A method, device, storage medium and equipment for detecting personnel wearing in violation of regulations

Abstract

The embodiment of the application provides a kind of personnel rule wearing intelligent detection method, comprising: obtaining the image data of scene picture;Increase a regression head in the head structure of yolov5 model, the regression head is used to measure the length of the sleeve of personnel wearing;The image data is detected based on the improved yolov5 model, locates personnel coordinate and judges whether personnel is wearing rule or not.By the above scheme, user can use unmanned aerial vehicle equipment to carry out construction site picture image acquisition, increase a regression head in the head structure of yolov5 model to improve yolov5 model, to detect based on the improved yolov5 model, judge the wearing condition of personnel in construction site, realize the intelligent detection of personnel rule wearing condition, improve the detection efficiency and accuracy of personnel rule wearing, reduce the waste of human resources and the safety risk of personnel of site supervision.

Description

TECHNICAL FIELD

[0001] The embodiment of the application relates to the technical field of intelligent detection of electric power construction sites, and particularly relates to a detection method, device and equipment for personnel wearing in violation of regulations and a storage medium. BACKGROUND

[0002] With the rapid development of electric power system construction, it is increasingly important to ensure the safe operation level of power grids, and for the staff at construction sites, in order to avoid accidents, it is often necessary to make regulations on wearing clothes, and long-sleeved trousers need to be worn when entering the construction site. However, in fact, there may be personnel rolling up sleeves or trousers on site, which requires real-time supervision and management.

[0003] The prior art usually needs manual judgment of whether wearing is standard, and therefore has a high requirement for labor cost, and at present, there is no method for effectively detecting and identifying whether long-sleeved work clothes are worn according to regulations at electric power construction sites, and management personnel cannot know and remind in time and accurately. Therefore, it is necessary to provide an effective detection and judgment method for whether personnel wear long-sleeved work clothes according to regulations during construction at electric power construction sites. SUMMARY

[0004] In view of the above problems, the embodiment of the application provides a detection method, device and equipment for personnel wearing in violation of regulations and a storage medium, so as to realize intelligent detection of whether personnel wear in violation of regulations at electric power construction sites, greatly reduce the waste of human resources and safety risks of on-site supervision, and improve the efficiency and effect of whether personnel wear in violation of regulations by supervisors.

[0005] In the first aspect, the embodiment of the application provides a detection method for personnel wearing in violation of regulations, characterized in that the method comprises the following steps.

[0006] Obtaining image data of a scene picture;

[0007] Adding a regression head in a head structure of a yolov5 model, the regression head being used to measure the length of sleeves worn by personnel;

[0008] Detecting the image data based on the improved yolov5 model, positioning personnel coordinates and judging whether personnel wear in violation of regulations according to the measurement result of the length of sleeves.

[0009] Preferably, a scene is photographed by a drone device to obtain image data of a scene picture.

[0010] Further, after adding a regression head in a head structure of a yolov5 model, the regression head being used to measure the length of sleeves worn by personnel, the method further comprises the following steps.

[0011] A metric value is introduced, the range of the metric value is 0-1, the metric value is used to output different values according to different wearing conditions when training data;

[0012] In the training session, the regression head regresses according to the metric value, which is used to train the improved yolov5 model to identify the difference and boundary of long and short sleeves.

[0013] Preferably, the introduction of the metric value, the range of the metric value is 0-1, the metric value is used to output different values according to different wearing conditions when training data, comprising:

[0014] When wearing a short sleeve and exposing the elbow joint, the metric value is 1;

[0015] When wearing a short sleeve but not exposing the elbow joint, the range of the metric value is 0.7-1;

[0016] When wearing a long sleeve and rolling up the sleeve, according to the rolling degree of the sleeve, the range of the metric value is 0.1-0.6;

[0017] When wearing a long sleeve normally, the metric value is 0.

[0018] Further, the improved yolov5 model based on the image data detection, positioning personnel coordinates and according to the metric result of the length of the sleeve to judge whether the personnel wear is illegal, comprising:

[0019] Adopting backbone network to extract image features, through pyramid network to carry out feature fusion and setting anchor in each size of feature map, carrying out boundary box regression, in order to realize the positioning of personnel;

[0020] When the metric value is 0.7-1, the result of personnel wearing illegal is output; According to the critical metric value X (0.1X<0.6) defined by the user, when the metric value is 0.1-X, the result of personnel wearing non-illegal is output, when the metric value is X-0.6, the result of personnel wearing illegal is output; When the metric value is 1, the result of personnel wearing non-illegal is output.

