Front-end monitoring device management method, apparatus and device, and storage medium

Abstract

The application discloses a front-end monitoring device management method and device, equipment and a storage medium, and relates to the technical field of monitoring device management. The method calculates the scene similarity of monitoring pictures taken by multiple front-end monitoring devices during inspection. When the scene similarity between two monitoring pictures is high, it indicates that the monitoring scenes of the corresponding two monitoring devices are the same. Then, it is further judged whether the position information of the two front-end monitoring devices is consistent. If the position information is consistent, it indicates that the two front-end monitoring devices may be caused by external force to make the monitoring area of one device incorrect, so that the two front-end monitoring devices monitor the same scene, and then generate corresponding inspection results. The inspection results are uploaded to a management platform device, so that the management personnel can process in time, and resource waste caused by different monitoring devices monitoring the same monitoring scene is avoided.

Description

Technical Field

[0001] This application relates to the field of computer technology, and more particularly to the field of monitoring equipment management technology, providing a front-end monitoring equipment management method, apparatus, device, and storage medium. Background Technology

[0002] Currently, surveillance equipment is widely used in various monitoring scenarios. To facilitate the management of surveillance equipment, it is common practice to integrate the equipment into a unified management platform. This platform then manages the surveillance equipment. In addition, a single surveillance device may be integrated into different management platforms, such as village-level government affairs management platforms, public affairs management platforms, and fire safety management platforms, so that the surveillance videos from each device can be flexibly accessed by various management units.

[0003] Currently, most management platforms can manage the video images from surveillance equipment, but they lack effective management measures for the equipment itself. For example, due to installation or post-installation errors, surveillance equipment may be subject to multiple captures of a single scene, resulting in wasted resources. Summary of the Invention

[0004] This application provides a front-end monitoring device management method, apparatus, device, and storage medium to solve the problem of resource waste caused by multiple monitoring devices collecting data multiple times for a single scene.

[0005] On the one hand, a method for managing front-end monitoring devices is provided, the method comprising:

[0006] Based on the pre-set monitoring equipment inspection strategy, the multiple front-end monitoring devices to be inspected in this inspection are identified.

[0007] Acquire monitoring images captured by each of the aforementioned front-end monitoring devices, wherein the time elapsed between the capture time of each monitoring image and the current time does not exceed a set time elapsed threshold.

[0008] Determine whether the scene similarity between any two monitored images is greater than a set first scene similarity threshold;

[0009] If the scene similarity is greater than the first scene similarity threshold, then it is determined whether the location information of the front-end monitoring device corresponding to the monitoring image associated with the similarity is consistent;

[0010] If the location information of the front-end monitoring devices is consistent, an inspection result is generated for the front-end monitoring devices monitoring the same scene, and the inspection result is uploaded to the management platform device.

[0011] On the one hand, a front-end monitoring equipment management device is provided, the device comprising:

[0012] The strategy determination unit is used to determine the multiple front-end monitoring devices to be inspected in this inspection based on the pre-set monitoring device inspection strategy.

[0013] The image acquisition unit is used to acquire the monitoring images captured by each of the front-end monitoring devices, wherein the time between the capture time of each monitoring image and the current time does not exceed a set time threshold.

[0014] The inspection and judgment unit is used to determine whether the scene similarity between any two monitoring images is greater than a set first scene similarity threshold; if the scene similarity is greater than the first scene similarity threshold, it is determined whether the location information of the front-end monitoring device corresponding to the monitoring images associated with the similarity is consistent; if the location information of the front-end monitoring device is consistent, an inspection result is generated for the front-end monitoring device to monitor the same scene.

[0015] The sending unit is used to upload the inspection results to the management platform device.

[0016] Optionally, the apparatus further includes a similarity determination unit, used for:

[0017] Scene features are extracted from each of the monitoring images to obtain scene feature information for each monitoring image;

[0018] Feature comparison is performed on the scene feature information of each pair of monitoring images to determine the scene similarity between each pair of monitoring images.

[0019] Optionally, the inspection determination unit is further configured to:

[0020] If the scene similarity is not greater than the first scene similarity threshold, then determine whether the scene similarity is greater than the set second scene similarity threshold, where the second scene similarity threshold is less than the first scene similarity threshold;

[0021] If the scene similarity is determined to be greater than the second scene similarity threshold, then based on the facial feature information in the surveillance images associated with the scene similarity, it is determined whether the surveillance images belong to the same scene;

[0022] If it is determined that the surveillance images belong to the same scene, determine whether the location information of the front-end monitoring devices corresponding to the surveillance images is consistent;

[0023] If the location information of the front-end monitoring devices is consistent, an inspection result is generated for the front-end monitoring devices monitoring the same scene, and the inspection result is uploaded to the management platform device.

