Abnormality determination method, device, electronic device and storage medium

Abstract

The present application discloses an abnormality determination method, device, electronic device and storage medium, and relates to the field of image analysis technology. The method includes: obtaining attribute information of an image sensor to be identified and a first image captured by the image sensor to be identified within a preset time period; obtaining preset information corresponding to the attribute information; wherein the preset information includes identification information of an image captured by a normal image sensor having the attribute information; and performing comparative analysis based on the identification information of the first image and the preset information to determine whether the image sensor to be identified is an abnormal image sensor. In the present application, the electronic device can reasonably determine whether the image sensor to be identified is an abnormal image sensor, and can improve the efficiency of determining abnormal image sensors.

Description

Technical Field

[0001] The present application relates to the field of image analysis technology, and in particular to an abnormality determination method, device, electronic device and storage medium. Background Art

[0002] When the current city-level video image monitoring system is running, monitoring contents in different areas and scenes can be obtained based on a series of image sensors included in the video image monitoring system.

[0003] However, these image sensors may be affected by external forces (such as typhoons) and cause abnormal conditions (such as deviation in the illumination direction). In this case, the operation and maintenance personnel need to conduct on-site inspections to confirm which image sensors have deviated in their illumination direction. However, the above-mentioned video image monitoring system may include tens of thousands of image sensors, so the inspection method may affect the efficiency of determining abnormal conditions, thereby affecting the monitoring effectiveness of the video image monitoring system. Summary of the invention

[0004] The present application provides an abnormality determination method, device, electronic device and storage medium, which solve the technical problem that the current method of determining whether there is an image sensor with a deviated irradiation direction through manual inspection affects the efficiency of abnormal situation determination.

[0005] The technical solution of the embodiment of the present application is as follows:

[0006] In a first aspect, a method for determining an abnormality is provided. The method may include: obtaining attribute information of an image sensor to be identified and a first image captured by the image sensor to be identified within a preset time period; obtaining preset information corresponding to the attribute information; wherein the preset information includes identification information of an image captured by a normal image sensor having the attribute information; and performing comparative analysis based on the identification information of the first image and the preset information to determine whether the image sensor to be identified is an abnormal image sensor.

[0007] In the present application, since the preset information corresponding to the attribute information of the image sensor to be identified may include (or represent) the identification information of the image captured by the image sensor in a normal state (for example, the category, quantity, position, etc. of the identification target included in the image in a normal state), the electronic device can determine whether the image sensor to be identified is in a normal state by comparing and analyzing the identification information of the first image with the identification information of the image captured by the image sensor in a normal state, that is, it can reasonably determine whether the image sensor to be identified is an abnormal image sensor, which can improve the efficiency of determining abnormal image sensors.

[0008] Optionally, the attribute information of the image sensor to be identified includes a target detection type of the image sensor to be identified; the obtaining of preset information corresponding to the attribute information specifically includes: obtaining first preset information corresponding to the target detection type; the comparative analysis based on the identification information of the first image and the preset information to determine whether the image sensor to be identified is an abnormal image sensor specifically includes: comparative analysis based on the identification information of the first image and the first preset information to determine whether the image sensor to be identified is an abnormal image sensor.

[0009] Optionally, the attribute information of the image sensor to be identified includes the target location type of the image sensor to be identified; the obtaining of the preset information corresponding to the attribute information specifically includes: obtaining second preset information corresponding to the target location type; the comparative analysis based on the identification information of the first image and the preset information to determine whether the image sensor to be identified is an abnormal image sensor specifically includes: comparative analysis based on the identification information of the first image and the second preset information to determine whether the image sensor to be identified is an abnormal image sensor.

[0010] Optionally, the above-mentioned preset information includes at least one of the target category of the recognition target contained in the image captured by the normal image sensor, the target number of the recognition targets of the same category, and the target position distribution of the recognition targets of the same category; the recognition target includes at least one of the background target and the foreground target in the image captured by the normal image sensor.

[0011] Optionally, the comparative analysis based on the identification information of the first image and the preset information to determine whether the image sensor to be identified is an abnormal image sensor specifically includes: determining a category of the identification target included in the first image; when the category of the identification target included in the first image does not belong to the target category, determining that the image sensor to be identified is an abnormal image sensor.

