A method, system, storage medium and electronic device for identifying on-duty behavior

Abstract

The present invention provides a method, system, storage medium and electronic device for identifying on-duty behavior. The method inputs the identity information of on-duty personnel and the corresponding facial images in advance to facilitate subsequent face recognition operations; marks the target areas that need to be supervised respectively, so that when the on-duty personnel are photographed into the target areas, the behavior of the on-duty personnel is targeted for identification; obtains the identity information and the corresponding facial images of the on-duty personnel when signing in, generates a duty plan at the same time, and determines whether the on-duty personnel who sign in executes the duty plan; if it is determined that the on-duty personnel who sign in executes the duty plan, the behavior of the on-duty personnel in the preset target area is analyzed to determine whether there is any violation; if it is determined that there is any violation, an early warning is issued, and specifically, the supervision burden of personnel is reduced, and the behavior of the on-duty personnel is effectively and automatically supervised.

Description

Technical Field

[0001] The present invention belongs to the technical field of on-duty behavior recognition, and in particular relates to an on-duty behavior recognition method, system, storage medium and electronic equipment. Background Art

[0002] Currently, in the scenario where two people take turns on duty, the on-duty personnel need to patrol within the prescribed range to ensure the safety of the duty area.

[0003] However, on-duty personnel often violate regulations during their duty, which poses a great safety hazard to areas with certain safety requirements. Currently, such situations are mainly supervised manually, and automatic identification and warning cannot be achieved. Summary of the invention

[0004] Based on this, an embodiment of the present invention provides a method, system, storage medium and electronic device for identifying on-duty behavior, aiming to automatically identify whether on-duty personnel have violated regulations and issue warnings.

[0005] A first aspect of an embodiment of the present invention provides a method for identifying on-duty behavior, which is applied to a scene with a shooting device, wherein an image of an on-duty person in a specific area is captured by the shooting device, and the specific area includes a fixed area and a moving area. The method includes:

[0006] Enter the identity information of the duty personnel and the corresponding facial image, so that when the duty personnel signs in, the corresponding facial image is obtained according to the identity information of the duty personnel;

[0007] Respectively acquiring a first image including the fixed area and a second image including the moving area captured by the capturing device, and marking a first target area of ​​the first image and a second target area of ​​the second image, so as to perform targeted identification of the behavior of the on-duty personnel when the on-duty personnel is captured entering the first target area or the second target area;

[0008] Obtaining identity information and a corresponding facial image of the on-duty personnel when signing in, and generating a duty plan, the duty plan including a first preset time for the signed-in on-duty personnel to appear in a first target area, a second preset time for the signed-in on-duty personnel to appear in a second target area, and a patrol range of the signed-in on-duty personnel in the second target area;

[0009] Determine whether the on-duty personnel who sign in follow the duty plan;

[0010] If it is determined that the signed-in on-duty personnel are performing according to the duty plan, the behavior of the on-duty personnel in the first target area is analyzed to determine whether there is any violation;

[0011] If it is determined that there is a violation, a warning will be issued;

[0012] The step of analyzing the behavior of the on-duty personnel in the first target area to determine whether there is any violation includes:

[0013] Acquire a standard facial contour of the on-duty personnel in the first target area, and determine pixel values ​​of pixel points representing the face in the facial contour;

[0014] The facial contour is updated in real time according to the pixel value, and whether there is any violation is determined according to the change of the facial contour.

[0015] Furthermore, the step of updating the facial contour in real time according to the pixel value and judging whether there is any violation according to the change of the facial contour includes:

[0016] According to the pixel value, the facial contour is updated in real time, and the area of ​​the updated facial contour is obtained in real time;

[0017] Determine whether the area of ​​the facial contour is larger than a preset area;

[0018] If it is determined that the area of ​​the facial contour is greater than the preset area, then calculating the area change rate of the facial contour at adjacent moments, and determining whether the area change rate is greater than the preset change rate;

[0019] If it is determined that the area change rate is greater than the preset change rate, it is determined that a violation has occurred.