[0024] Optionally, the inspection determination unit is specifically used for:

[0025] Face detection was performed on the surveillance images respectively;

[0026] If faces are detected in all of the surveillance images, facial feature information is extracted from each of the surveillance images.

[0027] The facial feature information corresponding to the surveillance image is compared to determine whether the facial similarity of the surveillance image is greater than the set facial similarity threshold.

[0028] If the facial similarity is greater than the facial similarity threshold, then the surveillance images are determined to belong to the same scene; or,

[0029] If the facial similarity is not greater than the facial similarity threshold, then the surveillance image is determined to belong to a different scene.

[0030] Optionally, the inspection judgment unit is further configured to generate an inspection result indicating that the location information of one of the front-end monitoring devices is incorrectly entered if it is determined that the location information of the front-end monitoring devices is inconsistent.

[0031] The sending unit is also used to upload the inspection results to the management platform device.

[0032] Optionally, if the N front-end monitoring devices come from multiple cascaded lower-level platforms, then the inspection and judgment unit is further used for:

[0033] Determine whether the identifiers of the lower-level platforms from which the front-end monitoring devices originate are the same;

[0034] If the identifiers of the lower-level platforms from which the front-end monitoring devices originate are different, then duplicate indication information is generated indicating that the front-end monitoring devices of the lower-level platforms are duplicated, and the duplicate front-end monitoring devices are merged and optimized.

[0035] On one hand, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any of the above methods.

[0036] On the one hand, a computer storage medium is provided that stores computer program instructions thereon, which, when executed by a processor, implement the steps of any of the above methods.

[0037] On one hand, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the steps of any of the methods described above.

[0038] In this embodiment, scene similarity calculation is performed on monitoring images captured by multiple front-end monitoring devices during inspection. When the scene similarity between monitoring images is high, it indicates that the monitoring scenes of the corresponding front-end monitoring devices are the same. Further, it is determined whether the location information of the two front-end monitoring devices is consistent. If they are consistent, it indicates that the monitoring area of ​​one of the two front-end monitoring devices may have been caused by external force, resulting in the two front-end monitoring devices monitoring the same scene. This generates corresponding inspection results, which are then uploaded to the management platform device so that the management personnel can handle them in a timely manner and avoid resource waste caused by different monitoring devices monitoring the same scene. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0040] Figure 1 An application scenario diagram provided for an embodiment of this application;

[0041] Figure 2 This is another application scenario diagram provided by an embodiment of this application;

[0042] Figure 3 A flowchart illustrating a front-end monitoring device management method provided in an embodiment of this application;

[0043] Figure 4 Another flowchart illustrating the front-end monitoring device management method provided in this application embodiment;

[0044] Figure 5 A schematic diagram of a front-end monitoring device management apparatus provided in an embodiment of this application;

[0045] Figure 6 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application. Unless otherwise specified, the embodiments and features in the embodiments of this application can be arbitrarily combined with each other. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than that shown here.

[0047] The design concept of the embodiments of this application will be briefly introduced below.

[0048] Surveillance equipment is ubiquitous in daily life, greatly enhancing convenience and security. Currently, various management platforms can generally manage surveillance video images, such as classifying heterogeneous data sources to distinguish between basic video image attributes, descriptive information, and raw data—essentially classifying video image data based on its attributes. However, effective management measures for surveillance equipment are lacking. For instance, errors in installation or post-installation adjustments may lead to multiple captures of a single scene, resulting in wasted resources.

[0049] Based on this, this application provides a front-end monitoring device management method. In this method, scene similarity is calculated for monitoring images captured by multiple front-end monitoring devices during inspection. When the scene similarity between two monitoring images is high, it indicates that the monitoring scenes of the two monitoring devices are the same. Further, it is determined whether the location information of the two front-end monitoring devices is consistent. If they are consistent, it indicates that the monitoring area of ​​one of the devices may be incorrect due to external force, causing the two front-end monitoring devices to monitor the same scene. This generates corresponding inspection results, which are then uploaded to the management platform device so that the management personnel can handle them in a timely manner and avoid resource waste caused by different monitoring devices monitoring the same scene.

[0050] Furthermore, if the location information of two front-end monitoring devices is different, but the monitoring scenarios of the two front-end monitoring devices are the same, then there is doubt about the location of the two front-end monitoring devices. In this case, the corresponding inspection results will be generated and reported to the management platform for timely handling.

[0051] In this embodiment of the application, it is also considered that when multiple front-end monitoring devices capture the same scene due to external forces, the monitoring scenes of the front-end monitoring devices may have certain differences. Therefore, other factors can be used to assist in the judgment. Based on this, this embodiment of the application performs face detection on the monitoring images. When two monitoring images contain faces, feature comparison can be performed on the faces. When the faces are consistent, it indicates that the monitoring scenes of the two front-end monitoring devices are the same, thereby reducing the error in judging the similarity of the monitoring scenes.

