Method and device for processing detection data, storage medium and electronic device

Abstract

The present application discloses a method and device for processing detection data, a storage medium and an electronic device. The method includes: obtaining object detection data obtained by an image acquisition device performing image acquisition on a target area; identifying the object detection data, and determining the historical point data corresponding to the target object, wherein the target object detection data associated with the target object detects an appearance object of a preset type, and identifies the object information belonging to a preset object information set, and the historical point data indicates that the target object has reached the target point within a preset time length; determining the patrol result data of the target object within the preset time length based on the historical point data and the candidate point set; determining the area patrol result data corresponding to the target area based on the patrol result data corresponding to each target object. The present application solves the technical problem of low processing efficiency due to the complex processing flow of detection data.

Description

Technical Field

[0001] The present application relates to the field of computers, and in particular to a method and device for processing detection data, a storage medium, and an electronic device. Background Art

[0002] At present, in the relevant technology, manual punching and signing in are usually used to record detection data and complete patrol tasks. In other words, if the subject forgets to punch in during the patrol, it will cause errors in the detection data. In this case, it is also necessary to specifically record the patrol period in which the punch in is forgotten, and then manually modify the corresponding detection data according to the patrol period, which makes the processing of the detection data time-consuming and the accuracy is difficult to guarantee. In summary, there is a technical problem in the relevant technology that the processing flow of the detection data is complicated, resulting in low processing efficiency.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present application provide a method and device for processing detection data, a storage medium, and an electronic device, so as to at least solve the technical problem of low processing efficiency due to the complex processing flow of detection data.

[0005] According to one aspect of an embodiment of the present application, a method for processing detection data is provided, comprising: acquiring object detection data obtained by an image acquisition device performing image acquisition on a target area, wherein the image acquisition device is deployed in the target area; identifying the object detection data, and determining historical point data corresponding to the target object, wherein the object detection data is related to at least one object, the at least one object includes the target object, the target object detection data associated with the target object detects an appearance object of a preset type and identifies object information belonging to a preset object information set, the image acquisition device includes a target image acquisition device, the target image acquisition device has an association relationship with a target point in the target area, the historical point data indicates that the target object has reached the target point within a preset time length; determining patrol result data of the target object within the preset time length according to the historical point data and a candidate point set, wherein the patrol result data is determined by whether the target point belongs to the candidate point set; and determining area patrol result data corresponding to the target area according to the patrol result data corresponding to each of the target objects.

[0006] According to another aspect of an embodiment of the present application, a detection data processing device is further provided, comprising: an acquisition module, configured to acquire object detection data obtained by an image acquisition device performing image acquisition on a target area, wherein the image acquisition device is deployed in the target area; an identification module, configured to identify the object detection data and determine historical point data corresponding to the target object, wherein the object detection data is associated with at least one object, the at least one object includes the target object, the target object detection data associated with the target object detects an appearance object of a preset type and identifies object information belonging to a preset object information set, the image acquisition device includes a target image acquisition device, the target image acquisition device has an association relationship with a target point in the target area, and the historical point data indicates that the target object has reached the target point within a preset time length; a first determination module, configured to determine patrol result data of the target object within the preset time length according to the historical point data and a candidate point set, wherein the patrol result data is determined by whether the target point belongs to the candidate point set; and a second determination module, configured to determine the area patrol result data corresponding to the target area according to the patrol result data corresponding to each of the target objects.

[0007] Optionally, the device is used to identify the object detection data and determine the historical point data corresponding to the target object in the following manner: identify the object detection data and determine an object whose appearance object type is the preset type among the at least one object as the target object; determine the data associated with the target object in the object detection data as the target object detection data; group the point data in the target object detection data according to each object in the target object to determine the historical point data, wherein the historical point data includes the target point and the time point of arrival at the target point.

[0008] Optionally, the device is used to identify the object detection data and determine the historical point data corresponding to the target object in the following manner: identify the object detection data, and determine the object whose object information belongs to the preset object information set among the at least one object as the target object; determine the data associated with the target object in the object detection data as the target object detection data; group the point data in the target object detection data according to each object in the target object to determine the historical point data, wherein the historical point data includes the target point and the time point of arrival at the target point.

[0009] Optionally, the device is used to determine the patrol result data of the target object within the preset time period according to the historical point data and the candidate point set in the following manner: sort the historical point data according to the acquisition time to obtain a target point list, wherein the center point in the target point list is represented as the center point; perform N rounds of deduplication on each point in the target point list to obtain the target point set, and determine the patrol result data according to whether the ratio between the number of points in the target point set and the number of points in the candidate point set meets a preset ratio condition, Wherein: in the first round represented by i being equal to 1, the i-th group of adjacent points is deduplicated, and the points in the i-th group of adjacent points that do not belong to the target point set are added to the target point set, and the i-th group of adjacent points represents the points adjacent to the center point; and in each subsequent round represented by i being incremented by 1 relative to the previous round, the i-th group of adjacent points adjacent to the i-1-th group of adjacent points obtained in the previous round is deduplicated, and the points in the i-th group of adjacent points that do not belong to the target point set are added to the target point set, until i reaches N, where N is a positive integer greater than 1.

[0010] Optionally, the device is also used to: perform N rounds of deduplication on each point in the target point list to obtain the target point set, then screen each point in the target point set according to the acquisition time to determine a redundant point set whose acquisition time is between the first P and last Q points, where P and Q are both positive integers; delete the redundant point set in the target point set to obtain an updated point set; and determine the patrol result data based on whether the ratio between the number of points in the updated point set and the number of points in the candidate point set meets a preset ratio condition.

[0011] Optionally, the device is also used for: sorting the historical point data according to the acquisition time to obtain the target point list, and then acquiring the first point and the second point in the target point list, wherein the first point is the point with the first acquisition time in the target point list, and the second point is the point with the last acquisition time in the target point list; determining the patrol duration according to the first acquisition time corresponding to the first point and the second acquisition time corresponding to the second point; and determining the patrol result data according to whether the ratio between the number of points in the target point set and the number of points in the candidate point set meets the preset ratio condition when the patrol duration meets the preset duration condition.

[0012] Optionally, the device is used to determine the area patrol result data corresponding to the target area according to the patrol result data corresponding to each of the target objects in the following manner: determine the number of patrols for each of the target points according to the patrol result data; and mark the target points corresponding to different patrol times with different forms of point identifiers in the visualization interface to obtain a target visualization interface corresponding to the target area.

[0013] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned method for processing detection data when running.

[0014] According to another aspect of the embodiment of the present application, a computer program product or a computer program is provided, the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the above detection data processing method.

[0015] According to another aspect of the embodiments of the present application, there is further provided an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the above-mentioned method for processing detection data through the computer program.

