Method and device for monitoring shielding of measured object

Abstract

The invention provides a method and a device for monitoring shielding of a measured object. The method comprises the following steps: capturing image data of the measured object in a monitoring scene in real time; when it is monitored that an operator enters a preset range of the measured object in the image data, determining a space relative distance between the operator and the measured object; storing the image data according to a preset time interval; extracting human body skeleton nodes of the operator from the stored target image data; based on the human skeleton nodes, calculating the change condition of the relative position relationship between the operator and the measured object within the time interval; and judging whether the detected object is operated by the operator or not according to the change condition of the relative position. The method and the device are used for monitoring whether a measured object is operated by an operator or not under the condition that the measured object is shielded, so that the monitoring accuracy and efficiency are improved, and the need of manual intervention is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of image detection, and in particular to a monitoring method and device when a detected object is blocked. Background Art

[0002] In scenarios such as forklift driving and factory buildings, accurately judging the relative positions between targets and the operations performed after the measured object is blocked is crucial to improving system safety and accuracy. The current main method is to use a 2D camera with an area intrusion-related algorithm to estimate whether a person has performed an operation on the measured object. However, this method has the following problems:

[0003] (1) Target occlusion: When a person stands between the monitored object and the camera, it is difficult to detect whether the person has operated the object.

[0004] (2) Lighting changes: Changes in lighting conditions can affect the imaging quality of 2D cameras and thus affect the accuracy of target detection.

[0005] (3) Background interference: Complex background environment will interfere with the target detection algorithm, resulting in misjudgment or missed detection.

[0006] These problems make it impossible for traditional target detection algorithms to accurately determine whether a person is close to the object being detected, or whether the person has performed an operation on the object being detected when the person blocks the object being detected. This seriously limits the reliability and security of the system. Summary of the invention

[0007] The present invention provides a monitoring method and device for when a measured object is blocked, which are used to monitor whether the measured object is operated by an operator when the measured object is blocked.

[0008] In a first aspect, the present invention provides a monitoring method when an object to be measured is blocked, comprising:

[0009] Capture image data of the object being measured in the monitoring scene in real time;

[0010] When it is detected in the image data that a worker enters a preset range of the object to be measured, determining a relative spatial distance between the worker and the object to be measured;

[0011] Saving the image data at preset time intervals;

[0012] Extracting the human skeleton nodes of the operator from the stored target image data;

[0013] Based on the human skeleton nodes, calculating the change in the relative position relationship between the operator and the object under test within the time interval;

[0014] According to the relative position change, it is determined whether the object to be measured is operated by the operator.

[0015] Optionally, when it is detected in the image data that a worker enters a preset range of the object to be measured, determining the relative spatial distance between the worker and the object to be measured includes:

[0016] Input the image data into the trained YOLOv8 target detection network to obtain the target detection result;

[0017] When the target monitoring result includes the operator and the operator enters the preset range of the object to be measured, determining the plane position information of the operator and the object to be measured;

[0018] Based on the planar position information, the spatial relative distance between the operator and the object to be measured is determined.

[0019] Optionally, determining the spatial relative distance between the operator and the measured object based on the planar position information includes:

[0020] Establishing a perspective transformation model according to the perspective information of the monitoring scene;

[0021] Using the perspective transformation model, converting the plane position information of the operator and the object to be measured into the spatial position information of the operator and the object to be measured respectively;

[0022] The spatial relative distance between the operator and the measured object is calculated by using a preset transformation formula in combination with the spatial position information.

[0023] Optionally, based on the human skeleton nodes, calculating the change in the relative position relationship between the operator and the object under test within the time interval includes:

[0024] Extracting wrist nodes from the human skeleton nodes;

[0025] Calculate the change of the relative position relationship between the wrist node and the object under test within the time interval.

[0026] Optionally, judging whether the object to be measured is operated by the operator according to the relative position change includes:

[0027] If the relative spatial distance between the wrist node and the object to be measured is reduced compared to before the time interval, it is determined that the object to be measured is operated by the operator;

[0028] If the spatial relative distance between the wrist node and the object to be measured remains unchanged or increases compared to before the time interval, it is determined that the object to be measured has not come into contact with the operator.

[0029] In a second aspect, the present invention provides a monitoring device when a detected object is blocked, comprising:

[0030] An acquisition module is used to capture image data of the object under test in the monitoring scene in real time;

[0031] A relative distance determination module, for determining the relative distance between the operator and the object to be measured when it is detected in the image data that an operator has entered a preset range of the object to be measured;

[0032] A saving module, used for saving the image data at a preset time interval;

[0033] An extraction module, used for extracting the human skeleton nodes of the operator from the stored target image data;

[0034] A position change determination module, used to calculate the change of the relative position relationship between the operator and the object to be measured within the time interval based on the human skeleton nodes;

[0035] The judgment module is used to judge whether the object to be measured is operated by the operator according to the change of the relative position.