[0052] After introducing the design concept of the embodiments of this application, the following is a brief introduction to the application scenarios to which the technical solutions of the embodiments of this application can be applied. It should be noted that the application scenarios described below are only for illustrating the embodiments of this application and are not intended to limit the scope. In specific implementation, the technical solutions provided by the embodiments of this application can be flexibly applied according to actual needs.

[0053] The solution provided in this application can be applied to most monitoring equipment management scenarios.

[0054] like Figure 1 The diagram shown is an application scenario diagram provided by an embodiment of this application. In this scenario, there are front-end monitoring devices 101, monitoring device management devices 102, management platform devices 103, and management user terminals 104.

[0055] The front-end monitoring device 101 can be any device with monitoring capabilities, such as cameras deployed in various monitoring scenarios. The front-end monitoring device 101 can capture monitoring video streams and upload them to the management platform device 103. The front-end monitoring device 101 can be connected to one or more management platform devices 103, and the monitoring video streams captured by it can be uploaded to each management platform device 103 separately.

[0056] The monitoring device management device 102 is a device with certain processing capabilities, which may include one or more processors 1021, a memory 1022, and an I / O interface 1023 for interacting with terminals. Furthermore, the monitoring device management device 102 may also be configured with a database 1024, which can be used to store data involved in the methods of this application embodiment. The memory 1022 of the monitoring device management device 102 may also store program instructions for the front-end monitoring device management method provided in this application embodiment. When these program instructions are executed by the processor 1021, they can be used to implement the steps of the front-end monitoring device management method provided in this application embodiment, so as to perform inspections of multiple front-end monitoring devices and obtain corresponding inspection results.

[0057] The management platform device 103 can be a backend server for the management platform. For example, it can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms, but it is not limited to these.

[0058] The management user terminal 104 can open the page corresponding to the management platform device 103, such as if a management client is installed, or it can open the corresponding management page through a browser. The management user terminal 104 can be, for example, a mobile phone, tablet computer (PAD), laptop computer, desktop computer, smart TV, or smart wearable device.

[0059] In practical applications, the front-end monitoring device 101 captures the monitoring video stream of its corresponding monitoring scene and uploads it to the corresponding management platform device 103. When the inspection time arrives, the monitoring device management device 102 can obtain the recently captured monitoring images of N front-end monitoring devices 101 specified in the inspection plan from the management platform device 103, and determine whether the monitoring scenes of each front-end monitoring device 101 are the same based on the monitoring images. When the monitoring scenes are the same, it can determine the possible deployment problems of the front-end monitoring devices 101 by combining the location information of each front-end monitoring device 101, generate the corresponding inspection results, and upload them to the management platform device 103. When a problem is found, the management platform device 103 can promptly push the information to the management user terminal 104 so that the personnel holding the management user terminal 104 can arrange for inspection in a timely manner and deal with the problem as soon as possible.

[0060] In specific implementation, the monitoring equipment management device 102 and the management platform device 103 can be separate and independent devices, or they can be different functional parts deployed on the same physical server, or the monitoring equipment management device 102 and the management platform device 103 can be on the same server. This application embodiment does not limit the specific deployment method.

[0061] The front-end monitoring device 101, the monitoring device management device 102, the management platform device 103, and the management user terminal 104 can communicate directly or indirectly through one or more networks 105. The network 105 can be a wired network or a wireless network. For example, the wireless network can be a mobile cellular network or a Wireless-Fidelity (WIFI) network, or other possible networks. This application embodiment does not limit this.

[0062] It should be noted that in this embodiment of the application, the number of front-end monitoring devices 101 can be one or more, and similarly, the number of management platform devices 103 can also be one or more. That is to say, there is no limit to the number of front-end monitoring devices 101 or management platform devices 103.

[0063] like Figure 2 The diagram shown illustrates another application scenario provided by an embodiment of this application. In this scenario, a multi-level cascaded management platform device is included. Figure 2 Taking Level 2 as an example, multiple lower-level management platform devices 21 are cascaded to the upper-level management platform device 20. Each lower-level management platform device 21 manages multiple front-end monitoring devices, and the video streams from these front-end monitoring devices are aggregated into the upper-level management platform device 20. In practical applications, the lower-level management platform device 21 can be, for example, a district-level management platform device, and the upper-level management platform device 20 can also be a district-level management platform device; alternatively, the lower-level management platform device 21 can be devices belonging to management platforms of different administrative departments, such as fire departments or other administrative departments, while the upper-level management platform device 20 is the device of the superior department that oversees these departments.