[0020] Furthermore, the step of determining whether the signed-in on-duty personnel perform according to the duty plan includes:

[0021] Acquire a first actual time when the facial image of the signed-in on-duty person is recognized in the first target area and a second actual time when the facial image of the signed-in on-duty person is recognized in the second target area;

[0022] Determining whether the first actual time belongs to the first preset time;

[0023] If it is determined that the first actual time belongs to the first preset time, then determining whether the second actual time belongs to the second preset time;

[0024] If it is determined that the second actual time belongs to the second preset time, when the second actual time is obtained, the relationship between the facial image of the signed-in duty personnel and the second target area is analyzed, and the inspection trajectory of the signed-in duty personnel is drawn;

[0025] Determining whether the inspection trajectory meets the inspection range;

[0026] If it is determined that the inspection trajectory is consistent with the inspection scope, it means that the signed-in duty personnel are performing according to the duty plan.

[0027] Furthermore, when the second actual time is obtained, the step of starting to analyze the relationship between the facial image of the signed-in on-duty personnel and the second target area and drawing the inspection track of the signed-in on-duty personnel includes:

[0028] Recognize the face of the on-duty personnel who sign in in real time, and obtain the pixel coordinate position and number of pixels of the facial image when the facial image of the on-duty personnel who sign in is recognized;

[0029] Determine the corresponding position in the first direction according to the number of pixels of the facial image and a mapping relationship between the preset number of pixels and the position in the first direction;

[0030] Determine the center point of the facial image according to the coordinate positions of the pixels of the facial image, and draw a straight line passing through the center point in a second direction perpendicular to the first direction;

[0031] Determine an intersection point between the straight line and the boundary of the second target area, and determine a corresponding position in the second direction according to a mapping relationship between the intersection point and a preset intersection point and a position in the second direction;

[0032] Generate inspection traces according to the determined position in the first direction and the position in the second direction, and the corresponding time;

[0033] Determining whether the inspection traces are continuous;

[0034] If it is determined that the inspection trace is discontinuous, the inspection trace is drawn complete according to a preset rule to obtain the inspection trajectory.

[0035] Furthermore, the step of drawing the inspection traces in full according to the preset rules to obtain the inspection track includes:

[0036] Obtain the distance between adjacent breakpoints, and determine whether the distance between adjacent breakpoints is less than a preset distance;

[0037] If it is determined that the distance between adjacent breakpoints is less than the preset distance, the adjacent breakpoints are connected by line segments;

[0038] If it is determined that the distance between adjacent breakpoints is not less than the preset distance, obtaining the number of adjacent breakpoints whose distance is not less than the preset distance, and determining whether the number is greater than a threshold;

[0039] If it is determined that the number is greater than the threshold, the drawing of the inspection track is stopped, and an early warning is issued. At the same time, the corresponding image is captured and sent to the server.

[0040] Furthermore, the step of determining whether the inspection trajectory meets the inspection range includes:

[0041] Obtaining two extreme value coordinate points of the inspection trajectory in the first direction, and determining whether the two extreme value coordinate points both fall within a preset moving area;

[0042] If it is determined that both extreme value coordinate points fall within the preset moving area, the inspection trajectory is compared with the preset inspection trajectory to determine whether the inspection trajectory meets the inspection range.

[0043] A second aspect of an embodiment of the present invention provides a duty behavior recognition system, which is used to implement the above-mentioned duty behavior recognition method, and is applied to a scene with a shooting device, wherein the image of the duty personnel in a specific area is captured by the shooting device, and the specific area includes a fixed area and a moving area. The system includes:

[0044] An input module is used to input the identity information of the duty personnel and the corresponding facial image, so that when the duty personnel signs in, the corresponding facial image is obtained according to the identity information of the duty personnel;

[0045] a marking module, used to respectively obtain a first image including the fixed area and a second image including the moving area captured by the shooting device, and to respectively mark a first target area of ​​the first image and a second target area of ​​the second image, so as to perform targeted identification of the behavior of the on-duty personnel when the on-duty personnel is captured entering the first target area or the second target area;

[0046] an acquisition module, for acquiring identity information and a corresponding facial image of a duty officer when signing in, and generating a duty plan, wherein the duty plan includes a first preset time when the signed-in duty officer appears in a first target area, a second preset time when the signed-in duty officer appears in a second target area, and a patrol range of the signed-in duty officer in the second target area;

[0047] The first judgment module is used to judge whether the on-duty personnel who sign in are performing according to the duty plan;

[0048] A second judgment module is used to analyze the behavior of the on-duty personnel in the first target area to determine whether there is any violation if it is determined that the on-duty personnel who signed in are performing according to the duty plan;

[0049] The early warning module is used to issue an early warning if it is determined that there is a violation.