[0012] Optionally, the comparative analysis based on the identification information of the first image and the preset information to determine whether the image sensor to be identified is an abnormal image sensor specifically includes: determining the position information of each identification target of the same category included in the first image; determining the position distribution of the identification targets of the same category based on the position information of each identification target of the same category; when the difference between the position distribution and the target position distribution meets a preset condition, determining that the image sensor to be identified is an abnormal image sensor.

[0013] In a second aspect, an abnormality determination device is provided. The device may include: an acquisition module and a determination module; the acquisition module is used to acquire attribute information of an image sensor to be identified and a first image captured by the image sensor to be identified within a preset time period; the acquisition module is also used to acquire preset information corresponding to the attribute information; wherein the preset information includes identification information of an image captured by a normal image sensor having the attribute information; the determination module is used to perform comparative analysis based on the identification information of the first image and the preset information to determine whether the image sensor to be identified is an abnormal image sensor.

[0014] Optionally, the attribute information of the image sensor to be identified includes a target detection type of the image sensor to be identified; the acquisition module is specifically used to acquire first preset information corresponding to the target detection type; the determination module is specifically used to perform comparative analysis based on the identification information of the first image and the first preset information to determine whether the image sensor to be identified is an abnormal image sensor.

[0015] Optionally, the attribute information of the image sensor to be identified includes the target place type of the image sensor to be identified; the acquisition module is specifically used to acquire second preset information corresponding to the target place type; the determination module is specifically used to perform comparative analysis based on the identification information of the first image, the first preset information and the second preset information to determine whether the image sensor to be identified is an abnormal image sensor.

[0016] Optionally, the above-mentioned preset information includes at least one of the target category of the recognition target contained in the image captured by the normal image sensor, the target number of the recognition targets of the same category, and the target position distribution of the recognition targets of the same category; the recognition target includes at least one of the background target and the foreground target in the image captured by the normal image sensor.

[0017] Optionally, the determination module is specifically used to determine the category of the identification target included in the first image; the determination module is also specifically used to determine that the image sensor to be identified is an abnormal image sensor when the category of the identification target included in the first image does not belong to the target category.

[0018] Optionally, the determination module is specifically used to determine the position information of each identification target of the same category included in the first image; the determination module is also specifically used to determine the position distribution of the identification targets of the same category based on the position information of each identification target of the same category; the determination module is also specifically used to determine that the image sensor to be identified is an abnormal image sensor when the difference between the position distribution and the target position distribution meets a preset condition.

[0019] According to a third aspect, an electronic device is provided, which may include: a processor and a memory configured to store processor-executable instructions; wherein the processor is configured to execute the instructions to implement any one of the optional abnormality determination methods in the first aspect described above.

[0020] In a fourth aspect, a computer-readable storage medium is provided, on which instructions are stored. When the instructions in the computer-readable storage medium are executed by an electronic device, the electronic device is enabled to execute any one of the optional abnormality determination methods in the first aspect.

[0021] In a fifth aspect, a computer program product is provided, the computer program product comprising computer instructions, which, when executed on an electronic device, enable the electronic device to execute any one of the optional abnormality determination methods in the first aspect.

[0022] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A schematic diagram of the internal structure of an electronic device provided in an embodiment of the present application is shown;

[0024] Figure 2 A schematic diagram of a process for determining an abnormality provided by an embodiment of the present application is shown;

[0025] Figure 3 A schematic diagram showing a flow chart of another abnormality determination method provided in an embodiment of the present application is shown;

[0026] Figure 4 A schematic diagram showing a flow chart of another abnormality determination method provided in an embodiment of the present application is shown;

[0027] Figure 5 A schematic diagram showing a flow chart of another abnormality determination method provided in an embodiment of the present application is shown;

[0028] Figure 6 A schematic diagram showing a flow chart of another abnormality determination method provided in an embodiment of the present application is shown;

[0029] Figure 7 A schematic diagram showing a first image captured by the image sensor to be identified within a preset time period provided in an embodiment of the present application;

[0030] Figure 8 A schematic diagram showing an image captured by a normal image sensor provided by an embodiment of the present application within a preset time period;

[0031] Fig. 9A schematic diagram of the structure of an abnormality determination device provided in an embodiment of the present application is shown;

[0032] Fig.10 A schematic diagram of the structure of another abnormality determination device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0033] In order to enable ordinary persons in the art to better understand the technical 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 accompanying drawings.

[0034] 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. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the attached claims.

[0035] It should also be understood that the term “comprising” indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements and / or components.