[0016] In an embodiment of the present application, object detection data obtained by acquiring an image of a target area by an image acquisition device is obtained, wherein the image acquisition device is deployed in the target area; the object detection data is identified to determine historical point data corresponding to the target object, wherein the object detection data is related to at least one object, the at least one object includes the target object, the target object detection data associated with the target object detects an appearance object of a preset type and identifies object information belonging to a preset object information set, the image acquisition device includes a target image acquisition device, the target image acquisition device has an association relationship with the target point in the target area, and the historical point data indicates that the target object has reached the target point within a preset time period; patrol result data of the target object within a preset time period is determined based on the historical point data and the candidate point set, wherein the patrol result data is determined by whether the target point belongs to the candidate point set; the method of determining the area patrol result data corresponding to the target area based on the patrol result data corresponding to each target object, by analyzing the historical point data and the candidate point set, the patrol result data of the target area can be automatically determined without manual intervention, thereby improving processing efficiency and accuracy, and further solving the technical problem of low processing efficiency due to the complex processing flow of the detection data. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 is a schematic diagram of an application environment of an optional detection data processing method according to an embodiment of the present application;

[0019] Figure 2 is a flowchart of an optional method for processing detection data according to an embodiment of the present application;

[0020] Figure 3 is a schematic diagram of an optional method for processing detection data according to an embodiment of the present application;

[0021] Figure 4 is a schematic diagram of another optional method for processing detection data according to an embodiment of the present application;

[0022] Figure 5 is a schematic diagram of another optional method for processing detection data according to an embodiment of the present application;

[0023] Figure 6 is a schematic diagram of another optional method for processing detection data according to an embodiment of the present application;

[0024] Figure 7 is a schematic diagram of another optional method for processing detection data according to an embodiment of the present application;

[0025] Figure 8 is a schematic structural diagram of an optional detection data processing device according to an embodiment of the present application;

[0026] Fig. 9 is a schematic diagram of the structure of an optional detection data processing product according to an embodiment of the present application;

[0027] Fig.10 It is a schematic diagram of the structure of an optional electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] The present application is described below in conjunction with embodiments:

[0031] According to one aspect of an embodiment of the present application, a method for processing an image is provided. Optionally, in this embodiment, the method for processing an image can be applied to Figure 1 In the hardware environment composed of the server 101 and the terminal device 103 shown in FIG. Figure 1 As shown, the server 101 is connected to the terminal 103 via a network, and can be used to provide services for the terminal device or an application 107 installed on the terminal device. The application can be a video application, an instant messaging application, a browser application, an educational application, a game application, etc. A database 105 may be set up on the server or independently of the server to provide data storage services for the server 101, for example, a game data storage server. The above-mentioned network may include, but is not limited to, a wired network and a wireless network, wherein the wired network includes, a local area network, a metropolitan area network and a wide area network; the wireless network includes, Bluetooth, WIFI and other networks that implement wireless communication; the terminal device 103 may be a terminal configured with an application, and may include, but is not limited to, at least one of the following: a mobile phone (such as an Android phone, an iOS phone, etc.), a laptop computer, a tablet computer, a PDA, a MID (Mobile Internet Devices), a PAD, a desktop computer, a smart TV, an intelligent voice interaction device, a smart home appliance, a vehicle-mounted terminal, an aircraft, a virtual reality (VR) terminal, an augmented reality (AR) terminal, a mixed reality (MR) terminal and other computer devices; the above-mentioned server may be a single server, a server cluster consisting of multiple servers, or a cloud server.

[0032] Combination Figure 1As shown, the above-mentioned image processing method can be executed by an electronic device, which can be a terminal device or a server. The above-mentioned image processing method can be implemented by the terminal device or the server respectively, or by the terminal device and the server together.

[0033] The above is only an example and is not specifically limited in this embodiment.

[0034] Optionally, as an optional implementation, as Figure 2 As shown, the image processing method includes:

[0035] S202, acquiring object detection data obtained by an image acquisition device performing image acquisition on a target area, wherein the image acquisition device is deployed in the target area;

[0036] Optionally, in an embodiment of the present application, the above-mentioned image acquisition device may include but is not limited to cameras, camcorders and other devices, the above-mentioned target area may include but is not limited to indoor areas, outdoor areas, etc., for example, residential areas, shops, parking lots, parks, etc., the above-mentioned object detection data may include but is not limited to the location, quantity, movement trajectory and other information of people, vehicles, animals and other objects in the target area, and the object detection data may include images, videos, hotspot data and other forms.

[0037] It should be noted that, taking the above-mentioned target area as a residential area as an example, the above-mentioned image acquisition device can be an existing community surveillance camera, that is, there is no need to additionally build the above-mentioned image acquisition device to obtain the above-mentioned object detection data, thereby further saving resource costs.

[0038] S204, identifying the object detection data, and determining historical point data corresponding to the target object, wherein the object detection data is associated with at least one object, the at least one object includes the target object, the target object detection data associated with the target object detects an appearance object of a preset type, and identifies object information belonging to a preset object information set, the image acquisition device includes a target image acquisition device, the target image acquisition device has an associated relationship with a target point in the target area, and the historical point data indicates that the target object has reached the target point within a preset time period;

[0039] Optionally, in an embodiment of the present application, the target object may include but is not limited to persons, animals, plants, buildings, etc. existing in the target area corresponding to the object detection data. Taking persons as an example, the target object may move within the target area, and the historical point data may include but is not limited to the movement of the target object at each point in the target area.

[0040] Exemplarily, the above-mentioned object detection data may include but is not limited to object information of several objects in the target area. For example, the object detection data is a captured image in the target area, image A includes 2 persons and 2 animals; image B does not include persons but only includes 2 buildings. In addition, multiple image acquisition devices may be deployed in the target area, and different image acquisition devices may acquire object detection data of the same partial area in the target area, and may also acquire object detection data of different partial areas in the target area. In other words, assuming that object A appears in a sub-area A in the target area, the object detection data acquired by image acquisition device A deployed in sub-area A includes the object information of object A, and the object detection data acquired by image acquisition device B deployed in sub-area B adjacent to sub-area A in the target area may also include the object information of object A. Taking object A as a person as an example, the object information of object A may include but is not limited to person feature information, face information such as clothing, body attribute information, etc.

[0041] Exemplarily, an image is captured by an image acquisition device, and the image includes person A and person B standing at the door of a store. Both person A and person B can be used as the above-mentioned target objects. At this time, the image will be determined as the above-mentioned target object detection data.

[0042] Furthermore, it may include but is not limited to identifying the object detection data, determining the target object detection data from the object detection data, and then obtaining the historical point data based on the target object detection data.

[0043] Specifically, each object in the above-mentioned object detection data can be identified, but not limited to, by image recognition technology, a neural network model (for example, a convolutional neural network (CNN) or a recurrent neural network (RNN)), and the like, and then, it can be determined whether each object has the above-mentioned preset type of appearance object. The preset type of appearance object here can include, but is not limited to, the appearance equipment possessed by the object.

[0044] In an exemplary embodiment, if the preset type is a security uniform type, or a clothing type directly specified by the user, for example, the user directly registers a clothing picture as the preset type, and the appearance object is clothing, then it can be determined whether the clothing of each identified object is a security uniform. If so, the object can be determined as the above-mentioned target object, including the object detection data of the target object will be determined as the above-mentioned target object detection data. Otherwise, it means that the clothing of the object is not a security uniform and cannot be determined as the above-mentioned target object.

[0045] In another exemplary embodiment, if the preset type is a wheelchair type and the appearance object is a means of transportation, it can be determined whether the means of transportation of each identified object is a wheelchair. If so, the object can be determined as the above-mentioned target object, including the object detection data of the target object will be determined as the above-mentioned target object detection data; otherwise, it means that the object's means of transportation is not a wheelchair and cannot be determined as the above-mentioned target object.

[0046] In another exemplary embodiment, if the preset type is a backpack type and the appearance object is a personal belongings, it can be determined whether the personal belongings of each identified object include a backpack. If so, the object can be determined as the above-mentioned target object, and the object detection data including the target object will be determined as the above-mentioned target object detection data. Otherwise, it means that the object's personal belongings do not include a backpack and cannot be determined as the above-mentioned target object.

[0047] Furthermore, it is also possible to determine whether each object can be determined as the above-mentioned target object according to the above-mentioned preset object information set. Specifically, the above-mentioned preset object information set may include but is not limited to object information corresponding to several objects. The object information here may include but is not limited to facial feature information, body feature information, sound feature information, action feature information, etc. By analyzing the object information, it can be determined whether the object meets the characteristics of the above-mentioned target object.