[0064] The front-end monitoring device management method of this application embodiment can be executed by any management platform device, for example, it can be executed by... Figure 2 It can be executed by either the lower-level management platform device 21 or the upper-level management platform device 20 shown.

[0065] In practical applications, since multi-level front-end monitoring devices can connect to different lower-level management platform devices 21, the same front-end monitoring device may exist multiple times in the upper-level management platform device 20, thus consuming the resources of the upper-level management platform device 20 and resulting in resource waste. Therefore, based on the front-end monitoring device management method of this application embodiment, during inspection, identical front-end monitoring devices can be detected, and they can be merged and optimized in the upper-level management platform device 20, reducing the multiple resource occupancy of the same front-end monitoring device and reducing resource waste.

[0066] Of course, the methods provided in the embodiments of this application are not limited to... Figure 1 or Figure 2 The application scenarios shown can also be used in other possible scenarios, and this application embodiment does not impose any limitations. Figure 1 or Figure 2 The functions that each device in the application scenario shown can achieve will be described in subsequent method embodiments, and will not be elaborated on here.

[0067] Please see Figure 3This is a flowchart illustrating a front-end monitoring device management method provided in various embodiments of this application. The method can... Figure 1 or Figure 2 The front-end monitoring device management device 101 in the process executes the method, and the process is described below.

[0068] Step 301: Based on the pre-set monitoring equipment inspection strategy, determine the multiple front-end monitoring devices to be inspected in this inspection.

[0069] In this embodiment of the application, the monitoring equipment inspection strategy can be pre-set, which includes information such as inspection time, cycle and inspection objects.

[0070] For example, there are two front-end monitoring devices at location A: one is the main monitoring device and the other is the backup monitoring device. Since the monitoring scenarios of these two front-end monitoring devices are the same, in order to avoid errors during inspection, one of the front-end monitoring devices can be selected as the inspection object. For example, the main monitoring device can be set as the inspection object.

[0071] Furthermore, when the inspection time arrives, multiple front-end monitoring devices, i.e. multiple inspection targets, can be identified for this inspection.

[0072] Step 302: Obtain the monitoring images captured by each front-end monitoring device. The time between the capture time of each monitoring image and the current time shall not exceed the set time threshold.

[0073] In this embodiment of the application, for the multiple front-end monitoring devices in this inspection, the monitoring images recently captured by each front-end monitoring device can be obtained, and then the subsequent inspection process can be continued based on the monitoring images.

[0074] Here, "recent" means that the time between the capture time of the surveillance image and the current time does not exceed a set time threshold. Generally speaking, surveillance images captured by multiple front-end monitoring devices at the same time can be selected. Of course, it should be noted that the same time does not mean exactly the same. It can mean that the time difference is within a certain range. For example, surveillance images captured within a 10-second time difference can be considered as captured at the same time.

[0075] Specifically, the video stream captured by the front-end monitoring equipment can be stored on a corresponding data server, for example... Figure 1 The management platform device shown can therefore obtain monitoring images from various front-end monitoring devices from the data server.

[0076] Step 303: Determine whether the scene similarity between any two monitoring images is greater than the set first scene similarity threshold.

[0077] In this embodiment of the application, in order to solve the problem of resource waste caused by multiple front-end monitoring devices monitoring a single monitoring scene, similarity detection can be performed on the monitoring images taken by each front-end monitoring device during the inspection to determine whether their monitoring scenes are the same, thereby assisting in the formulation of subsequent improvement measures.

[0078] Since the similarity determination process for any two surveillance images is similar, this section will specifically use the similarity determination process for two surveillance images as an example, namely, surveillance image 1 taken by front-end monitoring device A and surveillance image 2 taken by front-end monitoring device B.

[0079] Specifically, scene features can be extracted from each of the multiple surveillance images to obtain scene feature information for each image. For surveillance image 1 and surveillance image 2, scene feature extraction yields scene feature information for both images. This information is then compared to determine the scene similarity between surveillance image 1 and surveillance image 2, which in turn determines whether the scene similarity exceeds a predefined first scene similarity threshold.

[0080] In the process of scene feature extraction, each monitoring image can be processed into grayscale before a pre-trained feature extraction model is used. This feature extraction model can be implemented using deep learning neural network models such as Convolutional Neural Networks (CNNs).

[0081] In this embodiment of the application, in addition to obtaining a monitoring image for each front-end monitoring device, a monitoring video can also be obtained for each front-end monitoring device, and then scene feature extraction can be performed based on the monitoring video to obtain scene feature information. Based on the obtained scene feature information, the similarity between the monitoring scenes of each two front-end monitoring devices can be determined.