[0050] A third aspect of an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the on-duty behavior identification method provided by the first aspect.

[0051] A fourth aspect of an embodiment of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the on-duty behavior identification method provided in the first aspect is implemented.

[0052] A method, system, storage medium and electronic device for identifying on-duty behavior provided in an embodiment of the present invention, the method inputs the identity information of on-duty personnel and the corresponding facial image in advance to facilitate subsequent face recognition operations; marks the target areas that need to be supervised respectively, so that when the on-duty personnel are photographed into the target area, the behavior of the on-duty personnel is targeted for identification; obtains the identity information and the corresponding facial image of the on-duty personnel when signing in, generates a duty plan at the same time, and determines whether the on-duty personnel who sign in executes the duty plan; if it is determined that the on-duty personnel who sign in executes the duty plan, the behavior of the on-duty personnel in the preset target area is analyzed to determine whether there is any violation; if it is determined that there is any violation, an early warning is issued, specifically, the supervision burden of personnel is reduced, and the behavior of on-duty personnel is effectively and automatically supervised. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 A flowchart of a method for identifying on-duty behavior provided in the first embodiment of the present invention;

[0054] Figure 2 A structural block diagram of a duty behavior recognition system provided in Embodiment 2 of the present invention;

[0055] Figure 3 This is a structural block diagram of an electronic device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0056] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Several embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0057] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0058] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0059] Embodiment 1

[0060] According to an embodiment of the present invention, an embodiment of a method for identifying on-duty behavior is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0061] In the first embodiment of the present invention, a method for identifying on-duty behavior is provided, which can be used in electronic devices, such as computers. It should be noted that the method is applied to a scene with a shooting device, wherein the image of the on-duty personnel in a specific area is captured by the shooting device, and the specific area includes a fixed area and a mobile area. Specifically, the shooting device can be a shooting device equipped with a high-definition camera. The fixed area can be understood as a place where the on-duty personnel are required to stand guard. When on-duty personnel are in the fixed area, they generally need to look forward and pay attention to their appearance. The mobile area can be understood as an area where the on-duty personnel need to walk back and forth and patrol.

[0062] See also Figure 1 , Figure 1 A flowchart of an implementation of a method for identifying on-duty behavior provided in Embodiment 1 of the present invention is shown, which specifically includes steps S01 to S06.

[0063] Step S01, inputting the identity information of the duty personnel and the corresponding facial image, so that when the duty personnel signs in, the corresponding facial image is obtained according to the identity information of the duty personnel.

[0064] Specifically, first enter the identity information of the on-duty personnel and the corresponding facial image. The identity information of the on-duty personnel can be name, work number, rank, etc. The facial image is an image with specific facial features after face recognition. After the image is captured by the camera, the face in the image is recognized to determine the identity of the corresponding on-duty personnel.

[0065] Step S02, respectively obtaining a first image including the fixed area and a second image including the moving area taken by the shooting device, and marking a first target area of ​​the first image and a second target area of ​​the second image, so as to perform targeted identification of the behavior of the on-duty personnel when the on-duty personnel is photographed into the first target area or the second target area.

[0066] In this embodiment, the picture captured by the shooting device is usually wide, but the range to be inspected is limited. If the entire picture is recognized, a certain amount of resources will be wasted. Therefore, after obtaining the first image containing the fixed area and the second image containing the moving area, the first target area and the second target area can be framed by manual marking, that is, only the patrol personnel in the first target area and the second target area are subjected to face recognition.

[0067] It can be understood that the first target area can be an area similar to a sentry box in the actual scene, and the second target area can be a corridor area in the actual scene, wherein rooms are arranged on both sides of the corridor.

[0068] Step S03, obtaining the identity information and corresponding facial image of the on-duty personnel when signing in, and generating a duty plan at the same time, wherein the duty plan includes a first preset time for the signed-in on-duty personnel to appear in the first target area, a second preset time for the signed-in on-duty personnel to appear in the second target area, and a patrol range of the signed-in on-duty personnel in the second target area.