[0048] Exemplarily, face recognition technology can be used to determine whether the facial features of the object corresponding to the object detection data and the facial features of the objects in the preset object information set are consistent; voiceprint recognition technology can be used to determine whether the sound features of the object corresponding to the object detection data and the sound features of the objects in the preset object information set are consistent; behavior recognition technology can be used to determine whether the behavior features of the object corresponding to the object detection data and the behavior features of the objects in the preset object information set are consistent, etc. If they are consistent, it means that the object detection data includes object information belonging to the above-mentioned preset object information set, and the object can be determined as the above-mentioned target object, and the object detection data including the target object will be determined as the above-mentioned target object detection data.

[0049] In an exemplary embodiment, when the facial features of the object corresponding to the object detection data match the facial features of the object in the preset object information set, the object is the above-mentioned target object; or, when the facial features of the object corresponding to the object detection data match the facial features of the object in the preset object information set, and the voice features of the object corresponding to the object detection data match the voice features of the object in the preset object information set, the object is the above-mentioned target object.

[0050] In another exemplary embodiment, it is first determined whether the object in the object detection data has the appearance object of the above-mentioned preset type. If so, it is further determined whether the object detection data corresponding to the object includes object information belonging to the above-mentioned preset object information set. If so, the object is determined as the above-mentioned target object, and the corresponding object detection data is determined as the above-mentioned target detection data. Taking the target area as a residential area as an example, the image acquisition device is a residential area camera, the clothing is the above-mentioned appearance object, and the preset type is a security uniform type.

[0051] For example, Figure 3 is a schematic diagram of an optional method for processing detection data according to an embodiment of the present application, such as Figure 3 As shown, object detection data is first collected by an image acquisition device 302, and the object detection data is identified on a cloud platform 304 to obtain a target object and target object detection data corresponding to the target object, and then, the target object detection data is aggregated and analyzed to obtain historical point data 306.

[0052] Specifically, Figure 4 is a schematic diagram of another optional method for processing detection data according to an embodiment of the present application, such as Figure 4 As shown:

[0053] S402, turn on the cell camera;

[0054] S404, collecting the above object detection data, including face and body feature information in the target area, and obtaining collection time and location information;

[0055] S406, determining whether the clothing of the person in the object detection data is a security uniform, or a clothing type directly specified by the user, for example, the user directly registers a clothing picture as a preset type, if so, executing S408, otherwise, executing S416;

[0056] S408, judging whether the person is a person who has pre-registered security personnel information (the above-mentioned preset object information set) based on the face and body feature information, if so, executing S410, otherwise executing S412;

[0057] S410, determining the person as the target object, determining the corresponding object detection data as the target detection data, performing cluster analysis on the target object detection data, and obtaining historical point data;

[0058] S412, determining whether to ignore the person, that is, whether to directly determine the person as a security personnel, if so, executing S416, otherwise, executing S414;

[0059] S414, submitting the object detection data corresponding to the person to the management personnel for processing, including but not limited to directly determining the person as a target object, or determining the person as a non-target object.

[0060] S416, end.

[0061] Furthermore, when the above-mentioned target object detection data and target object are obtained, the target object detection data can be clustered and analyzed. That is, if multiple target objects are determined, the target object detection data needs to be grouped according to each target object, and then the above-mentioned historical point data corresponding to each object can be obtained.

[0062] Optionally, in an embodiment of the present application, the above-mentioned historical point data may include but is not limited to the location information of the target object: including the location coordinates of the target object at different time points, which is used to analyze the movement trajectory and activity range of the target object; the quantity information of the target object: including the quantity statistics of the target object at different time points; the attribute information of the target object: including the characteristic description, behavioral characteristics and other information of the target object; the association information of the target object: including the association relationship between the target objects, etc.

[0063] In an exemplary embodiment, the target objects are car A and car B, and the target object detection data are image C and image D. The target object detection data are clustered and analyzed according to car A to obtain target object detection data corresponding to car A including image C. Furthermore, according to the information of car A contained in image C, the position information of car A in the target area at different time points is obtained, that is, the historical point data corresponding to car A is obtained, for example: {point one: 00:00; point two: 00:15}. Similarly, according to car B, the target object detection data are clustered and analyzed to obtain target object detection data B corresponding to car B including image C and image D. Furthermore, according to the information of car A contained in image C and image D, the position information of car B in the target area at different time points is obtained, that is, the historical point data corresponding to car B is obtained, for example: {point three: 13:00; point two: 13:30}.

[0064] It should also be noted that the above-mentioned target point can be any point in the above-mentioned historical point data. For example, the above-mentioned target image acquisition device is deployed in area A in the target area, and area A includes the target point.

[0065] Furthermore, the target point data corresponding to different target objects may be the same or different, and the present application does not impose any limitation on this. That is, within the above-mentioned preset time period, different target objects may arrive at the above-mentioned target points at different time points or the same time points, and the time they stay at the target points may be the same or different.

[0066] S206, determining patrol result data of the target object within a preset time period according to the historical point data and the candidate point set, wherein the patrol result data is determined by whether the target point belongs to the candidate point set;

[0067] Optionally, in an embodiment of the present application, the above-mentioned candidate point set can be determined in advance. The present application does not limit the candidate point set. The above-mentioned patrol result data may include but is not limited to patrol time point, whether to patrol, patrol start time, patrol end time, patrol duration, number of patrol points, patrol speed (patrol duration / number of patrol points), patrol conclusion, etc., among which the patrol conclusion may include but is not limited to normal, patrol time is too long, patrol time is insufficient, etc.

[0068] Exemplarily, the above historical point data may be screened, cleaned, and deduplicated according to the above candidate point set to obtain valid historical point data, and then the above patrol result data may be generated using this part of valid historical point data.

[0069] In an exemplary embodiment, assuming the normal patrol duration is n and the required patrol time is A, the above-mentioned preset duration can be determined as (A-1h)~(A+n+1h). That is, in order to ensure the accuracy of data processing, 1 hour of reserved judgment time can be added before and after the standard patrol time period (A~(A+n)), and then the historical point data within the preset duration is determined to determine whether the target point in the historical point data is a point in the candidate point set. If so, the above-mentioned patrol result data is generated based on the target point.

[0070] In another exemplary embodiment, the points in the above historical point data are sorted in chronological order to obtain a group of points arranged in order, and then the central point is selected. The central point can be understood as: assuming that there are point A, point B, and point C, then point B is the central point, and traverse to both sides at the same time, that is, traverse n points on the left first, and then traverse n points on the right, or traverse n points on the right first, and then traverse n points on the left to complete the cross traversal, for example, traverse 1 point on the left first, traverse 1 point on the right, then traverse 1 point on the left, traverse 1 point on the right, and repeat n times; or, traverse n points on the right first, and then traverse n points on the left. Traverse one on the right, traverse one on the left, traverse one on the right again, traverse one on the left, and repeat n times to realize the point traversal in the above historical point data, where n is a positive integer. If the point is not in the list of traversed points, record the point and patrol time point, and determine whether the target point in the historical point data is a point in the candidate point set. If so, generate the above patrol result data based on the target point; otherwise, if the point is a point that has been traversed, ignore the point. It should be noted that the points that have executed the above cross-traversal judgment will no longer be subjected to a second cross-traversal judgment.

[0071] In another exemplary embodiment, assuming that the preset number of patrol points for each patrol is at least 30% higher than the required number of patrol points, the points in the historical point data can be used to generate patrol result data. It should be noted that the number of patrol points here is the number of points in the historical point data, and the required number of patrol points is the number of points in the candidate point set, and the comparison condition between the two can be flexibly set, including but not limited to the number of patrol points at least exceeding the preset value of the required number of patrol points (for example, 30%), etc. The preset value here can be flexibly set and is not limited in this application.

[0072] In another exemplary embodiment, a patrol point list can also be obtained based on the points in the historical point data, and then some of the points in the patrol point list can be deleted. For example, the first 10% of the points and the last 10% of the points in the patrol point list sorted by time can be deleted, and the middle 80% of the points can be used to generate patrol result data, and the specific proportion of the points can be flexibly set.