[0082] Step 304: If the scene similarity is greater than the first scene similarity threshold, then determine whether the location information of the front-end monitoring device corresponding to the scene similarity-related monitoring image is consistent.

[0083] In this embodiment of the application, if the determination result of step 303 is yes, that is, when the scene similarity between every two monitoring images is greater than the first scene similarity threshold, then it is determined whether the location information of the two front-end monitoring devices corresponding to every two monitoring images is consistent.

[0084] Using the example of monitoring image 1 and monitoring image 2 above, if the scene similarity between monitoring image 1 and monitoring image 2 is greater than the first scene similarity threshold, the location information of the corresponding front-end monitoring device A and front-end monitoring device B can be obtained, thereby determining whether the location information of front-end monitoring device A and front-end monitoring device B are consistent.

[0085] Among them, the surveillance images with similar scenes refer to another surveillance image used to calculate similarity, such as surveillance image 1 and surveillance image 2 of the cedar tree.

[0086] Step 305: If the location information of the front-end monitoring devices is consistent, generate inspection results showing that the front-end monitoring devices are monitoring the same scene, and upload the inspection results to the management platform device.

[0087] In this embodiment of the application, if the determination result of step 304 is yes, that is, when the location information of the front-end monitoring device A and the front-end monitoring device B is consistent, it indicates that the front-end monitoring device A and the front-end monitoring device B are two front-end monitoring devices set in the same scene, and the content they monitor is the same. Thus, the inspection results of the front-end monitoring devices monitoring the same scene for each pair of monitoring images can be generated, and the inspection results can be uploaded to the management platform device.

[0088] Specifically, the identical monitoring scenarios of two front-end monitoring devices may be caused by the following reasons:

[0089] (1) Due to incorrect installation or subsequent adjustment of the front-end monitoring equipment, multiple front-end monitoring devices may capture the same scene. For example, when multiple cameras are installed on the same pole, incorrect adjustment may cause multiple cameras to capture the same direction.

[0090] (2) Due to external forces, the shooting direction of the front-end monitoring equipment changes, resulting in multiple front-end monitoring equipment shooting the same scene. For example, when multiple cameras are installed on the same pole, the shooting direction of the cameras may change due to strong winds, resulting in multiple cameras shooting in the same direction. Or the shooting direction of the cameras may be changed manually, resulting in multiple cameras shooting in the same direction.

[0091] (3) When multiple front-end monitoring devices that need to be inspected come from multiple cascaded lower-level platforms, multiple front-end monitoring devices from different lower-level platforms may be the same front-end monitoring device, resulting in the same monitoring scene. If the location information of two front-end monitoring devices is consistent, in addition to generating inspection results for each pair of monitoring images corresponding to the front-end monitoring devices monitoring the same scene, it can also determine whether the identifiers of the lower-level platforms from which the two front-end monitoring devices come are the same. If the identifiers of the lower-level platforms from which the two front-end monitoring devices come are different, then the information indicating that the front-end monitoring devices of the lower-level platforms have duplicate information is generated, and the duplicate front-end monitoring devices are merged and optimized.

[0092] Therefore, when multiple front-end monitoring devices are detected capturing the same scene, it is necessary to remind management personnel to verify the situation and resolve the issue of multiple front-end monitoring devices capturing the same scene in a timely manner, thereby reducing resource waste.

[0093] See Figure 4 The diagram shown is another flowchart illustrating the front-end monitoring device method provided in this application embodiment.

[0094] Step 401: Based on the pre-set monitoring equipment inspection strategy, determine the multiple front-end monitoring devices to be inspected in this inspection.

[0095] Step 402: Obtain the monitoring images captured by each front-end monitoring device.

[0096] Step 403: Determine whether the scene similarity between any two monitoring images is greater than the set first scene similarity threshold X.

[0097] It should be noted that the following examples will all use two surveillance images as examples. These two surveillance images can be any two images from a combination of N surveillance images.

[0098] Step 404: If the result of step 403 is yes, then obtain the location information of the front-end monitoring devices corresponding to the two monitoring images whose scene similarity is greater than the first scene similarity threshold.

[0099] Step 405: Determine whether the location information of the front-end monitoring devices is consistent.

[0100] That is, if the scene similarity of two surveillance images is greater than the set first scene similarity threshold X, then the location information of the front-end monitoring devices corresponding to these two surveillance images is obtained, and it is determined whether the location information of the two front-end monitoring devices corresponding to these two surveillance images is consistent.

[0101] Step 406: If the result of step 405 is yes, then generate inspection results showing that there are front-end monitoring devices monitoring the same scene.

[0102] Among them, steps 401 to 406 and Figure 3 The processing procedures in the illustrated embodiments are similar and therefore can be referred to. Figure 3 The descriptions of the corresponding parts in the illustrated embodiments will not be repeated here.