[0021] Preferably, after the improved yolov5 model based on the image data detection, positioning personnel coordinates and according to the metric result of the length of the sleeve to judge whether the personnel wear is illegal, it still comprises:

[0022] The detection and judgment result is sent to the alarm module and pushed to the applet.

[0023] Further, after the image data of the live picture is obtained, it still comprises:

[0024] Optimizing the image data for screening and processing.

[0025] The second aspect of the embodiment of the present application further provides a detection device for personnel wearing in violation of regulations, comprising

[0026] An image data acquisition module is configured to acquire image data of a scene;

[0027] A first processing module is configured to add a regression head in a head structure of a yolov5 model, and the regression head is configured to measure the length of a sleeve of clothing worn by a person;

[0028] A second processing module is configured to detect the image data based on the improved yolov5 model, locate the coordinates of the person, and determine whether the person wears in violation of regulations according to the measurement result of the length of the sleeve.

[0029] The third aspect of the embodiment of the present application further provides a storage medium, which is a computer-readable storage medium, and has a computer program stored thereon, and the computer program is executed to implement the steps of the detection method for personnel wearing in violation of regulations.

[0030] The fourth aspect of the embodiment of the present application further provides a computer device, which comprises a processor, a memory, and a computer program stored on the memory and executable on the processor, and the processor implements the steps of the detection method for personnel wearing in violation of regulations when executing the computer program.

[0031] The embodiment of the present application uses the unmanned aerial vehicle device to collect the image of the scene of the construction site, improves the yolov5 model by adding a regression head in the head structure of the yolov5 model, thereby measuring the length of the sleeve of the clothing worn by the person and identifying and determining the wearing condition. Based on the improved yolov5 model in the embodiment of the present application, the wearing condition of the person in the construction site is detected, the intelligent detection of the wearing condition in violation of regulations of the person is realized, the detection efficiency and accuracy of the wearing condition in violation of regulations of the person are improved, and the waste of human resources and the safety risk of the person of the site supervision are reduced. BRIEF DESCRIPTION OF DRAWINGS

[0032] Figure 1 is a flowchart of the detection method for personnel wearing in violation of regulations provided by an embodiment of the present application;

[0033] Figure 2 is a flowchart of the detection method for personnel wearing in violation of regulations provided by an embodiment of the present application;

[0034] Figure 3 is a structural schematic diagram of the detection device for personnel wearing in violation of regulations provided by an embodiment of the present application;

[0035] Figure 4 Fig. 1 is a structural schematic diagram of a storage medium provided by an embodiment of the present application;

[0036] Figure 5 Fig. 2 is a structural schematic diagram of a computer device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0037] The present application will be further described below in conjunction with the drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application. In addition, it should be noted that, for the convenience of description, only the parts related to the present application are shown in the drawings, but not all the structures.

[0038] Before the example embodiments are discussed in more detail, it should be mentioned that some of the example embodiments are described as processes or methods depicted as flow charts. While the steps of the processes are depicted in a sequential order, many of the steps can be performed in parallel, concurrently or at the same time. In addition, the order of the steps can be re-arranged. The processes can be terminated when their operations are completed, but can also have additional steps not included in the figure. The processes can correspond to methods, functions, procedures, subroutines, subprograms, etc.

[0039] In addition, the terms "first", "second", etc. can be used herein to describe various orientations, actions, steps or elements, etc., but these terms do not limit these orientations, actions, steps or elements. These terms are only used to distinguish one orientation, action, step or element from another orientation, action, step or element. For example, a first processing module can be a second processing module, and similarly, a second processing module can be a first processing module, without departing from the scope of the present application. Both the first processing module and the second processing module are processing modules, but they are not the same processing module. The terms "first", "second", etc. are used herein to distinguish one element from another, but these elements are not to be understood as being ranked or one being superior to the other. Therefore, a feature limited by "first", "second", etc. can explicitly or implicitly include one or more of the features. In the description of the present application, the meaning of "a plurality of" is at least two, for example, two, three, etc., unless otherwise specifically limited.