[0073] S208: Determine the area patrol result data corresponding to the target area according to the patrol result data corresponding to each target object.

[0074] Optionally, in an embodiment of the present application, the patrol result data corresponding to each of the above-mentioned target objects may be the same or different, and the above-mentioned area patrol result data may include the patrol situation of each target object in the target area, that is, by analyzing the patrol result data of each target object, the overall patrol situation of the target area can be obtained, including but not limited to patrol frequency, patrol route, patrol time, etc.

[0075] In an exemplary embodiment, Figure 5 is a schematic diagram of another optional method for processing detection data according to an embodiment of the present application, such as Figure 5 As shown, including but not limited to:

[0076] S502, obtaining patrol result data corresponding to each target object;

[0077] S504, according to each patrol result data, the number of points, patrol frequency, patrol route, patrol time, etc. of each point in the target area within a preset time period are counted to obtain the regional patrol result data corresponding to the target area;

[0078] S506, analyzing patrol defects in the target area based on the area patrol result data, for example, there are points that need to be patrolled but have not been patrolled, the patrol time of the points is insufficient, etc.;

[0079] S508, optimize patrol routes and point layout based on patrol defects to improve patrol efficiency and coverage;

[0080] S510, end.

[0081] For example, Figure 6 It is a schematic diagram of another optional detection data processing method according to an embodiment of the present application. The area patrol result data corresponding to the target area can also be visualized, that is, the data collected during the patrol process is displayed in the form of charts, maps, etc. The display interface is as follows Figure 6 shown.

[0082] In an exemplary embodiment, Figure 7 is a schematic diagram of another optional detection data processing method according to an embodiment of the present application. The detection data processing method proposed in the present application can be applied to the security field, including but not limited to: Figure 7 As shown:

[0083] S702, obtaining object detection data;

[0084] S704, determining a target object and target object detection data according to the object detection data;

[0085] S706, grouping the target object detection data according to each target object to obtain historical point data of each target object;

[0086] S708, sorting the points in the historical point data of each target object in ascending order according to the time sequence to obtain an initial patrol point list;

[0087] S710, filter the time period, obtain the point corresponding to each target object in the initial patrol point list within the preset time period, if the point exists, execute S712, otherwise, execute S742;

[0088] S712, starting traversal based on the central point in the initial patrol point list;

[0089] S714, traversing the points in the initial patrol point list to the front and rear sides of the center point respectively;

[0090] S716, determine whether the point traversal is completed, if not, execute S718, if yes, execute S724;

[0091] S718, determine whether the next point in the initial patrol point list has been traversed, if so, execute S720, otherwise execute S722;

[0092] S720, ignore this point;

[0093] S722, record the point and the corresponding patrol time point in the target patrol point list, and then execute S716;

[0094] S724, determining a list of target patrol points sorted in ascending order of time;

[0095] S726, determining whether the ratio between the number of patrol points in the target patrol point list and the number of preset patrol points exceeds 30%, if so, executing S728, otherwise, executing S740;

[0096] S728, determining the average patrol time of each point in the target patrol point list;

[0097] S730, deleting the first 10% and last 10% of the points in the target patrol point list;

[0098] S732, obtaining the total patrol duration according to the patrol time points corresponding to the start point and the end point in the target patrol point list;

[0099] S734, if the total patrol time exceeds the preset patrol time, execute S7236, otherwise, execute S738;

[0100] S736, abnormal patrol time;

[0101] S738, patrol is normal, provide patrol report (the above patrol result data);

[0102] S740: Insufficient patrol coverage, providing patrol report (including patrol conclusions on insufficient patrol coverage, etc.), and failure to perform patrol tasks;

[0103] S742, patrol mission not performed.

[0104] According to the embodiment of the present application, object detection data obtained by image acquisition of a target area by an image acquisition device is acquired, wherein the image acquisition device is deployed in the target area; the object detection data is identified to determine the historical point data corresponding to the target object, wherein the object detection data is related to at least one object, the at least one object includes the target object, the target object detection data associated with the target object detects an appearance object of a preset type and identifies the object information belonging to a preset object information set, the image acquisition device includes a target image acquisition device, the target image acquisition device has an association relationship with the target point in the target area, and the historical point data indicates that the target object has reached the target point within a preset time period; patrol result data of the target object within a preset time period is determined according to the historical point data and the candidate point set, wherein the patrol result data is determined by whether the target point belongs to the candidate point set; the regional patrol result data corresponding to the target area is determined according to the patrol result data corresponding to each target object. By analyzing the historical point data and the candidate point set, the patrol result data of the target area can be automatically determined without manual intervention, thereby improving processing efficiency and accuracy, and further solving the technical problem of low processing efficiency due to the complex processing flow of the detection data.

[0105] As an optional scheme, the above-mentioned identification of the above-mentioned object detection data and determination of the historical point data corresponding to the target object include: identifying the above-mentioned object detection data, and determining the object whose appearance object type is the above-mentioned preset type in the above-mentioned at least one object as the above-mentioned target object; determining the data associated with the above-mentioned target object in the above-mentioned object detection data as the above-mentioned target object detection data; grouping the point data in the above-mentioned target object detection data according to each object in the above-mentioned target object to determine the above-mentioned historical point data, wherein the above-mentioned historical point data includes the above-mentioned target point and the time point of arrival at the above-mentioned target point.

[0106] As an optional scheme, the above-mentioned identification of the above-mentioned object detection data and determination of the historical point data corresponding to the target object include: identifying the above-mentioned object detection data, and determining the object whose object information in at least one of the above-mentioned objects belongs to the above-mentioned preset object information set as the above-mentioned target object; determining the data associated with the above-mentioned target object in the above-mentioned object detection data as the above-mentioned target object detection data; grouping the point data in the above-mentioned target object detection data according to each object in the above-mentioned target object to determine the above-mentioned historical point data, wherein the above-mentioned historical point data includes the above-mentioned target point and the time point of arrival at the above-mentioned target point.

[0107] In an exemplary embodiment, if the preset type is a property uniform type and the appearance object is clothing, it can be determined whether the clothing of each identified object is a property uniform. If so, the object can be determined as the above-mentioned target object, and the object detection data including the target object will be determined as the above-mentioned target object detection data. Otherwise, it means that the clothing of the object is not a property uniform and cannot be determined as the above-mentioned target object.

[0108] In another exemplary embodiment, if the preset type is a car type and the appearance object is a means of transportation, it can be determined whether the means of transportation of each identified object is a car. If so, the object can be determined as the above-mentioned target object, including the object detection data of the target object will be determined as the above-mentioned target object detection data. Otherwise, it means that the object's means of transportation is not a car and cannot be determined as the above-mentioned target object.

[0109] In an exemplary embodiment, when the facial features of the object corresponding to the object detection data match the facial features of the object in the preset object information set, the object is the above-mentioned target object, and the object detection data including the target object will be determined as the above-mentioned target object detection data.

[0110] For example, assuming that the target object is a car and the target point is the dedicated parking space where the car is parked in a parking lot, the historical point data may include but is not limited to the location of the car parked in different parking lots and the time of parking. For example, the dedicated parking space where the car is parked in the parking lot has the longitude and latitude coordinates (40.7128, -74.0060), and the time of parking is 2 pm on October 1st.