[0103] Step 407: If the result of step 405 is negative, then generate an inspection result showing that the front-end monitoring device is monitoring the same scene and the location information is incorrect.

[0104] If the location information of the two front-end monitoring devices corresponding to these two monitoring images is inconsistent, that is, two front-end monitoring devices that should be set in different locations have captured two monitoring images of the same scene, it means that the location information of one of the front-end monitoring devices is incorrect. This results in an inspection result showing that the location information of one of the front-end monitoring devices corresponding to these two monitoring images has been entered incorrectly. After the management personnel learn of this inspection result, they can check on-site whether there is a corresponding problem and make improvements.

[0105] Step 408: If the result of step 403 is negative, then determine whether the scene similarity between the two monitoring images is greater than the set second scene similarity threshold Y.

[0106] Wherein, the second scene similarity threshold Y is less than the first scene similarity threshold X. Both the first scene similarity threshold X and the second scene similarity threshold Y are values ​​set by the user. For example, the first scene similarity threshold can be set to 98% and the second scene similarity threshold can be set to 95%. Of course, other values ​​that meet the conditions can also be set. This application embodiment does not limit this.

[0107] Step 409: If the result of step 408 is yes, then check whether there is a human face in the two surveillance images.

[0108] In other words, when scene feature information is insufficient to prove that two surveillance images are of the same scene, the faces appearing in the scene can be used to help determine whether they are of the same scene. Since the above N surveillance images were taken at almost the same time, if the same face appears in the scene, it is sufficient to prove that the two surveillance images are of the same scene.

[0109] Step 410: If both surveillance images contain human faces, extract facial feature information from each image and perform feature comparison.

[0110] Specifically, when face detection is performed on both surveillance images and faces are detected in both images, facial feature information can be extracted separately. When multiple faces are present in the surveillance images, facial feature information can be extracted for each face. Then, during feature comparison, a one-to-one (1V1) comparison can be performed between the faces in the two surveillance images. That is, each face in surveillance image A is compared with each face in surveillance image B to determine if there are two faces whose facial similarity exceeds a facial similarity threshold Z.

[0111] Step 411: Determine whether the facial similarity between the two surveillance images is greater than the facial similarity threshold Z.

[0112] Specifically, facial feature information corresponding to every two surveillance images is extracted and compared to determine whether the facial similarity between the two images is greater than a set facial similarity threshold Z. The facial similarity threshold can be set according to the user's specific needs, for example, it can be set to 95%, or other possible values; this embodiment does not limit this.

[0113] In practical applications, if the result of step 411 is that the facial similarity between the two surveillance images is greater than the set facial similarity threshold Z, then it indicates that the two surveillance images belong to the same scene, and then the process jumps to step 405 to continue execution.

[0114] If the result of step 411 is negative, that is, the face similarity is not greater than the face similarity threshold Z, then it is determined that the two surveillance images belong to different scenes.

[0115] In summary, this application embodiment addresses situations where a large number of front-end monitoring devices exist. It involves inspecting these devices to determine if multiple cameras are capturing the same scene due to installation or post-installation errors. For example, multiple cameras mounted on a single pole may consistently capture the same scene due to external force or human intervention, or there may be errors in location information input during initial construction, or the possibility of multiple front-end devices on a single pole. Furthermore, it addresses scenarios where multi-level front-end monitoring platforms are cascaded to a higher-level platform. If the same front-end monitoring device exists on different platforms, the cascading process may result in the same device appearing multiple times on the higher-level platform. This application embodiment obtains scene images, extracts features, and performs feature comparison to identify suspected cases of multiple front-end monitoring devices capturing the same scene. This information is then alerted to the administrator, integrating data resources within the system to achieve "one source of data" and resolving the resource waste caused by multiple front-end monitoring devices in a single scene.

[0116] Please see Figure 5Based on the same inventive concept, embodiments of this application also provide a front-end monitoring device management device 50, which includes:

[0117] The strategy determination unit 501 is used to determine multiple front-end monitoring devices to be inspected in this inspection based on a pre-set monitoring device inspection strategy.

[0118] Image acquisition unit 502 is used to acquire monitoring images captured by each front-end monitoring device. The time between the capture time of each monitoring image and the current time does not exceed a set time threshold.

[0119] The inspection judgment unit 503 is used to determine whether the scene similarity between any two monitoring images is greater than the set first scene similarity threshold; if the scene similarity is greater than the first scene similarity threshold, it determines whether the location information of the front-end monitoring devices corresponding to the similarity-related monitoring images is consistent; if the location information of the front-end monitoring devices is consistent, it generates an inspection result for the front-end monitoring devices monitoring the same scene.

[0120] The sending unit 504 is used to upload the inspection results to the management platform device.