[0036] Optionally, the relative distance determination module includes:

[0037] An input submodule is used to input the image data into a trained YOLOv8 target detection network to obtain a target detection result;

[0038] A plane position information determination submodule, used for determining the plane position information of the operator and the object to be measured when the target monitoring result includes the operator and the operator enters the preset range of the object to be measured;

[0039] The spatial relative distance determination submodule is used to determine the spatial relative distance between the operator and the object to be measured based on the planar position information.

[0040] In a third aspect, the present invention provides an electronic device, comprising a processor and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in the method provided in the first aspect are performed.

[0041] In a fourth aspect, the present invention provides a storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, runs the steps of the method provided in the first aspect.

[0042] In a fifth aspect, the present invention provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the steps in the method provided in the first aspect are performed.

[0043] It can be seen from the above technical solutions that the present invention has the following advantages:

[0044] The present invention provides a monitoring method and device when the object to be measured is blocked, and the method includes: real-time capture of image data of the object to be measured in the monitoring scene; when it is detected that there is an operator entering the preset range of the object to be measured in the image data, determining the relative spatial distance between the operator and the object to be measured; saving the image data according to a preset time interval; extracting the human skeleton nodes of the operator from the saved target image data; based on the human skeleton nodes, calculating the change of the relative position relationship between the operator and the object to be measured within the time interval; judging whether the object to be measured is operated by the operator according to the relative position change. It is used to extract the human skeleton nodes of the operator from the target image data in special scenarios where the object to be measured is blocked, and calculate the change of the relative position relationship between the operator and the object to be measured within the time interval based on the human skeleton nodes, determine whether the object to be measured is operated, improve the accuracy and efficiency of monitoring, and reduce the need for manual intervention, thereby reducing the risk of human error. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0046] Figure 1 This is a flow chart of a first embodiment of a monitoring method for when a detected object is blocked according to the present invention;

[0047] Figure 2 This is a flow chart of a second embodiment of a monitoring method when a detected object is blocked according to the present invention;

[0048] Figure 3 This is a target detection schematic diagram of a second embodiment of a monitoring method when a detected object is blocked by the present invention;

[0049] Figure 4This is a schematic diagram of a wrist node approaching an object to be measured in Embodiment 2 of a monitoring method when an object to be measured is blocked by the present invention;

[0050] Figure 5 The present invention is a structural block diagram of an embodiment of a monitoring device when a detected object is blocked. DETAILED DESCRIPTION

[0051] The embodiments of the present invention provide a method and device for monitoring when a measured object is blocked, which are used to monitor whether the measured object is operated by an operator when the measured object is blocked.

[0052] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions 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 embodiments described below 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 are within the scope of protection of the present invention.

[0053] For example, see Figure 1 , Figure 1 This is a flow chart of a first embodiment of a monitoring method for an object under test when the object under test is blocked according to the present invention. The method includes:

[0054] Step S101, capturing image data of the object under test in the monitoring scene in real time;

[0055] In an embodiment of the present application, a suitable camera or other type of image acquisition device is selected and deployed in the monitoring scene. During use, the image acquisition device adjusts the angle and focal length according to the position and size of the object to be measured to ensure that the object to be measured is always within the field of view of the image acquisition device.

[0056] In a specific implementation, the captured image data needs to undergo a preprocessing process including denoising, contrast enhancement and brightness adjustment to improve the accuracy of subsequent image analysis.

[0057] Step S102, when it is detected in the image data that a worker enters a preset range of the object to be measured, determining a relative spatial distance between the worker and the object to be measured;

[0058] In an embodiment of the present application, through a target detection algorithm, when a worker is present in real-time captured image data and the worker enters a virtual preset range of the object to be measured, image processing technology is used to calculate the spatial relative distance between the worker and the object to be measured in three-dimensional space.

[0059] Step S103, saving the image data at a preset time interval;

[0060] In the embodiment of the present application, the preset time interval is 3 seconds.

[0061] In the specific implementation, when it is detected in the image data that there is a worker entering the preset range of the object to be measured, the image data of the current frame is saved every 3 seconds, and these target image data are saved to a local storage device or cloud storage, and timestamp information is generated for subsequent retrieval.