[0036] As described in the background technology, since the video image monitoring system may include tens of thousands of image sensors, and the related technology will affect the efficiency of abnormal situation determination through manual inspection. Based on this, the embodiment of the present application provides an abnormality determination method. Since the preset information corresponding to the attribute information of the image sensor to be identified can include (or represent) the identification information of the image captured by the image sensor in a normal state (for example, the category, quantity, position, etc. of the identification target included in the image in a normal state), the electronic device can compare and analyze the identification information of the first image with the identification information of the image captured by the image sensor in a normal state, and can determine whether the image sensor to be identified is in a normal state, that is, it can reasonably determine whether the image sensor to be identified is an abnormal image sensor, which can improve the determination efficiency of abnormal image sensors.

[0037] The abnormality determination method, device, electronic device, and storage medium provided in the embodiments of the present application are applied to video image monitoring scenarios (specifically, scenarios that may include monitoring related identification targets). When the electronic device obtains the attribute information of the image sensor to be identified and the first image captured by the image sensor to be identified within a preset time period, it can determine whether the image sensor to be identified is an abnormal image sensor according to the method provided in the embodiments of the present application.

[0038] The following is an exemplary description of the abnormality determination method provided in the embodiment of the present application in conjunction with the accompanying drawings:

[0039] Exemplarily, the electronic device that executes the abnormality determination method provided in the embodiment of the present application can be a mobile phone, a tablet computer, a desktop, a laptop, a handheld computer, a notebook computer, an ultra-mobile personal computer (ultra-mobile personal computer, UMPC), a netbook, and a cellular phone, a personal digital assistant (personal digital assistant, PDA), an augmented reality (augmented reality, AR)\virtual reality (virtual reality, VR) device, etc., which can install and use the content community application. The present application does not impose any special restrictions on the specific form of the electronic device. It can interact with the user through one or more methods such as a keyboard, a touchpad, a touch screen, a remote control, voice interaction or a handwriting device.

[0040] like Figure 1 As shown, in one implementation, an electronic device that executes the abnormality determination method provided in an embodiment of the present application may include an input and output module, a data acquisition module, a content recognition module, and a difference analysis module.

[0041] Among them, the input and output module is used to input the analysis task created by the user account, and the analysis task may include the range of multiple image sensors to be analyzed (for example, including the identification information of the multiple image sensors to be analyzed, the location information of the multiple image sensors to be analyzed, the detection type of the multiple image sensors to be analyzed, or the location type of the multiple image sensors to be analyzed, etc.), and the analysis task is used to instruct the electronic device to determine whether there are abnormal image sensors among the multiple image sensors to be analyzed, and the number of abnormal image sensors. The analysis task may also include an analysis cycle, which is used to characterize the time interval for executing the analysis task, for example, executing the analysis task once every 24 hours.

[0042] The input-output module is also used to output an abnormality analysis report, which may include an identification of at least one image sensor, and the abnormality analysis report is used to characterize the at least one image sensor as an abnormal image sensor. The input-output module can also be understood as a human-computer interaction module in the electronic device.

[0043] The data acquisition module is used to acquire (or obtain) the images acquired by each of the multiple image sensors to be analyzed.

[0044] The content recognition module is used to recognize the recognition targets included in the images collected by the multiple image sensors to be analyzed. Specifically, the content recognition module can be used to recognize the category, quantity, location, etc. of the recognition targets.

[0045] The difference analysis module is used to analyze (or determine) the difference between the identification information of the images collected by the above-mentioned multiple image sensors to be analyzed and the identification information of the images collected by the normal image sensor. For example, the difference between the category of the identification target included in the first image and the target category of the identification target included in the image collected by the normal image sensor can be determined, and then the abnormal image sensor can be determined from the multiple image sensors to be analyzed.

[0046] like Figure 2 As shown, the abnormality determination method provided in the embodiment of the present application may include S101-S103.

[0047] S101: The electronic device obtains attribute information of an image sensor to be identified and a first image captured by the image sensor to be identified within a preset time period.

[0048] In one implementation of the embodiment of the present application, the video image monitoring system can store the attribute information of the image sensor to be identified and the first image captured by the image sensor to be identified within a preset time period, so that the electronic device can obtain the attribute information and the first image from the video image monitoring system. For the storage process of the first image in the video image monitoring system, after the image sensor to be identified captures the first image within the preset time period, the first image can be sent to the video image monitoring system, so that the video image monitoring system can receive and store the first image.