[0121] Optionally, the device further includes a similarity determination unit 505, used for:

[0122] Scene features are extracted from each surveillance image to obtain scene feature information for each image.

[0123] Feature comparison is performed on the scene feature information of each pair of monitoring images to determine the scene similarity between each pair of monitoring images.

[0124] Optionally, the inspection judgment unit 503 is also used for:

[0125] If the scene similarity is not greater than the first scene similarity threshold, then determine whether the scene similarity is greater than the set second scene similarity threshold. The second scene similarity threshold is less than the first scene similarity threshold.

[0126] If the scene similarity is determined to be greater than the second scene similarity threshold, then based on the facial feature information in the surveillance images associated with scene similarity, it is determined whether the surveillance images belong to the same scene.

[0127] If it is determined that the surveillance images belong to the same scene, determine whether the location information of the front-end monitoring devices corresponding to the surveillance images is consistent;

[0128] If the location information of the front-end monitoring devices is consistent, the inspection results of the front-end monitoring devices monitoring the same scene are generated and uploaded to the management platform device.

[0129] Optionally, the inspection judgment unit 503 is specifically used for:

[0130] Perform face detection on the surveillance images separately;

[0131] If faces are detected in all the surveillance images, facial feature information is extracted from each of the surveillance images.

[0132] The facial feature information corresponding to the surveillance image is compared to determine whether the facial similarity of the surveillance image is greater than the set facial similarity threshold.

[0133] If the facial similarity is greater than the facial similarity threshold, then the surveillance images are determined to belong to the same scene; or,

[0134] If the facial similarity is not greater than the facial similarity threshold, then the surveillance images are determined to belong to different scenes.

[0135] Optionally, the inspection judgment unit 503 is also used to generate an inspection result indicating that the location information of one of the front-end monitoring devices is incorrectly entered if the location information of the front-end monitoring devices is determined to be inconsistent.

[0136] The sending unit 504 is also used to upload the inspection results to the management platform device.

[0137] Optionally, if N front-end monitoring devices originate from multiple cascaded lower-level platforms, then the inspection judgment unit 503 is also used for:

[0138] Determine whether the identifiers of the lower-level platforms from which the front-end monitoring devices originate are the same;

[0139] If the identifiers of the lower-level platforms from which the front-end monitoring devices originate are different, then duplicate indication information is generated indicating that the front-end monitoring devices of the lower-level platforms are duplicated, and the duplicate front-end monitoring devices are merged and optimized.

[0140] This device can be used to perform Figure 3 or Figure 4 The method shown in the illustrated embodiment is relevant here; therefore, the functions that each functional module of the device can achieve can be referred to. Figure 3 or Figure 4 The embodiments shown are described in detail below.

[0141] Please see Figure 6 Based on the same technical concept, this application also provides a computer device 60, which may include a memory 601 and a processor 602.

[0142] The memory 601 is used to store computer programs executed by the processor 602. The memory 601 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function, etc.; the data storage area may store data created based on the use of the computer device, etc. The processor 602 may be a central processing unit (CPU), or a digital processing unit, etc. This application embodiment does not limit the specific connection medium between the memory 601 and the processor 602. This application embodiment... Figure 6 The memory 601 and the processor 602 are connected via a bus 603, and the bus 603 is in Figure 6 The connections between other components are shown in bold and are for illustrative purposes only, not as limiting information. The bus 603 can be divided into address bus, data bus, control bus, etc. For ease of illustration, Figure 6 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0143] Memory 601 may be volatile memory, such as random-access memory (RAM); memory 601 may also be non-volatile memory, such as read-only memory, flash memory, hard disk drive (HDD), or solid-state drive (SSD); or memory 601 may be any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto. Memory 601 may be a combination of the above-described memories.

[0144] Processor 602 is configured to execute, when calling a computer program stored in memory 601, such as Figure 3 or Figure 4 The method performed by the device in the illustrated embodiment.

[0145] In some possible implementations, various aspects of the methods provided in this application can also be implemented as a program product comprising program code that, when run on a computer device, causes the computer device to perform the steps of the methods according to the various exemplary embodiments of this application described above. For example, the computer device may perform actions such as... Figure 3 or Figure 4 The method performed by the device in the illustrated embodiment.