[0062] Step S104, extracting the human skeleton nodes of the operator from the stored target image data;

[0063] In an embodiment of the present application, the human skeleton nodes of the operator are extracted through a human posture estimation algorithm, and the extracted skeleton node information is saved in the data results.

[0064] In a specific implementation, in order to ensure the accuracy of the extracted human skeleton nodes, the human skeleton nodes need to be filtered to remove noise and erroneous detection results.

[0065] Step S105, calculating the change of the relative position relationship between the operator and the object to be measured within the time interval based on the human skeleton nodes;

[0066] In the embodiment of the present application, for each time interval (3 seconds), the spatial relative distance between the operator's skeletal nodes and the object being measured is calculated, and then the change in their relative position relationship is determined.

[0067] Step S106: judging whether the object to be measured is operated by the operator according to the relative position change.

[0068] In the embodiment of the present application, based on the data record of the change in the relative position relationship, it is checked whether it meets the preset operation judgment rules.

[0069] The monitoring method provided by the embodiment of the present invention when the measured object is blocked includes: real-time capturing of the image data of the measured object in the monitoring scene; when it is detected that there is an operator entering the preset range of the measured object in the image data, determining the relative spatial distance between the operator and the measured object; saving the image data at a preset time interval; extracting the human skeleton nodes of the operator from the saved target image data; calculating the change of the relative position relationship between the operator and the measured object within the time interval based on the human skeleton nodes; judging whether the measured object is operated by the operator according to the change of the relative position. It is used to extract the human skeleton nodes of the operator from the target image data in special scenarios where the measured object is blocked, and calculate the change of the relative position relationship between the operator and the measured object within the time interval based on the human skeleton nodes, determine whether the measured object is operated, improve the accuracy and efficiency of monitoring, and reduce the need for manual intervention, thereby reducing the risk of human error.

[0070] For example 2, please refer to Figure 2 , Figure 2 This is a flow chart of a second embodiment of a monitoring method for when a detected object is blocked according to the present invention, and the steps include:

[0071] Step S201, capturing image data of the object under test in the monitoring scene in real time;

[0072] Step S202, inputting the image data into a trained YOLOv8 target detection network to obtain a target detection result;

[0073] Step S203, when the target monitoring result includes the operator and the operator enters the preset range of the measured object, determining the plane position information of the operator and the measured object;

[0074] See also Figure 3 , Figure 3 This is a schematic diagram of target detection in Example 2 of a monitoring method for when a measured object is obstructed by the present invention. The embodiment of the present application uses an image acquisition device such as a camera to capture image data in a monitoring scene in real time, and inputs the image data into a target detection module. The YOLOv8 target detection network in the target detection module is used to efficiently identify the workers and measured objects in the image, and divide the region of interest containing these targets, thereby reducing errors.

[0075] In the specific implementation, technologies such as depthwise separable convolution, feature pyramid network (FPN) and path aggregation network (PAN) can be used to improve monitoring speed and accuracy.

[0076] Step S204, determining the spatial relative distance between the operator and the measured object based on the planar position information;

[0077] In an optional embodiment, determining the spatial relative distance between the operator and the measured object based on the planar position information includes:

[0078] Establishing a perspective transformation model according to the perspective information of the monitoring scene;

[0079] Using the perspective transformation model, converting the plane position information of the operator and the object to be measured into the spatial position information of the operator and the object to be measured respectively;

[0080] The spatial relative distance between the operator and the measured object is calculated by using a preset transformation formula in combination with the spatial position information.

[0081] In the application embodiment, a perspective transformation model is established based on the perspective information of the monitoring scene, including the focal length and optical center position of the camera, and the geometric characteristics of the monitoring scene that may be involved, such as the position and inclination of the plane or wall. Then, through the scene modeling method, the perspective change parameters are further refined, and then the plane position information in the image data is converted into spatial position information in three-dimensional space, thereby determining the spatial relative distance between the operator and the object being measured.

[0082] The spatial relative distance between the operator and the object being measured is determined by a preset transformation formula, which is specifically: spatial relative distance = (object height / pixel height) * distance transformation coefficient, wherein the distance transformation coefficient is defined in combination with focal length and other conditions, and a calibration method may be used.

[0083] Step S205, saving the image data at a preset time interval;

[0084] In the embodiment of the present application, the pixel area of ​​the object under test detected by the YOLOv8 target detection algorithm is retained, temporarily stored for 3 seconds, and updated every 3 seconds. That is, each frame obtained by the algorithm contains two pieces of information, one is the current real-time frame, and the other is the pixel area of ​​the object under test three seconds ago.