[0069] The duty plan can be understood as the need to regularly patrol different areas, for example, every half an hour of standing guard in a fixed area, it is necessary to patrol the mobile area twice. Then, the first preset time and the second preset time represent time periods.

[0070] Step S04, determine whether the signed-in duty personnel perform according to the duty plan, if so, execute step S05.

[0071] It should be noted that the first actual time when the facial image of the signed-in duty person is recognized in the first target area and the second actual time when the facial image of the signed-in duty person is recognized in the second target area are obtained;

[0072] Determine whether the first actual time belongs to the first preset time, that is, determine whether to return to the fixed area to stand guard within the preset time;

[0073] If it is determined that the first actual time belongs to the first preset time, then it is determined whether the second actual time belongs to the second preset time, that is, it is determined whether the patrol in the moving area starts within the preset time;

[0074] If it is determined that the second actual time belongs to the second preset time, then when the second actual time is obtained, the relationship between the facial image of the signed-in duty personnel and the second target area is analyzed, and the inspection trajectory of the signed-in duty personnel is drawn. Specifically, the face of the signed-in duty personnel is recognized in real time, and when the facial image of the signed-in duty personnel is recognized, the pixel coordinate position and the number of pixels of the facial image are obtained;

[0075] According to the mapping relationship between the number of pixels of the facial image and the preset number of pixels and the position in the first direction, the corresponding position in the first direction is determined. It should be noted that the camera shoots at a fixed angle, and the distance of the on-duty personnel from the camera will directly affect the size of the on-duty personnel's face in the image. It can be understood that the farther the on-duty personnel is from the camera, the fewer the number of pixels of the facial image, and the closer the on-duty personnel is to the camera, the more the number of pixels of the facial image. Therefore, according to the above principle, the mapping relationship between the number of pixels of the facial image and the preset number of pixels and the position in the first direction is established in advance, and data can be collected by manual surveying, wherein the first direction refers to the direction facing the camera, which is actually the length direction of the corridor;

[0076] Determine the center point of the facial image according to the coordinate positions of the pixels of the facial image, wherein the center point is the geometric center of the facial image, and draw a straight line in a second direction perpendicular to the first direction passing through the center point;

[0077] Determine the intersection of the straight line and the boundary of the second target area, and determine the corresponding position in the second direction according to the intersection and the mapping relationship between the preset intersection and the position in the second direction. It should be noted that a mapping relationship between each point on the boundary of the second target area and the position in the second direction is pre-established, wherein each point on the boundary of the second target area can be determined by finding a reference object, or by marking scales on the boundary of the second target area, and different scales correspond to specific positions in the second direction;

[0078] According to the determined position in the first direction and the position in the second direction, and the corresponding time, a patrol trace is generated. In this embodiment, a camera is installed at least at both ends of the corridor in the length direction. It can be understood that the on-duty personnel can only be identified when most of their facial areas are photographed. During the patrol process, since there are rooms on both sides of the corridor, the on-duty personnel need to inspect back and forth during the patrol process. Then, when the head is tilted to the left or right to a certain angle, the face cannot be recognized. Therefore, the patrol trace is usually composed of points and / or line segments.

[0079] Determine whether the inspection traces are continuous;

[0080] If it is determined that the inspection trace is discontinuous, the inspection trace is drawn completely according to the preset rules to obtain the inspection trajectory. Specifically, the distance between adjacent breakpoints is obtained, and it is determined whether the distance between adjacent breakpoints is less than the preset distance;

[0081] If it is determined that the distance between adjacent breakpoints is less than the preset distance, the adjacent breakpoints are connected by line segments;

[0082] If it is determined that the distance between adjacent breakpoints is not less than the preset distance, the number of adjacent breakpoints whose distance is not less than the preset distance is obtained, and whether the number is greater than a threshold is determined;

[0083] If the number of judgments is greater than the threshold, it means that the facial recognition is abnormal, then the drawing of the inspection track is stopped, and an early warning is issued. At the same time, the corresponding image is intercepted and sent to the server for tracing;

[0084] Determine whether the patrol trajectory meets the patrol range. Specifically, obtain two extreme value coordinate points of the patrol trajectory in the first direction, that is, the extreme value coordinate points close to the two ends of the corridor, and determine whether the two extreme value coordinate points fall within the preset moving area.