[0146] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0147] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0148] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method of managing a front-end monitoring device, characterized by, The method comprises: determining a plurality of front-end monitoring devices for this time according to a preset monitoring device inspection strategy; acquiring monitoring pictures taken by each of the plurality of front-end monitoring devices, wherein a time difference between the time of taking each of the monitoring pictures and the current time is not more than a preset time threshold, and a time difference between the time of taking the monitoring pictures corresponding to the plurality of front-end monitoring devices is not more than a preset time threshold; for two front-end monitoring devices of the plurality of front-end monitoring devices, performing the following steps: determining whether the scene similarity of two monitoring pictures corresponding to the two front-end monitoring devices is greater than a preset first scene similarity threshold; if the scene similarity is not greater than the first scene similarity threshold, determining whether the scene similarity is greater than a preset second scene similarity threshold, wherein the second scene similarity threshold is less than the first scene similarity threshold; if it is determined that the scene similarity is greater than the second scene similarity threshold, performing face detection on the two monitoring pictures respectively; if it is detected that the two monitoring pictures both include faces, extracting face feature information from the two monitoring pictures respectively; performing feature comparison on the face feature information corresponding to the two monitoring pictures to determine whether the face similarity of the two monitoring pictures is greater than a preset face similarity threshold; if the face similarity is greater than the face similarity threshold, or if the scene similarity is greater than the first scene similarity threshold, determining whether the position information of the two front-end monitoring devices is consistent; if the position information of the two front-end monitoring devices is consistent, generating an inspection result that the two front-end monitoring devices monitor the same scene, and uploading the inspection result to a management platform device; determining whether the subordinate platform identifiers of the two front-end monitoring devices are the same; if the subordinate platform identifiers of the two front-end monitoring devices are different, generating indication information indicating that there are repeated front-end monitoring devices of the subordinate platform, and performing merging and optimization processing on the repeated front-end monitoring devices.

2. The method of claim 1, wherein, After acquiring the monitoring pictures taken by each of the plurality of front-end monitoring devices, the method further comprises: extracting scene feature information of each of the monitoring pictures respectively; performing feature comparison on the scene feature information of each two of the monitoring pictures to determine the scene similarity between each two of the monitoring pictures.

3. The method of claim 1, wherein, Further comprising: if the face similarity is not greater than the face similarity threshold, determining that the monitoring pictures belong to different scenes.

4. The method according to any one of claims 1 to 3, characterized in that After determining whether the position information of the two front-end monitoring devices corresponding to each two of the monitoring pictures is consistent, the method further comprises: if it is determined that the position information of the front-end monitoring devices is inconsistent, generating an inspection result that the position information of one of the front-end monitoring devices is inputted incorrectly, and uploading the inspection result to the management platform device.

5. A front-end monitoring device management apparatus characterized by comprising: The device comprises: a strategy determination unit configured to determine a plurality of front-end monitoring devices for this time according to a preset monitoring device inspection strategy; The picture acquisition unit is configured to acquire monitoring pictures captured by each of the plurality of front-end monitoring devices, wherein a time difference between a capturing time of each of the monitoring pictures and a current time is less than a preset time threshold, and a time difference between capturing times of the monitoring pictures corresponding to the plurality of front-end monitoring devices is less than the preset time threshold. The inspection determination unit is configured to determine, for two front-end monitoring devices of the plurality of front-end monitoring devices, whether a scene similarity of two monitoring pictures corresponding to the two front-end monitoring devices is greater than a preset first scene similarity threshold; if the scene similarity is not greater than the first scene similarity threshold, determine whether the scene similarity is greater than a preset second scene similarity threshold, the second scene similarity threshold being less than the first scene similarity threshold; if it is determined that the scene similarity is greater than the second scene similarity threshold, perform face detection on the two monitoring pictures respectively; if a face is detected in each of the two monitoring pictures, extract face feature information from the two monitoring pictures respectively; perform feature comparison on the face feature information corresponding to the two monitoring pictures, and determine whether a face similarity of the two monitoring pictures is greater than a preset face similarity threshold; if the face similarity is greater than the face similarity threshold, or if the scene similarity is greater than the first scene similarity threshold, determine whether position information of the two front-end monitoring devices corresponding to each of the two monitoring pictures is consistent; if the position information of the two front-end monitoring devices is consistent, generate an inspection result that the two front-end monitoring devices monitor a same scene; determine whether sub-platform identifiers of the two front-end monitoring devices are the same; if the sub-platform identifiers of the two front-end monitoring devices are different, generate indication information indicating that there is repetition of front-end monitoring devices of a sub-platform, and perform merging and optimization processing on the repeated front-end monitoring devices. The sending unit is configured to upload the inspection result to a management platform device. 6.A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: The processor executes the computer program to implement the steps of the method in any one of claims 1 to 4. 7.A computer storage medium having computer program instructions stored thereon, wherein: The computer program instructions are executed by a processor to implement the steps of the method in any one of claims 1 to 4.

8. A computer program product, characterised in that, The computer program product comprises computer instructions stored in a computer storage medium; a processor of a computer device reads the computer instructions from the computer storage medium and executes the computer instructions, so that the computer device performs the steps of the method in any one of claims 1 to 4.

Images