[0111] As an optional solution, the above-mentioned method of determining the patrol result data of the above-mentioned target object within the above-mentioned preset time period based on the above-mentioned historical point data and the candidate point set includes: sorting the above-mentioned historical point data according to the acquisition time to obtain a target point list, wherein the point in the middle of the above-mentioned target point list is represented as the center point; performing N rounds of deduplication on each point in the above-mentioned target point list to obtain the above-mentioned target point set, and determining the above-mentioned patrol result data based on whether the ratio between the number of points in the above-mentioned target point set and the number of points in the above-mentioned candidate point set meets the preset ratio condition, wherein In the first round represented by i being equal to 1, the i-th group of adjacent points is deduplicated, and the points in the i-th group of adjacent points that do not belong to the target point set are added to the target point set, and the i-th group of adjacent points represents the points adjacent to the center point; and in each subsequent round represented by i being incremented by 1 relative to the previous round, the i-th group of adjacent points adjacent to the i-1-th group of adjacent points obtained in the previous round is deduplicated, and the points in the i-th group of adjacent points that do not belong to the target point set are added to the target point set, until i reaches N, where N is a positive integer greater than 1.

[0112] Optionally, in an embodiment of the present application, the above-mentioned target point list and target point set may include but are not limited to a plurality of points, and time point information corresponding to each point, etc.

[0113] In an exemplary embodiment, taking the target point list of {point 1, corresponding to time point A; point 2, corresponding to time point B; point 3, corresponding to time point C; point 1, corresponding to time point D; point 4, corresponding to time point E} as an example, the time sequence is: time point B is earlier than time point A, time point A is earlier than time point C, time point C is earlier than time point D, and time point D is earlier than time point E; therefore, the target point list sorted by time is {point 2, corresponding to time point B; point 1, corresponding to time point A; point 3, corresponding to time point C; point 1, corresponding to time point D; point 4, corresponding to time point E}, or, {point 4, corresponding to time point E; point 1, corresponding to time point D; point 3, corresponding to time point C; point 1, corresponding to time point A; point 2, corresponding to time point B}.

[0114] Furthermore, taking the target point list sorted by time as {point 2, corresponding to time point B; point 1, corresponding to time point A; point 3, corresponding to time point C; point 1, corresponding to time point D; point 4, corresponding to time point E} as an example, assuming that the target point set is an empty set, the above N rounds of deduplication can be understood as:

[0115] S1, determine point 3 in the middle of "point 3, corresponding to time point C" in the target point list sorted by time as the center point, and add point 3 to the target point set;

[0116] S2, i takes the value of 1, and performs the first deduplication. The first group of adjacent points is the points adjacent to point 3, which may include but is not limited to point 1 in "point 1, corresponding to time point A" and point 1 in "point 1, corresponding to time point D" as the first group of adjacent points;

[0117] S3, respectively judging whether the target point set includes points that are the same as the points in the first group of adjacent points. If so, the points are ignored. Otherwise, the points can be added to the target point set, which may include but are not limited to:

[0118] First judge the point with an earlier time point (that is, point 1 corresponding to time point A), and then judge the point with a later time point (that is, point 1 corresponding to time point D), or first judge the point with a later time point (that is, point 1 corresponding to time point D), and then judge the point with an earlier time point (that is, point 1 corresponding to time point A); taking the example of first judging the point with an earlier time point (that is, point 1 corresponding to time point A), and then judging the point with a later time point (that is, point 1 corresponding to time point D), since the target point set only includes one point 3, point 1 corresponding to time point D can be added to the target point set. At this time, it can be determined according to the corresponding time point that point 1 is stored before point 3, and the target point set includes point 1 and point 3. Since point 1 already exists in the target point set, point 1 corresponding to time point D will not be judged repeatedly, and the next round of deduplication operation will be directly performed.

[0119] S4, i takes the value of 2, and performs the second deduplication. The second group of adjacent points are the points adjacent to point 1. At this time, the points adjacent to point 1 are: point 2, point 3, and point 4. Since point 3 has been deduplicated, point 3 is removed, and the second group of adjacent points is point 2 and point 4.

[0120] S5, respectively determine whether the target point set includes points that are the same as the points in the second group of adjacent points. If included, the point is ignored. Otherwise, the point can be added to the target point set, which may include but is not limited to first determining the point with an earlier time point (i.e., point 2) and then determining the point with a later time point (i.e., point 4), or first determining the point with a later time point (i.e., point 4) and then determining the point with an earlier time point (i.e., point 2).

[0121] Among them, since the target point set only includes point 1 and point 3, point 2 and point 4 can be added to the target point set.

[0122] It can be understood that the round N of the above-mentioned deduplication operation may include but is not limited to being related to the points in the target point list. For example, the more different points there are in the target point list, the larger the value of round N is, so as to ensure the accuracy of the target point set, thereby improving the accuracy of the subsequent generation of patrol result data. Alternatively, the higher the similarity between the points in the target point list, the smaller the value of round N is, which further shortens the time of the deduplication operation, speeds up the determination of the target point set, and improves the efficiency of the subsequent generation of patrol result data.

[0123] Through the embodiments of the present application, first, in the first round, the points adjacent to the center point are deduplicated, and the points that do not belong to the target point set are added to the target point set. Then, starting from the second round, the adjacent points obtained in the previous round are deduplicated and added again until the specified number of rounds N is reached, and the target point set is sorted and screened for subsequent processing or analysis.

[0124] As an optional scheme, after performing N rounds of deduplication on each point in the above-mentioned target point list to obtain the above-mentioned target point set, the above-mentioned method also includes: screening each point in the above-mentioned target point set according to the above-mentioned acquisition time, and determining the redundant point set whose acquisition time is in the first P and last Q, wherein P and Q are both positive integers; deleting the above-mentioned redundant point set in the above-mentioned target point set to obtain an updated point set; and determining the above-mentioned patrol result data according to whether the ratio between the number of points in the above-mentioned updated point set and the number of points in the above-mentioned candidate point set meets the preset ratio condition.

[0125] Optionally, in an embodiment of the present application, the above P and Q values ​​can be flexibly set, and the present application does not limit this.

[0126] Exemplarily, assume that the target point set includes five points A, B, C, D, and E, and the acquisition times are 1, 2, 3, 4, and 5 respectively; preset P=1, Q=1, and screening is performed according to the acquisition time. The first P redundant points are A, the last Q redundant points are E, and the updated point set is B, C, and D; further, the preset ratio condition is that the ratio of the number of points in the updated point set to the number of points in the candidate point set is greater than or equal to 0.5, then the number of points in the updated point set is 3, and if the number of points in the candidate point set is 10, the condition cannot be met and cannot be used to determine the patrol result data, or, if the number of points in the candidate point set is 4, the condition is met and it can be used to determine the patrol result data.

[0127] It should be noted that the ratio of the number of points in the target point set can also be set. For example, 10% of the points in the target point set with earlier corresponding time points can be used as the above-mentioned P points, and 10% of the points in the target point set with later corresponding time points can be used as the above-mentioned Q points. This application does not limit this.

[0128] Through the embodiments of the present application, each point in the target point set is screened according to the acquisition time, a redundant point set whose acquisition time is in the first P and last Q points is determined, and the redundant point set in the target point set is deleted to obtain an updated point set; patrol result data is determined based on whether the ratio between the number of points in the updated point set and the number of points in the candidate point set meets a preset ratio condition, thereby improving the generation efficiency and accuracy of the patrol result data.

[0129] As an optional scheme, after the above-mentioned historical point data is sorted according to the acquisition time to obtain the target point list, the above-mentioned method also includes: acquiring the first point and the second point in the above-mentioned target point list, wherein the above-mentioned first point is the point with the first acquisition time in the above-mentioned target point list, and the above-mentioned second point is the point with the last acquisition time in the above-mentioned target point list; determining the patrol duration according to the first acquisition time corresponding to the above-mentioned first point and the second acquisition time corresponding to the above-mentioned second point; when the above-mentioned patrol duration meets the preset duration condition, determining the above-mentioned patrol result data according to whether the ratio between the number of points in the above-mentioned target point set and the number of points in the above-mentioned candidate point set meets the preset ratio condition.