[0040] Figure 1 Fig. 1 is a structural schematic diagram of a storage medium provided by an embodiment of the present application;

[0041] As Figure 1As shown, the smart detection method for illegal wearing provided by the embodiment of the application comprises:

[0042] S10, acquiring image data of a live picture;

[0043] S20, adding a regression head in the head structure of the yolov5 model, the regression head being used to measure the length of the sleeve of the clothes worn by the personnel;

[0044] S30, detecting the image data based on the improved yolov5 model, positioning the personnel coordinates and judging whether the personnel wear illegally according to the measurement result of the sleeve length.

[0045] In the embodiment of the application, the video data of the live picture can be acquired by a drone device. Preferably, the drone device is a four-rotor professional drone DJIM300RTK or a sprite 4 / 4pro DJI drone, etc. The four-rotor professional drone can carry a visible light load holder camera, and the load adopts a Zenith X5S holder camera, which has the advantages of compact design, flexible expansion, intelligent control system and significant optimization of flight performance, and new functions of flight and data safety, and has good performance in collecting the situation of the construction site. The sprite 4 DJI drone has excellent flexibility and portability. The camera of the Phantom 4 Pro is equipped with a 1-inch 20 million-pixel image sensor, and is matched with a rear-view visual sensor and infrared sensors on both sides of the body, which brings 5-way environmental recognition and 4-way obstacle avoidance capability, higher safety, more intelligent flight, and users can flexibly select the drone device to acquire the image data of the live picture.

[0046] Through the above scheme, the user can use the drone device to collect the image of the construction site, and by adding a regression head in the head structure of the yolov5 model to improve the yolov5 model, the length of the sleeve of the clothes worn by the personnel can be measured and the wearing condition can be identified and judged. In the yolov5 model, first, the personnel can be positioned by using anchor, adaptive anchor calculation, FPN+PAN structure, etc., so as to perform the subsequent identification process. The improved yolov5 model of the present application measures and identifies the length of the sleeve of the clothes worn by the personnel to judge the wearing condition of the personnel at the construction site, realizes the smart detection of the illegal wearing condition of the personnel, improves the detection efficiency and accuracy of the illegal wearing of the personnel, and reduces the waste of human resources and the safety risk of the personnel of the site supervisor.

[0047] Further, with reference to Figure 2 In the embodiment of the application, the step S20 of adding a regression head in the head structure of the yolov5 model, the regression head being used to measure the length of the sleeve of the clothes worn by the personnel comprises:

[0048] S21, introduce a metric value ranging from 0 to 1, which is used to output different values according to different wearing conditions during training data;

[0049] S22, in the training session, the regression head regresses according to the metric value, for training the improved yolov5 model to identify the difference and boundary of long and short sleeves.

[0050] In the embodiment of the application, the length of the sleeve can be identified by the improved head structure of the yolov5 model. First, in the annotation session of the training data, in addition to the label itself, a metric value is introduced, and the regression head will regress according to different metric values, which can improve the ability of the model to identify the difference and boundary of long and short sleeves, thereby improving the accuracy of the judgment. Specifically, in the embodiment of the application, when the wearing condition is to wear a short sleeve and expose the elbow joint, the metric value is 1; when the wearing condition is to wear a short sleeve but not to expose the elbow joint, the metric value ranges from 0.7 to 1; when the wearing condition is to wear a long sleeve and roll up the sleeve, according to the rolling degree of the sleeve, the metric value ranges from 0.1 to 0.6; when the wearing condition is to wear a long sleeve normally, the metric value is 0. Wherein, the length range of the sleeve corresponding to different wearing conditions can be set according to the actual situation, in this application, the length range will represent different wearing conditions according to the identified length, the boundary of the length range is not limited in the embodiment of the application, and the user can adjust it according to the actual demand. In the training session, the regression head fits different metric values with the corresponding wearing conditions, so as to achieve the purpose of real-time detection and output of the detection result of the wearing condition.