[0085] If it is determined that both extreme value coordinate points fall within the preset moving area, the inspection trajectory is compared with the preset inspection trajectory, wherein the inspection trajectory and the preset inspection trajectory can be divided into multiple segments, and the similarities between these segments are compared, thereby obtaining a similarity measure of the entire trajectory to determine whether the inspection trajectory meets the inspection range;

[0086] If it is judged that the inspection trajectory is in line with the inspection scope, it means that the signed-in duty personnel are executing according to the duty plan.

[0087] In step S05, the behavior of the on-duty personnel in the first target area is analyzed to determine whether there is any violation. If so, step S06 is executed.

[0088] Specifically, a standard facial contour of the on-duty personnel in the first target area is obtained, and pixel values ​​of pixel points representing the face in the facial contour are determined;

[0089] According to the pixel value, the facial contour is updated in real time, and according to the change of the facial contour, whether there is any violation is determined. Specifically, according to the pixel value, the facial contour is updated in real time, and the area of ​​the updated facial contour is obtained in real time;

[0090] Determine whether the area of ​​the facial contour is larger than the preset area. It is understandable that if the area of ​​the facial contour is not larger than the preset area, it means that the on-duty personnel may be bowing their heads;

[0091] If it is determined that the area of ​​the facial contour is greater than the preset area, then calculating the area change rate of the facial contour at adjacent moments, and determining whether the area change rate is greater than the preset change rate;

[0092] If the area change rate is judged to be greater than the preset change rate, it means that the on-duty personnel may be dozing off, that is, nodding, and it is judged that there is a violation.

[0093] Step S06: issue an early warning.

[0094] In the embodiment of the present invention, a wristband can be worn by the on-duty personnel. When a situation requiring early warning occurs, the wristband is activated to remind the on-duty personnel in the form of vibration.

[0095] In summary, the on-duty behavior identification method in the above-mentioned embodiment of the present invention inputs the identity information of the on-duty personnel and the corresponding facial image in advance to facilitate subsequent face recognition operations; marks the target areas that need to be supervised respectively, so that when the on-duty personnel are photographed into the target area, the behavior of the on-duty personnel can be targetedly identified; the identity information and the corresponding facial image of the on-duty personnel when signing in are obtained, and a duty plan is generated at the same time, and it is determined whether the on-duty personnel who sign in executes the duty plan; if it is determined that the on-duty personnel who sign in executes the duty plan, the behavior of the on-duty personnel in the preset target area is analyzed to determine whether there is any violation; if it is determined that there is a violation, an early warning is issued. Specifically, the supervision burden of personnel is reduced, and the behavior of on-duty personnel is effectively and automatically supervised.

[0096] Embodiment 2

[0097] See also Figure 2 , Figure 2 It is a structural block diagram of a duty behavior identification system provided in Example 2 of the present invention. The duty behavior identification system 200 is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0098] Specifically, the on-duty behavior recognition system 200 is applied to a scene with a shooting device, wherein the image of the on-duty personnel in a specific area is captured by the shooting device, and the specific area includes a fixed area and a moving area, including: an input module 21, a marking module 22, an acquisition module 23, a first judgment module 24, a second judgment module 25 and an early warning module 26, wherein:

[0099] An input module 21 is used to input the identity information of the duty personnel and the corresponding facial image, so that when the duty personnel signs in, the corresponding facial image is obtained according to the identity information of the duty personnel;

[0100] a marking module 22, for respectively acquiring a first image including the fixed area and a second image including the moving area captured by the capturing device, and marking a first target area of ​​the first image and a second target area of ​​the second image, so as to perform targeted identification of the behavior of the on-duty personnel when the on-duty personnel are captured entering the first target area or the second target area;

[0101] An acquisition module 23 is used to acquire the identity information of the on-duty personnel when they sign in and the corresponding facial image, and generate a duty plan, wherein the duty plan includes a first preset time when the on-duty personnel who sign in appear in the first target area, a second preset time when the on-duty personnel who sign in appear in the second target area, and a patrol range of the on-duty personnel who sign in in the second target area;

[0102] The first judgment module 24 is used to judge whether the on-duty personnel who sign in are performing according to the duty plan;

[0103] The second judgment module 25 is used to analyze the behavior of the on-duty personnel in the first target area to determine whether there is any violation if it is determined that the on-duty personnel who signed in are performing according to the duty plan;

[0104] The early warning module 26 is used to issue an early warning if it is determined that there is a violation.