[0130] Optionally, in an embodiment of the present application, the above-mentioned first point can be understood as the point whose corresponding time point in the target point list (the above-mentioned first acquisition time) is the earliest time point, and the above-mentioned second point can be understood as the point whose corresponding time point in the target point list (the above-mentioned second acquisition time) is the latest time point, or, the above-mentioned first point can also be the point whose corresponding time point in the target point set is the earliest time point, and the above-mentioned second point can also be the point whose corresponding time point in the target point set is the latest time point, that is, you can choose whether to perform deduplication operation on the target point list, and the present application does not limit this.

[0131] In an exemplary embodiment, assume that the target point list is {Point A: 01-0108:00:00; Point B: 10:00:00; Point C: 12:00:00}, wherein Point A is the point with the first acquisition time, and Point B is the point with the last acquisition time. Assume that the acquisition time corresponding to Point A is 08:00:00, and the acquisition time corresponding to Point B is 10:00:00. Based on these two times, the above patrol duration is determined to be 2 hours. Assume that the preset duration condition is 3 hours. Therefore, the preset duration condition is not met, and the patrol result data indicates that the patrol duration is too short.

[0132] In another exemplary embodiment, if it is assumed that the preset duration condition is 1 hour, then if the preset duration condition is met, patrol result data with a normal patrol duration can be obtained.

[0133] Through the embodiments of the present application, the first point and the second point in the target point list are obtained; the patrol duration is determined according to the first acquisition time corresponding to the first point and the second acquisition time corresponding to the second point; when the patrol duration meets the preset duration condition, the patrol result data is determined according to whether the ratio between the number of points in the target point set and the number of points in the candidate point set meets the preset ratio condition, so as to more accurately evaluate the patrol effect.

[0134] As an alternative solution, determining the area patrol result data corresponding to the target area based on the above-mentioned patrol result data corresponding to each of the above-mentioned target objects includes: determining the number of patrols for each of the above-mentioned target points according to the above-mentioned patrol result data; the above-mentioned target points corresponding to different above-mentioned numbers of patrols are marked with different forms of point identifiers on the visualization interface to obtain the target visualization interface corresponding to the above-mentioned target area.

[0135] Optionally, in the embodiments of the present application, the above-mentioned patrol result data includes the patrol results corresponding to multiple target objects respectively. Therefore, the number of patrols for each target point can be obtained according to the patrol result data, and the above-mentioned point identifier may include, but is not limited to, forms such as digital markings, color markings, icons, etc.

[0136] Exemplarily, the above-mentioned area patrol result data is visually displayed according to the number of patrols. For example, as Figure 6 shown, the number of patrols being 0, the number of patrols ≥ n, and the number of patrols < n can all be marked with different point identifiers, clearly showing the number of patrols for each target point in the visualization interface and better understanding the patrol situation of the target area.

[0137] In an exemplary embodiment, digital markings can be used to represent the number of patrols. For example, the point with 1 patrol is marked with the number 1, and the point with 2 patrols is marked with the number 2. Alternatively, different colors can be used to represent different numbers of patrols. For example, the point with 1 patrol is marked in green, the point with 2 patrols is marked in yellow, and the point with 3 patrols is marked in red. Different icons can also be used to represent different numbers of patrols. For example, the point with 1 patrol is marked with a circular icon, the point with 2 patrols is marked with a square icon, and the point with 3 patrols is marked with a triangular icon, etc.

[0138] In an exemplary embodiment, the detection data processing method proposed in the present application may include but is not limited to being realized through collaborative control of a front-end camera and a cloud platform, and can be used in application scenarios of attendance statistics based on portrait clustering and uniform judgment. Taking a residential community as an example, it can be used with the existing security monitoring cameras in the community. There is no need to renovate and construct the community, and it does not affect the generation of community residents. The investment cost is low. For the personnel being checked, there is no need for additional workload, nor is there any need to increase the equipment carried during patrols to assist the property in conducting patrol assessments of the security and other patrol personnel in the community at a low cost and accurately. Before the system is officially used, a front-facing portrait of the person being assessed (security, the above-mentioned target object) can be registered, and the matching uniforms (security uniforms, the above-mentioned preset type of appearance objects) can be entered. The front-end intelligent camera captures all the personnel in the picture, and a personnel file is formed through the cloud platform portrait clustering algorithm. Based on the uniform and registration information, it is determined whether the person is being checked, and then the patrol attendance data (the above-mentioned patrol result data) is generated according to the clustering information of the person being checked (the above-mentioned target object detection data).

[0139] Specifically, it may include but is not limited to:

[0140] S1, the community camera collects the face and body information of the people, including the characteristics of the people, clothing and other face and body attributes, and provides it to the cloud platform for portrait archiving. After archiving, each person's snapshot at different times and spaces can be stored as a natural person. For security personnel, if they are not registered personnel, the management personnel will determine the treatment method or ignore them. For registered personnel in uniform, they will be archived and landed;

[0141] S2, based on the effective patrol attendance of security personnel, each patrol must be carried out at a certain number of points. The required patrol points, normal patrol duration n, and required patrol time A are preset first. Based on the above presets, the patrol situation is judged, including but not limited to:

[0142] S2-1, within the time interval of each set patrol moment, obtain the personnel cluster information (the above-mentioned object information) and analyze it. Considering that the time when security personnel start patrol will be slightly adjusted according to the actual situation, patrolling earlier or later, therefore, within the statistical patrol time point, a 1-hour reserved judgment time will be added before and after the standard patrol time period (A~(A+n)). For example, if the patrol time is A, the cluster data within the time period (A-1h)~(A+n+1h) can be analyzed.

[0143] S2-2, remove duplicate patrol point lists from the center to both ends to obtain a pure patrol list (the above target point list). The specific method is as follows: Figure 7As shown, select the one in the center of the list and traverse to the left and right sides at the same time (traverse one on the left and one on the right, cross traversal). If the next point is not in the list of traversed points, record the point and patrol time point; if it is a target that has been traversed, ignore it; assuming that the system presets that each patrol point must exceed at least 1 / 3 of the required patrol points to be considered an effective patrol, if the number of patrol points is less than 1 / 3 of the number of patrol points to be patrolled, it is judged that there is no patrol during this period; considering that during the statistical time period, patrol personnel may have other work besides patrol work and may also appear at patrol points, according to the above cross traversal deduplication method, there are two situations for points passed by informal patrols, namely: if they are repeated with points in the patrol list, they have been deduplicated and do not affect the patrol time statistics; if they are repeated with points in the patrol list, they have been deduplicated and do not affect the patrol time statistics; The points in the table are not repeated, and these points will appear at the front or end of the list. If the patrol time of these points is included when calculating the patrol time, the patrol time may be counted as too long. The actual patrol task generally starts or ends at the office or guard post where the property staff are concentrated. For example, security personnel are slacking off or leaving their posts during patrols, which are generally concentrated in the middle part of the patrol. In view of the fact that the patrol time at the front and back ends of the patrol points has little effect on attendance and the time may be inaccurate, when calculating the patrol time, the front and back 10% (or the specific proportion can be selected according to the actual situation) of the patrol point list can be removed, and only the middle 80% of the points can be checked to see if there is a problem of too long patrol time. Then, based on the above patrol data, a personnel patrol report can be generated.

[0144] S3, stores individual patrol attendance data, and based on each person's patrol result data, can form the community's patrol result data. According to the points that need to be patrolled in the community and the actual patrol result data, the weak points of the community patrol can be regularly analyzed to check for omissions and fill in the gaps, thereby making the community patrol more comprehensive. For example, based on a week's data, point A has not been patrolled, then the management personnel can communicate with the patrol personnel and improve the patrol route.