[0051] Further, the step S30 of detecting the image data based on the improved yolov5 model, locating the personnel coordinates and judging whether the personnel wears in violation of the rules according to the metric result of the sleeve length, comprises:

[0052] S31, the backbone network is used to extract image features, the pyramid network is used for feature fusion, and the anchor is set in each size of feature map for bounding box regression, so as to realize the positioning of personnel;

[0053] S32, when the metric value is 0.7-1, the result of personnel wearing in violation of the rules is output; according to the critical metric value X (0.1X<0.6) defined by the user, when the metric value is 0.1-X, the result of personnel wearing without violation of the rules is output, when the metric value is X-0.6, the result of personnel wearing in violation of the rules is output; when the metric value is 1, the result of personnel wearing without violation of the rules is output.

[0054] The backbone network adopts Swin-Transformer, the capability of feature extraction can be increased, the target positioning is more accurate, and the detection and identification accuracy is further improved.

[0055] In the embodiment of the present application, the critical metric value X can be set according to specific requirements because different work scenes have different requirements for personnel clothing.

[0056] Further, with reference to Figure 2 In the embodiment of the present application, after the step S30 of detecting the image data based on the improved yolov5 model, positioning personnel coordinates and judging whether personnel wear is in violation, the method further comprises:

[0057] S40, send the detection result to an alarm module, and the alarm module sends an alarm signal to a server according to the detection result.

[0058] The alarm module is arranged on an edge device carried by the unmanned aerial vehicle device, and when a detection result of personnel wearing in violation is obtained, an alarm signal is sent to the server. Further, after receiving the alarm signal, the server synchronizes the detection result to a mobile terminal, such as an APP or a mini program, so as to achieve the purpose of timely alarm.

[0059] Preferably, after the step S10 of acquiring image data of a live picture, the method further comprises:

[0060] S11, the image data is optimized and screened.

[0061] In the embodiment of the present application, the image data is optimized and screened, only one of the same image data is retained as optimized data, the repeated operation caused by repeated data can be reduced, and the processing efficiency is improved.

[0062] Figure 3 The structure diagram of the personnel wearing in violation detection device provided by the embodiment of the present application, with reference to Figure 3 The personnel wearing in violation detection device provided by the embodiment of the present application comprises an image data acquisition module 1, a first processing module 2 and a second processing module 3.

[0063] The image data acquisition module 1 is used for acquiring image data of a live picture;

[0064] The first processing module 2 is used for adding a regression head in the head structure of the yolov5 model, and the regression head is used for measuring the length of the sleeve of personnel clothing.

[0065] The second processing module 3 is used for detecting the image data based on the improved yolov5 model, positioning personnel coordinates, and judging whether the personnel wear in violation of regulations according to the measurement result of the sleeve length.

[0066] In the embodiment of the application, the video data of the scene picture can be obtained by a UAV device. The UAV device is preferably a four-rotor professional UAV DJIM300RTK or a Lingling 4 / 4pro DJI UAV, etc. The four-rotor professional UAV can carry a visible light load holder camera, and the load adopts a Chan Si X5S holder camera, which has the advantages of compact design, flexible expansion, intelligent control system, and significant optimization of flight performance, and new functions of flight and data safety, and has good performance in collecting the situation of the construction site. The Lingling 4 DJI UAV has excellent flexibility and portability. The camera of the Phantom 4 Pro is equipped with a 1-inch 20 million-pixel image sensor, and is matched with a rear-view visual sensor and infrared sensors on both sides of the body, which brings 5-way environmental recognition and 4-way obstacle avoidance capability, higher safety, more intelligent flight, and users can flexibly select the UAV device to obtain the image data of the scene picture.

[0067] In the embodiment of the application, the user can use the UAV device to collect the image of the construction site picture, and a regression head is added in the head structure of the yolov5 model to improve the yolov5 model, so that the length of the sleeve worn by the personnel can be measured and the wearing condition can be identified and judged. In the yolov5 model, the personnel can be positioned by using anchor, adaptive anchor calculation, FPN+PAN structure, etc., so that the subsequent identification process can be carried out. The improved yolov5 model of the application measures and identifies the length of the sleeve worn by the personnel to judge the wearing condition of the personnel in the construction site, realizes intelligent detection of the personnel wearing in violation of regulations, improves the detection efficiency and accuracy of the personnel wearing in violation of regulations, and reduces the waste of human resources and the safety risk of personnel of the site supervisor.

[0068] Further, the first processing module 2 further includes a first processing unit and a second processing unit.

[0069] The first processing unit is used to introduce a measurement value, the range of the measurement value is 0-1, and the measurement value is used to output different values according to different wearing conditions when training data.