[0105] Further, in some optional embodiments of the present invention, the first determination module 24 includes:

[0106] A first acquisition unit, used for acquiring a first actual time when the facial image of the signed-in duty person is recognized in the first target area and a second actual time when the facial image of the signed-in duty person is recognized in the second target area;

[0107] A first judging unit, configured to judge whether the first actual time belongs to the first preset time;

[0108] a second judging unit, configured to judge whether the second actual time belongs to the second preset time if it is judged that the first actual time belongs to the first preset time;

[0109] a drawing unit, for, if it is determined that the second actual time belongs to the second preset time, starting to analyze the relationship between the facial image of the signed-in duty personnel and the second target area when the second actual time is acquired, and drawing the inspection trajectory of the signed-in duty personnel;

[0110] A third judgment unit, used to judge whether the inspection trajectory meets the inspection range;

[0111] If it is determined that the inspection trajectory is consistent with the inspection scope, it means that the signed-in duty personnel are performing according to the duty plan.

[0112] Furthermore, in some optional embodiments of the present invention, the drawing unit includes:

[0113] The first acquisition subunit is used to recognize the face of the on-duty personnel who signs in in real time, and obtain the pixel coordinate position and the number of pixels of the facial image when the facial image of the on-duty personnel who signs in is recognized;

[0114] A first determining subunit, configured to determine a corresponding position in the first direction according to the number of pixels of the facial image and a mapping relationship between a preset number of pixels and the position in the first direction;

[0115] a second determining subunit, configured to determine a center point of the facial image according to the coordinate positions of the pixels of the facial image, and draw a straight line passing through the center point in a second direction perpendicular to the first direction;

[0116] A third determining subunit is used to determine the intersection of the straight line and the boundary of the second target area, and determine the corresponding position in the second direction according to the intersection and a mapping relationship between a preset intersection and the position in the second direction;

[0117] An inspection trace generation subunit, used to generate an inspection trace according to the determined position in the first direction and the position in the second direction, and the corresponding time;

[0118] A first judging subunit is used to judge whether the inspection traces are continuous;

[0119] A drawing subunit is used for drawing the inspection trace completely according to a preset rule to obtain the inspection track if it is determined that the inspection trace is discontinuous. Specifically, the distance between adjacent breakpoints is obtained, and whether the distance between adjacent breakpoints is less than a preset distance;

[0120] If it is determined that the distance between adjacent breakpoints is less than the preset distance, the adjacent breakpoints are connected by line segments;

[0121] If it is determined that the distance between adjacent breakpoints is not less than the preset distance, obtaining the number of adjacent breakpoints whose distance is not less than the preset distance, and determining whether the number is greater than a threshold;

[0122] If it is determined that the number is greater than the threshold, the drawing of the inspection track is stopped, and an early warning is issued. At the same time, the corresponding image is captured and sent to the server.

[0123] Further, in some optional embodiments of the present invention, the third judgment unit includes:

[0124] A second judgment subunit is used to obtain two extreme value coordinate points of the inspection track in the first direction, and judge whether the two extreme value coordinate points fall within a preset moving area;

[0125] The comparison subunit is used to compare the inspection trajectory with the preset inspection trajectory if it is determined that both extreme value coordinate points fall within the preset moving area, so as to determine whether the inspection trajectory meets the inspection range.

[0126] Further, in some optional embodiments of the present invention, the second determination module 25 includes:

[0127] A second acquisition unit is used to acquire a standard facial contour of the on-duty personnel in the first target area, and determine pixel values ​​of pixel points representing the face in the facial contour;

[0128] The updating unit is used to update the facial contour in real time according to the pixel value, and to determine whether there is any violation according to the change of the facial contour.