[0085] Step S206, extracting the human skeleton nodes of the operator from the stored target image data;

[0086] In an embodiment of the present application, the human skeleton near the object to be measured is extracted based on the YOLOv8 target detection network, and the coordinate information of each key point is output. These coordinates can be further analyzed and visualized by post-processing steps, such as forming the skeleton structure of the human body by connecting adjacent key points, thereby extracting human skeleton node information. This step marks and stores 17 human skeleton nodes to compare the skeleton nodes with the pixel area of ​​the object to be measured.

[0087] Step S207, extracting wrist nodes from the human skeleton nodes;

[0088] Step S208, calculating the change of the relative position relationship between the wrist node and the object under test within the time interval;

[0089] Step S209: judging whether the object to be measured is operated by the operator according to the relative position change.

[0090] In an embodiment of the present application, if the relative spatial distance between the wrist node and the object to be measured is reduced compared to before the time interval, it is determined that the object to be measured is operated by the operator; if the relative spatial distance between the wrist node and the object to be measured remains unchanged or increases compared to before the time interval, it is determined that the object to be measured has not been in contact with the operator.

[0091] See also Figure 4 , Figure 4 This is a schematic diagram of the wrist node approaching the object to be measured in Example 2 of a monitoring method for when the object to be measured is obstructed by the present invention. In this embodiment of the application, it is calculated whether the wrist node is close to the object to be measured within an event interval of 3 seconds, that is, the wrist node is close to the pixel of the cart three seconds ago, so as to determine whether the operator has performed an operation on the object to be measured (the cart in the figure).

[0092] The embodiment of the present invention discloses a monitoring method when the object to be measured is blocked, comprising: capturing image data of the object to be measured in the monitoring scene in real time; when it is detected that there is an operator entering the preset range of the object to be measured in the image data, determining the relative spatial distance between the operator and the object to be measured; saving the image data at a preset time interval; extracting the human skeleton nodes of the operator from the saved target image data; based on the human skeleton nodes, calculating the change in the relative position relationship between the operator and the object to be measured within the time interval; judging whether the object to be measured is operated by the operator according to the change in the relative position. It is used to process image data using the YOLOv8 target detection network in special scenarios where the object to be measured is blocked, and determine whether the object to be measured is operated based on the change in the relative position between the wrist node and the object to be measured, thereby improving the accuracy and real-time performance of monitoring, reducing the need for manual intervention, and thus reducing the risk of human error.

[0093] For example 3, please refer to Figure 5 , Figure 5 This is a structural block diagram of an embodiment of a monitoring device for when a detected object is blocked according to the present invention, and the device includes:

[0094] The acquisition module 301 is used to capture the image data of the object under test in the monitoring scene in real time;

[0095] A relative distance determination module 302, for determining the relative distance between the operator and the object to be measured when it is detected in the image data that an operator enters into a preset range of the object to be measured;

[0096] A saving module 303, used to save the image data at a preset time interval;

[0097] An extraction module 304 is used to extract the human skeleton nodes of the operator from the stored target image data;

[0098] A position change determination module 305 is used to calculate the change of the relative position relationship between the operator and the object under test within the time interval based on the human skeleton nodes;

[0099] The judgment module 306 is used to judge whether the object to be measured is operated by the operator according to the relative position change.

[0100] In an optional embodiment, the relative distance determination module 302 includes:

[0101] An input submodule is used to input the image data into a trained YOLOv8 target detection network to obtain a target detection result;

[0102] A plane position information determination submodule, used for determining the plane position information of the operator and the object to be measured when the target monitoring result includes the operator and the operator enters the preset range of the object to be measured;

[0103] The spatial relative distance determination submodule is used to determine the spatial relative distance between the operator and the measured object based on the plane position information.

[0104] In an optional embodiment, the spatial relative distance determination submodule includes:

[0105] A model building unit, used to build a perspective transformation model according to the perspective information of the monitoring scene;

[0106] An information conversion unit, used to convert the plane position information of the operator and the object to be measured into the space position information of the operator and the object to be measured respectively by using the perspective transformation model;

[0107] The spatial relative distance determination unit is used to calculate the spatial relative distance between the operator and the measured object by using a preset transformation formula in combination with the spatial position information.

[0108] In an optional embodiment, the position change determination module 305 includes:

[0109] An extraction submodule, used for extracting wrist nodes from the human skeleton nodes;

[0110] The position change determination submodule is used to calculate the change of the relative position relationship between the wrist node and the object under test within the time interval.