[0070] The second processing unit is used for regression of the regression head according to the measurement value in the training link, and is used for training the improved yolov5 model to identify the difference and boundary between long-sleeve and short-sleeve.

[0071] In the embodiment of the present application, the length of the sleeve can be recognized by improving the head structure of the improved yolov5 model. First, in the labeling link of the training data, a measurement value is introduced in addition to the label of each target. The regression head will regress according to different measurement values, which can improve the ability of the model to recognize the difference and boundary between long and short sleeves, thereby improving the accuracy of judgment. Specifically, in the embodiment of the present application, when the wearing condition is wearing a short sleeve and exposing the elbow joint, the measurement value is 1; when the wearing condition is wearing a short sleeve but not exposing the elbow joint, the measurement value ranges from 0.7 to 1; when the wearing condition is wearing a long sleeve and rolling up the sleeve, according to the rolling degree of the sleeve, the measurement value ranges from 0.1 to 0.6; when the wearing condition is wearing a long sleeve normally, the measurement value is 0. Wherein, the length range of the sleeve corresponding to different wearing conditions can be set according to the actual situation. In this application, the length will be preliminarily judged according to the recognized length, and different length ranges will represent different wearing conditions. The boundaries of the length range are not limited in the embodiment of the present application, and users can adjust them according to actual needs. In the training link, the regression head fits different measurement values with the corresponding wearing conditions, so as to achieve the purpose of real-time detection and output of the detection result. Further, the second processing module 3 further comprises a third processing unit and a fourth processing unit.

[0072] The third processing unit is used to extract image features by using a backbone network, perform feature fusion by using a pyramid network, and set anchors in feature maps of various sizes to regress bounding boxes, so as to realize positioning of the person.

[0073] The fourth processing unit is used to output a result that the person is wearing in violation of the rules when the measurement value is 0.7-1; according to a critical measurement value X (0.1X<0.6) defined by the user, when the measurement value is 0.1-X, output a result that the person is not wearing in violation of the rules, when the measurement value is X-0.6, output a result that the person is wearing in violation of the rules; when the measurement value is 1, output a result that the person is not wearing in violation of the rules.

[0074] Wherein, the backbone network adopts Swin-Transformer, which can increase the feature extraction capability, so as to make the target positioning more accurate, and the more accurate target positioning further improves the accuracy of detection and recognition.

[0075] In the embodiment of the present application, because different work scenes have different requirements for personnel wearing, the critical measurement value X can be set according to specific requirements.

[0076] Further, the embodiment of the present application further comprises a third processing module, which is used to send the detection and judgment result to an alarm module, and the alarm module sends an alarm signal to a server according to the detection result.

[0077] The alarm module is arranged on an edge device carried by the unmanned aerial vehicle device, and when a detection result of illegal wearing of personnel is obtained, an alarm signal is sent to a server.

[0078] Further, the embodiment of the present application further comprises a fourth processing module, which is used for optimizing and screening the image data.

[0079] In the embodiment of the present application, the image data is optimized and screened, and only one of the same image data is kept as optimized data, so that repeated operations caused by repeated data can be reduced, and the processing efficiency is improved.

[0080] Reference Figure 4 The embodiment of the present application further provides a storage medium 100, and the medium 100 stores a computer program 200, which, when running on a computer, enables the computer to execute the detection method of illegal wearing of personnel described in the above embodiment.

[0081] Reference Figure 5 The embodiment of the present application further provides a device 300 containing instructions, which is a computer device, and when running on the device 300, enables the device 300 to execute the detection method of illegal wearing of personnel described in the above embodiment through the processor 400 arranged inside the device 300.

[0082] As will be appreciated by those skilled in the art, the personnel violation dress detection method, apparatus and the above-mentioned devices for performing one or more of the methods described herein can be implemented by those skilled in the art. These devices can be specially designed and manufactured for the desired purpose, or can also include known devices in a general-purpose computer. These devices have computer programs or application programs stored therein, which are selectively activated or reconfigured. Such computer programs can be stored in a device (e.g., a computer) readable medium or in any type of medium suitable for storing electronic instructions and respectively coupled to the bus, including but not limited to any type of disk (including floppy disks, hard disks, optical disks, CD-ROMs, and magneto-optical disks), ROM (Read-Only Memory), RAM (Random Access Memory), EPROM (Erasable Programmable Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), flash memory, magnetic cards or optical cards. That is, the readable medium includes any medium that stores or transmits information in a form that can be read by a device (e.g., a computer).