[0129] Further, in some optional embodiments of the present invention, the updating unit includes:

[0130] A second acquisition subunit, used to update the facial contour in real time according to the pixel value, and acquire the area of ​​the updated facial contour in real time;

[0131] A third judging subunit, used to judge whether the area of ​​the facial contour is greater than a preset area;

[0132] a fourth judgment subunit, configured to calculate the area change rate of the facial contour at adjacent moments if it is judged that the area of ​​the facial contour is greater than a preset area, and to judge whether the area change rate is greater than a preset change rate;

[0133] The fifth judgment subunit is used to judge that there is a violation if it is judged that the area change rate is greater than a preset change rate.

[0134] Embodiment 3

[0135] Another aspect of the present invention provides an electronic device, see Figure 3 , shown is an electronic device in Embodiment 3 of the present invention, including a memory 20, a processor 10, and a computer program 30 stored in the memory and executable on the processor, wherein the processor 10 implements the above-mentioned on-duty behavior recognition method when executing the computer program 30.

[0136] In some embodiments, the processor 10 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor or other data processing chip, used to run program codes or process data stored in the memory 20, such as executing access restriction programs.

[0137] Among them, the memory 20 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 20 can be an internal storage unit of an electronic device, such as a hard disk of the electronic device. In other embodiments, the memory 20 can also be an external storage device of an electronic device, such as a plug-in hard disk equipped on the electronic device, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. Further, the memory 20 can also include both an internal storage unit of the electronic device and an external storage device. The memory 20 can not only be used to store application software and various types of data of the electronic device, but also can be used to temporarily store data that has been output or is to be output.

[0138] It should be pointed out that Figure 3 The structure shown does not constitute a limitation on the electronic device. In other embodiments, the electronic device may include fewer or more components than those shown in the figure, or combine certain components, or arrange the components differently.

[0139] The embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which implements the above-mentioned on-duty behavior identification method when executed by a processor.

[0140] Those skilled in the art will appreciate that the logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For purposes of this specification, "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0141] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0142] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0143] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0144] The above embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present invention. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention patent shall be subject to the attached claims.

Claims

1. A method for identifying on-duty behavior, characterized in that: Applied in a scene with a shooting device, wherein the image of a person on duty in a specific area is captured by the shooting device, and the specific area includes a fixed area and a moving area. The method includes: Enter the identity information of the duty personnel and the corresponding facial image, so that when the duty personnel signs in, the corresponding facial image is obtained according to the identity information of the duty personnel; Respectively acquiring a first image including the fixed area and a second image including the moving area captured by the capturing device, and marking a first target area of ​​the first image and a second target area of ​​the second image, so as to perform targeted identification of the behavior of the on-duty personnel when the on-duty personnel is captured entering the first target area or the second target area; Obtaining identity information and a corresponding facial image of the on-duty personnel when signing in, and generating a duty plan, the duty plan including a first preset time for the signed-in on-duty personnel to appear in a first target area, a second preset time for the signed-in on-duty personnel to appear in a second target area, and a patrol range of the signed-in on-duty personnel in the second target area; Determine whether the on-duty personnel who sign in follow the duty plan; If it is determined that the signed-in on-duty personnel are performing according to the duty plan, the behavior of the on-duty personnel in the first target area is analyzed to determine whether there is any violation; If it is determined that there is a violation, a warning will be issued; The step of analyzing the behavior of the on-duty personnel in the first target area to determine whether there is any violation includes: Acquire a standard facial contour of the on-duty personnel in the first target area, and determine pixel values ​​of pixel points representing the face in the facial contour; According to the pixel value, the facial contour is updated in real time, and according to the change of the facial contour, whether there is any violation; The step of judging whether the signed-in duty personnel perform according to the duty plan includes: Acquire a first actual time when the facial image of the signed-in on-duty person is recognized in the first target area and a second actual time when the facial image of the signed-in on-duty person is recognized in the second target area; Determining whether the first actual time belongs to the first preset time; If it is determined that the first actual time belongs to the first preset time, then determining whether the second actual time belongs to the second preset time; If it is determined that the second actual time belongs to the second preset time, then when the second actual time is obtained, the relationship between the facial image of the signed-in duty personnel and the second target area is analyzed, and the inspection trajectory of the signed-in duty personnel is drawn. Specifically, the face of the signed-in duty personnel is recognized in real time, and when the facial image of the signed-in duty personnel is recognized, the pixel coordinate position and the number of pixels of the facial image are obtained; Determine the corresponding position in the first direction according to the number of pixels of the facial image and a mapping relationship between the preset number of pixels and the position in the first direction; Determine the center point of the facial image according to the coordinate positions of the pixels of the facial image, and draw a straight line passing through the center point in a second direction perpendicular to the first direction; Determine an intersection point between the straight line and the boundary of the second target area, and determine a corresponding position in the second direction according to a mapping relationship between the intersection point and a preset intersection point and a position in the second direction; Generate inspection traces according to the determined position in the first direction and the position in the second direction, and the corresponding time; Determining whether the inspection traces are continuous; If it is determined that the inspection trace is discontinuous, the inspection trace is drawn to be complete according to a preset rule to obtain the inspection trajectory; Determining whether the inspection trajectory meets the inspection range; If it is determined that the inspection trajectory is consistent with the inspection scope, it means that the signed-in duty personnel are performing according to the duty plan.

