working point; Based on the working status of the working point, a monitoring result of the working point is obtained.

9. The system according to claim 8, characterized in that The position of the camera is determined according to the position of the working point.

10. A point monitoring device during the tower crane lifting process, characterized in that: include: An acquisition module is used to acquire images of working points in real time, wherein the working points include one or more of a jacking cylinder, an upper pin shaft of a standard section, a lifting frame of a standard section, a lower pin shaft of a standard section, a step-changing support rod, and a crossbeam safety pin shaft; A detection module, used to detect key components in the image of the working point based on a preset target detection model to obtain the working status of the working point; The monitoring module is used to obtain the monitoring result of the working point based on the working status of the working point.

Images