[0083] It should be noted that the above are only preferred embodiments of the present application and the technical principles applied. Those skilled in the art will understand that the present application is not limited to the specific embodiments described herein, and those skilled in the art can make various obvious changes, re-adjustments and substitutions without departing from the scope of the present application. Therefore, although the present application has been described in more detail through the above embodiments, the present application is not limited to the above embodiments, and can include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the appended claims.

Claims

1. A method for intelligent detection of personnel violating dress code, characterized in that, The method comprises the following steps: obtaining image data of a live scene; adding a regression head in the head structure of the yolov5 model, which is used to measure the length of the sleeve of the clothes worn by the personnel; after adding the regression head in the head structure of the yolov5 model, which is used to measure the length of the sleeve of the clothes worn by the personnel, the method further comprises introducing a measurement value, the range of the measurement value is 0-1, and the measurement value is used to output different values according to different wearing conditions when training data; in the training link, the regression head is regressed according to the measurement value, so as to train the improved yolov5 model to identify the difference and boundary between long sleeves and short sleeves; the introduction of the measurement value, the range of the measurement value is 0-1, and the measurement value is used to output different values according to different wearing conditions when training data, which comprises: when a short sleeve is worn and the elbow joint is exposed, the measurement value is 1; when a short sleeve is worn but the elbow joint is not exposed, the range of the measurement value is 0.7-1; when a long sleeve is worn and the sleeve is rolled up, according to the rolling degree of the sleeve, the range of the measurement value is 0.1-0.6; when a long sleeve is worn normally, the measurement value is 0; detecting the image data based on the improved yolov5 model, positioning the coordinates of the personnel and judging whether the personnel wear clothes in violation of the rules according to the measurement result of the sleeve length; the detection of the image data based on the improved yolov5 model, the positioning of the coordinates of the personnel and the judgment of whether the personnel wear clothes in violation of the rules according to the measurement result of the sleeve length, which comprises: adopting a backbone network to extract image features, performing feature fusion through a pyramid network and setting an anchor in each size of feature map to realize the regression of the boundary box, so as to realize the positioning of the personnel; when the measurement value is 0.7-1, the result of the personnel wearing clothes in violation of the rules is output; according to the critical measurement value X (0.1X<0.6) defined by the user, when the measurement value is 0.1-X, the result of the personnel not wearing clothes in violation of the rules is output, when the measurement value is X-0.6, the result of the personnel wearing clothes in violation of the rules is output; when the measurement value is 1, the result of the personnel not wearing clothes in violation of the rules is output.

2. The method of claim 1, wherein, The live scene is photographed by a drone device to obtain the image data of the live scene.

3. The method of claim 1, wherein, after the detection of the image data based on the improved yolov5 model, the positioning of the coordinates of the personnel and the judgment of whether the personnel wear clothes in violation of the rules according to the measurement result of the sleeve length, the method further comprises: sending the detection and judgment result to an alarm module and pushing it to a mini program.

4. The method of claim 1, wherein, after the image data of the live scene is obtained, the method further comprises: optimizing and screening the image data.

5. A device for detecting a violation of wearing by a person, which implements the steps of the method for intelligently detecting a violation of wearing by a person according to any one of claims 1 to 4, characterized by, The method comprises the following steps: an image data acquisition module, which is used to obtain the image data of a live scene; a first processing module, which is used to add a regression head in the head structure of the yolov5 model, which is used to measure the length of the sleeve of the clothes worn by the personnel; A second processing module is configured to detect the image data based on the improved yolov5 model, locate personnel coordinates, and determine whether the personnel are in violation of the dress code according to the measurement result of the sleeve length.

6. A storage medium having stored thereon a computer program, characterized in that The application discloses a computer readable storage medium, which stores a computer program, and the computer program is executed to realize the steps of the intelligent detection method for personnel in violation of the dress code.

7. An apparatus, comprising: The application discloses a computer readable storage medium, which stores a computer program, and the computer program is executed to realize the steps of the intelligent detection method for personnel in violation of the dress code.

Images