2. The on-duty behavior identification method according to claim 1, characterized in that: The step of updating the facial contour in real time according to the pixel value and judging whether there is any violation according to the change of the facial contour comprises: According to the pixel value, the facial contour is updated in real time, and the area of ​​the updated facial contour is obtained in real time; Determine whether the area of ​​the facial contour is larger than a preset area; If it is determined that the area of ​​the facial contour is greater than the preset area, then calculating the area change rate of the facial contour at adjacent moments, and determining whether the area change rate is greater than the preset change rate; If it is determined that the area change rate is greater than the preset change rate, it is determined that a violation has occurred.

3. The on-duty behavior identification method according to claim 2, characterized in that: The step of drawing the inspection traces in full according to the preset rules to obtain the inspection track comprises: Obtain the distance between adjacent breakpoints, and determine whether the distance between adjacent breakpoints is less than a preset distance; If it is determined that the distance between adjacent breakpoints is less than the preset distance, the adjacent breakpoints are connected by line segments; If it is determined that the distance between adjacent breakpoints is not less than the preset distance, obtaining the number of adjacent breakpoints whose distance is not less than the preset distance, and determining whether the number is greater than a threshold; If it is determined that the number is greater than the threshold, the drawing of the inspection track is stopped, and an early warning is issued. At the same time, the corresponding image is captured and sent to the server.

4. The on-duty behavior identification method according to claim 3, characterized in that: The step of determining whether the inspection trajectory meets the inspection range includes: Obtaining two extreme value coordinate points of the inspection trajectory in the first direction, and determining whether the two extreme value coordinate points both fall within a preset moving area; If it is determined that both extreme value coordinate points fall within the preset moving area, the inspection trajectory is compared with the preset inspection trajectory to determine whether the inspection trajectory meets the inspection range.

5. A duty behavior recognition system, characterized in that: The method for recognizing on-duty behavior according to any one of claims 1 to 4 is applied to a scene with a photographing device, wherein the photographing device is used to capture an image of an on-duty person in a specific area, wherein the specific area includes a fixed area and a moving area, and the system includes: An input module is used to input the identity information of the duty personnel and the corresponding facial image, so that when the duty personnel signs in, the corresponding facial image is obtained according to the identity information of the duty personnel; a marking module, used to respectively obtain a first image including the fixed area and a second image including the moving area captured by the shooting device, and to respectively mark a first target area of ​​the first image and a second target area of ​​the second image, so as to perform targeted identification of the behavior of the on-duty personnel when the on-duty personnel is captured entering the first target area or the second target area; an acquisition module, for acquiring identity information and a corresponding facial image of a duty officer when signing in, and generating a duty plan, wherein the duty plan includes a first preset time when the signed-in duty officer appears in a first target area, a second preset time when the signed-in duty officer appears in a second target area, and a patrol range of the signed-in duty officer in the second target area; The first judgment module is used to judge whether the on-duty personnel who sign in are performing according to the duty plan; A second judgment module is used to analyze the behavior of the on-duty personnel in the first target area to determine whether there is any violation if it is determined that the on-duty personnel who signed in are performing according to the duty plan; The early warning module is used to issue an early warning if it is determined that there is a violation.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the on-duty behavior identification method as described in any one of claims 1 to 4 is implemented.

7. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the on-duty behavior identification method as described in any one of claims 1 to 4 is implemented.

Images