[0145] Through the embodiments of the present application, security attendance based on clustering result analysis is realized, wherein it can be implemented based on the existing community surveillance cameras without the need to set up additional collection equipment; it only needs to input security personnel information and security uniform information in the early stage, and the security patrol attendance is automatically generated without additional workload; through uniform filtering, non-uniform personnel data is not recorded, avoiding excessive collection of data on other personnel; based on this solution, the patrol map of the community and the distribution of patrol frequency can be intuitively seen, which is convenient for community managers to optimize patrol routes based on data.

[0146] It is understandable that in the specific implementation of this application, related data such as user information is involved. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0147] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0148] According to another aspect of the embodiments of the present application, a detection data processing device for implementing the detection data processing method is also provided. Figure 8 As shown, the device comprises:

[0149] An acquisition module 802 is used to acquire object detection data obtained by an image acquisition device performing image acquisition on a target area, wherein the image acquisition device is deployed in the target area;

[0150] The identification module 804 is used to identify the object detection data and determine the historical point data corresponding to the target object, wherein the object detection data is related to at least one object, the at least one object includes the target object, the target object detection data associated with the target object detects an appearance object of a preset type and identifies object information belonging to a preset object information set, the image acquisition device includes a target image acquisition device, the target image acquisition device has an associated relationship with the target point in the target area, and the historical point data indicates that the target object has reached the target point within a preset time period;

[0151] The first determination module 806 is used to determine the patrol result data of the target object within a preset time period according to the historical point data and the candidate point set, wherein the patrol result data is determined by whether the target point belongs to the candidate point set;

[0152] The second determination module 808 is used to determine the area patrol result data corresponding to the target area according to the patrol result data corresponding to each target object.

[0153] As an optional solution, the above-mentioned device is used to identify the object detection data and determine the historical point data corresponding to the target object in the following manner: identify the object detection data, and determine an object whose appearance object type is a preset type in at least one object as the target object; determine the data associated with the target object in the object detection data as the target object detection data; group the point data in the target object detection data according to each object in the target object to determine the historical point data, wherein the historical point data includes the target point and the time point of arrival at the target point.

[0154] As an optional scheme, the above-mentioned device is used to identify the object detection data and determine the historical point data corresponding to the target object in the following manner: identify the object detection data, and determine the object whose object information belongs to a preset object information set in at least one object as the target object; determine the data associated with the target object in the object detection data as the target object detection data; group the point data in the target object detection data according to each object in the target object to determine the historical point data, wherein the historical point data includes the target point and the time point of arrival at the target point.

[0155] As an optional solution, the above-mentioned device is used to determine the patrol result data of the target object within a preset time period according to the historical point data and the candidate point set in the following manner: sort the historical point data according to the acquisition time to obtain a target point list, wherein the point in the middle of the target point list is represented as the center point; perform N rounds of deduplication on each point in the target point list to obtain a target point set, and determine the patrol result data according to whether the ratio between the number of points in the target point set and the number of points in the candidate point set meets the preset ratio condition , where: in the first round represented by i being equal to 1, duplicates are removed from the i-th group of adjacent points, and the points in the i-th group of adjacent points that do not belong to the target point set are added to the target point set, and the i-th group of adjacent points represents the points adjacent to the center point; and in each subsequent round represented by i being incremented by 1 relative to the previous round, duplicates are removed from the i-th group of adjacent points adjacent to the i-1-th group of adjacent points obtained in the previous round, and the points in the i-th group of adjacent points that do not belong to the target point set are added to the target point set, until i reaches N, where N is a positive integer greater than 1.

[0156] As an optional solution, the above-mentioned device is also used to: perform N rounds of deduplication on each point in the target point list to obtain a target point set, then screen each point in the target point set according to the acquisition time, and determine a redundant point set whose acquisition time is in the first P and last Q points, where P and Q are both positive integers; delete the redundant point set in the target point set to obtain an updated point set; and determine the patrol result data based on whether the ratio between the number of points in the updated point set and the number of points in the candidate point set meets a preset ratio condition.

[0157] As an optional scheme, the above-mentioned device is also used to: sort the historical point data according to the acquisition time, and after obtaining the target point list, obtain the first point and the second point in the target point list, wherein the first point is the point with the first acquisition time in the target point list, and the second point is the point with the last acquisition time in the target point list; determine the patrol duration according to the first acquisition time corresponding to the first point and the second acquisition time corresponding to the second point; when the patrol duration meets the preset duration condition, determine the patrol result data according to whether the ratio between the number of points in the target point set and the number of points in the candidate point set meets the preset ratio condition.

[0158] As an optional solution, the above-mentioned device is used to determine the area patrol result data corresponding to the target area according to the patrol result data corresponding to each target object in the following manner: determine the number of patrols for each target point according to the patrol result data; mark the target points corresponding to different patrol times with different forms of point identifiers in the visualization interface to obtain the target visualization interface corresponding to the target area.

[0159] In the embodiments of the present application, the term "module" or "unit" refers to a computer program or a part of a computer program that has a predetermined function and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as processing circuits or memories), or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

[0160] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0161] According to one aspect of the present application, a computer program product is provided. The computer program product includes a computer program.

[0162] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0163] Fig. 9 The structure block diagram of a computer system for implementing an electronic device according to an embodiment of the present application is schematically shown.

[0164] It should be noted that Fig. 9 The computer system 900 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0165] like Fig. 9 As shown, the computer system 900 includes a central processing unit 901 (CPU), which can perform various appropriate actions and processes according to the program stored in the read-only memory 902 (ROM) or the program loaded from the storage part 908 to the random access memory 903 (RAM). Various programs and data required for system operation are also stored in the random access memory 903. The central processing unit 901, the read-only memory 902 and the random access memory 903 are connected to each other through a bus 904. The input / output interface 905 (Input / Output interface, i.e., I / O interface) is also connected to the bus 904.

[0166] The following components are connected to the input / output interface 905: an input section 906 including a keyboard, a mouse, etc.; an output section 907 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage section 908 including a hard disk, etc.; and a communication section 909 including a network interface card such as a LAN card, a modem, etc. The communication section 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to the input / output interface 905 as needed. A removable medium 911, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 910 as needed so that a computer program read therefrom is installed into the storage section 908 as needed.

[0167] In particular, according to an embodiment of the present application, the process described in each method flow chart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer readable medium, and the computer program contains a program code for executing the method shown in the flow chart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 909, and / or installed from the removable medium 911. When the computer program is executed by the central processor 901, various functions defined in the system of the present application are executed.

[0168] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 909, and / or installed from the removable medium 911. When the computer program is executed by the central processor 901, various functions provided by the embodiments of the present application are performed.

[0169] According to another aspect of the embodiment of the present application, an electronic device for implementing the above-mentioned detection data processing method is also provided. The electronic device may be Figure 1 The terminal device or server shown in the figure. This embodiment is described by taking the electronic device as a terminal device as an example. Fig.10 As shown, the electronic device includes a memory 1002 and a processor 1004. The memory 1002 stores a computer program, and the processor 1004 is configured to execute the steps in any of the above method embodiments through the computer program.

[0170] Optionally, in this embodiment, the electronic device may be located in at least one network device among a plurality of network devices of a computer network.

[0171] Optionally, in this embodiment, the above-mentioned processor can be configured to execute the methods in each embodiment of the present application through a computer program.

[0172] Alternatively, a person skilled in the art may understand that: Fig.10 The structure shown is for illustration only. Fig.10 The structure of the electronic device is not limited. Fig.10 More or fewer components (such as network interfaces, etc.) as shown in, or with Fig.10 Different configurations are shown.

[0173] Among them, the memory 1002 can be used to store software programs and modules, such as the program instructions / modules corresponding to the detection data processing method and device in the embodiment of the present application. The processor 1004 executes various functional applications and data processing by running the software programs and modules stored in the memory 1002, that is, realizing the above-mentioned detection data processing method. The memory 1002 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 1002 may further include a memory remotely arranged relative to the processor 1004, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. Among them, the memory 1002 can be specifically, but not limited to, used to store information such as detection result data. As an example, such as Fig.10 As shown, the memory 1002 may include, but is not limited to, the acquisition module 802, the identification module 804, the first determination module 806, and the second determination module 808 in the detection data processing device. In addition, other module units in the detection data processing device may also be included but are not limited to, which will not be repeated in this example.