[0111] In an optional embodiment, the determination module 306 includes:

[0112] A first judgment submodule is used to determine that the object to be measured is operated by the operator when the relative spatial distance between the wrist node and the object to be measured is reduced compared to before the time interval;

[0113] The second judgment submodule is used to determine that the object to be measured has not come into contact with the operator when the relative spatial distance between the wrist node and the object to be measured remains unchanged or increases compared with before the time interval.

[0114] Embodiment 4, the embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of a monitoring method when a measured object is obstructed in any embodiment.

[0115] Embodiment 5, the embodiment of the present invention further provides a computer storage medium, on which a computer program is stored, and when the computer program is executed by the processor, the steps of a monitoring method when a detected object is obstructed are implemented in any embodiment.

[0116] Embodiment 6. Embodiments of the present invention further provide a computer program product on which a computer program is stored. When the computer program is executed by the processor, the steps of a monitoring method when an object to be measured is obstructed are implemented in any embodiment.

[0117] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0118] In the several embodiments provided in the present application, it should be understood that the methods, devices, electronic devices and storage media disclosed in the present invention can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as 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 devices or units, which can be electrical, mechanical or other forms.

[0119] 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 network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0120] 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.

[0121] 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 is essentially 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 readable storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned readable storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0122] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A monitoring method when the object being measured is blocked, characterized in that: include: Capture image data of the object being measured in the monitoring scene in real time; When it is detected in the image data that a worker enters a preset range of the object to be measured, determining a relative spatial distance between the worker and the object to be measured; Saving the image data at preset time intervals; Extracting the human skeleton nodes of the operator from the stored target image data; Based on the human skeleton nodes, calculating the change in the relative position relationship between the operator and the object under test within the time interval; According to the relative position change, it is determined whether the object to be measured is operated by the operator.

2. The monitoring method when the object to be measured is blocked according to claim 1, characterized in that: When it is detected in the image data that a worker enters a preset range of the object to be measured, determining the relative spatial distance between the worker and the object to be measured includes: Input the image data into the trained YOLOv8 target detection network to obtain the target detection result; When the target monitoring result includes the operator and the operator enters the preset range of the object to be measured, determining the plane position information of the operator and the object to be measured; Based on the planar position information, the spatial relative distance between the operator and the object to be measured is determined.

3. The monitoring method when the object to be measured is blocked according to claim 2, characterized in that: Determining the spatial relative distance between the operator and the object to be measured based on the planar position information includes: Establishing a perspective transformation model according to the perspective information of the monitoring scene; Using the perspective transformation model, converting the plane position information of the operator and the object to be measured into the spatial position information of the operator and the object to be measured respectively; The spatial relative distance between the operator and the measured object is calculated by using a preset transformation formula in combination with the spatial position information.

4. The monitoring method when the object to be measured is blocked according to claim 2, characterized in that: Based on the human skeleton nodes, calculating the change of the relative position relationship between the operator and the object to be measured within the time interval, including: Extracting wrist nodes from the human skeleton nodes; Calculate the change of the relative position relationship between the wrist node and the object under test within the time interval.

5. The monitoring method when the object to be measured is blocked according to claim 4, characterized in that: Judging whether the object to be measured is operated by the operator according to the relative position change includes: If the relative spatial distance between the wrist node and the object to be measured is reduced compared to before the time interval, it is determined that the object to be measured is operated by the operator; If the spatial relative distance between the wrist node and the object to be measured remains unchanged or increases compared to before the time interval, it is determined that the object to be measured has not come into contact with the operator.

6. A monitoring device for when the object being measured is blocked, characterized in that: include: An acquisition module is used to capture image data of the object under test in the monitoring scene in real time; A relative distance determination module, for determining the relative distance between the operator and the object to be measured when it is detected in the image data that an operator has entered a preset range of the object to be measured; A saving module, used for saving the image data at a preset time interval; An extraction module, used for extracting the human skeleton nodes of the operator from the stored target image data; A position change determination module, used to calculate the change of the relative position relationship between the operator and the object to be measured within the time interval based on the human skeleton nodes; The judgment module is used to judge whether the object to be measured is operated by the operator according to the change of the relative position.

7. The monitoring device for when the object to be measured is blocked according to claim 6, characterized in that: The relative distance determination module comprises: An input submodule is used to input the image data into a trained YOLOv8 target detection network to obtain a target detection result; A plane position information determination submodule, used for determining the plane position information of the operator and the object to be measured when the target monitoring result includes the operator and the operator enters the preset range of the object to be measured; The spatial relative distance determination submodule is used to determine the spatial relative distance between the operator and the object to be measured based on the planar position information.

8. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 5 is executed.

9. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is performed.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images