[0174] Optionally, the transmission device 1006 is used to receive or send data via a network. Specific examples of the network may include a wired network and a wireless network. In one example, the transmission device 1006 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices and routers via a network cable so as to communicate with the Internet or a local area network. In one example, the transmission device 1006 is a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0175] In addition, the electronic device further comprises: a display 1008 for displaying the detection result data; and a connection bus 1010 for connecting various module components in the electronic device.

[0176] In other embodiments, the terminal device or server may be a node in a distributed system, wherein the distributed system may be a blockchain system, and the blockchain system may be a distributed system formed by connecting the multiple nodes through network communication. The nodes may form a peer-to-peer network, and any form of computing device, such as a server, terminal or other electronic device, may become a node in the blockchain system by joining the peer-to-peer network.

[0177] According to one aspect of the present application, a computer-readable storage medium is provided, and a processor of an electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device executes the detection data processing method provided in various optional implementations of the above-mentioned detection data processing.

[0178] Optionally, in this embodiment, the above-mentioned computer-readable storage medium can be configured to store data for executing the methods in various embodiments of the present application.

[0179] Optionally, in this embodiment, a person of ordinary skill in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing hardware related to the terminal device through a program, and the program may be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0180] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0181] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above computer-readable storage medium. Based on this understanding, the technical solution of the present application, 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, which is stored in a storage medium and includes several instructions for one or more electronic devices to execute all or part of the steps of the methods described in each embodiment of the present application.

[0182] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0183] In the several embodiments provided in the present application, it should be understood that the disclosed application can be implemented in other ways. Among them, 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. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0184] 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.

[0185] In addition, each functional unit in each embodiment of the present application 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.

[0186] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for processing detection data, characterized in that: include: Acquiring object detection data obtained by an image acquisition device performing image acquisition on a target area, wherein the image acquisition device is deployed in the target area; The object detection data is identified to determine historical point data corresponding to the target object, wherein the object detection data is associated with at least one object, the at least one object includes the target object, the target object detection data associated with the target object detects an appearance object of a preset type and identifies object information belonging to a preset object information set, the image acquisition device includes a target image acquisition device, the target image acquisition device has an associated relationship with a target point in the target area, and the historical point data indicates that the target object has reached the target point within a preset time period; Determine patrol result data of the target object within the preset time period according to the historical point data and the candidate point set, wherein the patrol result data is determined by whether the target point belongs to the candidate point set; Determine the area patrol result data corresponding to the target area according to the patrol result data corresponding to each target object; The method of determining the area patrol result data corresponding to the target area based on the patrol result data corresponding to each target object includes: sorting the historical point data according to the acquisition time to obtain a target point list; performing N rounds of deduplication on each point in the target point list to obtain a target point set, wherein N is a positive integer; determining the patrol duration when the ratio between the number of points in the target point set and the number of points in the candidate point set meets a preset ratio condition, and determining the patrol result data when the patrol duration meets a preset duration condition.

2. The method according to claim 1, characterized in that The identifying the object detection data to determine the historical point data corresponding to the target object includes: Identifying the object detection data, and determining an object of the at least one object whose appearance object type is the preset type as the target object; determining data associated with the target object in the object detection data as the target object detection data; The point data in the target object detection data are grouped according to each object in the target object to determine the historical point data, wherein the historical point data includes the target point and the time point of reaching the target point.

3. The method according to claim 1, characterized in that The identifying the object detection data to determine the historical point data corresponding to the target object includes: Identifying the object detection data, and determining an object among the at least one object whose object information belongs to the preset object information set as the target object; determining data associated with the target object in the object detection data as the target object detection data; The point data in the target object detection data are grouped according to each object in the target object to determine the historical point data, wherein the historical point data includes the target point and the time point of reaching the target point.

4. The method according to claim 1, characterized in that The determining of patrol result data of the target object within the preset time period according to the historical point data and the candidate point set includes: The historical point data are sorted according to the acquisition time to obtain a target point list, wherein the point in the middle of the target point list is represented as the center point; Perform N rounds of deduplication on each point in the target point list to obtain the target point set, and determine the patrol result data according to whether the ratio between the number of points in the target point set and the number of points in the candidate point set meets the preset ratio condition, wherein: In the first round represented by i being equal to 1, deduplication is performed on the i-th group of adjacent points, and points in the i-th group of adjacent points that do not belong to the target point set are added to the target point set, wherein the i-th group of adjacent points represents points adjacent to the center point; and In each subsequent round where i is incremented by 1 relative to the previous round, the i-th group of adjacent points adjacent to the i-1-th group of adjacent points obtained in the previous round are deduplicated, and the points in the i-th group of adjacent points that do not belong to the target point set are added to the target point set, until i reaches N, where N is a positive integer greater than 1.

5. The method according to claim 4, characterized in that After performing N rounds of deduplication on each point in the target point list to obtain the target point set, the method further includes: Screening each point in the target point set according to the acquisition time, and determining a redundant point set whose acquisition time is in the first P and last Q points, where P and Q are both positive integers; Deleting the redundant point set in the target point set to obtain an updated point set; The patrol result data is determined according to whether a ratio between the number of points in the update point set and the number of points in the candidate point set meets a preset ratio condition.

6. The method according to claim 4, characterized in that After the historical point data are sorted according to the acquisition time to obtain the target point list, the method further includes: Acquire the first point and the second point in the target point list, wherein the first point is the point with the first acquisition time in the target point list, and the second point is the point with the last acquisition time in the target point list; Determine the patrol duration according to a first acquisition time corresponding to the first point and a second acquisition time corresponding to the second point; When the patrol duration satisfies the preset duration condition, the patrol result data is determined according to whether the ratio between the number of points in the target point set and the number of points in the candidate point set satisfies a preset ratio condition.

7. The method according to claim 1, characterized in that The determining of the area patrol result data corresponding to the target area according to the patrol result data corresponding to each target object includes: Determine the number of patrols for each target point according to the patrol result data; The target points corresponding to the different patrol times are marked in the visualization interface using different forms of point identifiers to obtain a target visualization interface corresponding to the target area.

8. A detection data processing device, characterized in that: include: An acquisition module, used to acquire object detection data obtained by an image acquisition device performing image acquisition on a target area, wherein the image acquisition device is deployed in the target area; an identification module, configured to identify the object detection data and determine historical point data corresponding to the target object, wherein the object detection data is associated with at least one object, the at least one object includes the target object, the target object detection data associated with the target object detects an appearance object of a preset type and identifies object information belonging to a preset object information set, the image acquisition device includes a target image acquisition device, the target image acquisition device has an associated relationship with a target point in the target area, and the historical point data indicates that the target object has reached the target point within a preset time period; A first determination module is used to determine patrol result data of the target object within the preset time period according to the historical point data and the candidate point set, wherein the patrol result data is determined by whether the target point belongs to the candidate point set; A second determination module is used to determine the area patrol result data corresponding to the target area according to the patrol result data corresponding to each target object; The device is used to determine the area patrol result data corresponding to the target area according to the patrol result data corresponding to each target object in the following manner: sort the historical point data according to the acquisition time to obtain a target point list; perform N rounds of deduplication on each point in the target point list to obtain a target point set, where N is a positive integer; determine the patrol duration when the ratio between the number of points in the target point set and the number of points in the candidate point set meets a preset ratio condition, and determine the patrol result data when the patrol duration meets a preset duration condition.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein the computer program can be executed by an electronic device to perform the method described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 7 are implemented.

11. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 7 through the computer program.

Images