[0049] Optionally, the functions of the video image monitoring system can be integrated in a server, which can be an independent physical server, a server cluster or a 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 communications, middleware services, domain name services, security services, network acceleration services (content delivery network, CDN), as well as big data and artificial intelligence platforms.

[0050] It should be noted that the above-mentioned preset time period can be 1 day, 1 week or 1 month, etc., and the embodiment of the present application does not make any specific limitation.

[0051] Exemplarily, the image sensor in the embodiment of the present application may be a camera.

[0052] S102: The electronic device obtains preset information corresponding to the attribute information of the image sensor to be identified.

[0053] The preset information includes identification information of an image captured by a normal image sensor having the attribute information.

[0054] It should be understood that a normal image sensor is an image sensor in a normal state, and the normal state can be understood as the shooting direction of the image sensor is normal (for example, no offset occurs) or the position information of the image sensor is normal, etc. A normal image sensor having the attribute information means that the attribute information of the normal image sensor is the same as the attribute information of the image sensor to be identified.

[0055] It can be understood that the identification information of the image captured by the above-mentioned normal image sensor includes relevant information recognized based on the captured image, such as the category, quantity, position, etc. of the recognition target included in the captured image.

[0056] S103: The electronic device performs comparative analysis based on the identification information of the first image and preset information corresponding to the attribute information of the image sensor to be identified, and determines whether the image sensor to be identified is an abnormal image sensor.

[0057] It should be understood that the identification information of the first image includes relevant information identified based on the first image, such as the category, quantity, and location of the identification target included in the first image. Since the above-mentioned preset information may include the identification information of the image captured by the image sensor in a normal state (i.e., a normal image sensor), the electronic device can determine whether the image sensor to be identified is in a normal state, that is, determine whether the image sensor to be identified is an abnormal image sensor, by comparing and analyzing the identification information of the first image with the identification information of the image captured by the image sensor in a normal state.

[0058] In the technical solution provided in the embodiment of the present application, the electronic device can obtain the attribute information of the image sensor to be identified and the first image captured by the image sensor to be identified within a preset time period; then the electronic device obtains the preset information corresponding to the attribute information, and performs a comparative analysis based on the identification information of the first image and the preset information to determine whether the image sensor to be identified is an abnormal image sensor. In the embodiment of the present application, since the preset information can include (or characterize) the identification information of the image captured by the image sensor in a normal state (for example, the category, quantity, position, etc. of the identification target included in the image in a normal state), the electronic device can determine whether the image sensor to be identified is in a normal state by performing a comparative analysis based on the identification information of the first image and the identification information of the image captured by the image sensor in a normal state, that is, it can reasonably determine whether the image sensor to be identified is an abnormal image sensor, which can improve the efficiency of determining abnormal image sensors.

[0059] Combination Figure 2 ,like Figure 3 As shown, in one implementation of the embodiment of the present application, the attribute information of the image sensor to be identified includes the target detection type of the image sensor to be identified, and the preset information corresponding to the attribute information of the image sensor to be identified can specifically include S1021.

[0060] S1021. The electronic device obtains first preset information corresponding to the target detection type.

[0061] It should be understood that the detection type of an image sensor is used to characterize the type of identification target or the behavior type of the identification target that the image sensor can detect, etc. For example, the detection type of an image sensor can be a portrait recognition image sensor, a vehicle recognition image sensor, a shape recognition image sensor, a fire point recognition image sensor, or a water surface floating object monitoring image sensor, etc.

[0062] Continue as Figure 3 As shown, the above-mentioned comparison and analysis based on the recognition information of the first image and the preset information corresponding to the attribute information of the image sensor to be identified to determine whether the image sensor to be identified is an abnormal image sensor specifically includes S1031.

[0063] S1031: The electronic device determines whether the image sensor to be identified is an abnormal image sensor based on identification information of the first image and first preset information corresponding to the target detection type.

[0064] It is understandable that one detection type corresponds to one first preset information. In the embodiment of the present application, the electronic device can obtain the target detection type of the image sensor to be identified by obtaining the attribute information of the image sensor to be identified, and then the electronic device can obtain the first preset information corresponding to the target detection type. Since the first preset information may include the identification information of the image captured by a normal image sensor with the target detection type, that is, the first preset information includes the identification information of the image captured by the image sensor with the same detection type as the image sensor to be identified under normal conditions, the electronic device can compare and analyze the identification information of the first image with the identification information of the image captured by the image sensor with the target detection type under normal conditions, and can quickly and effectively determine whether the image sensor to be identified is an abnormal image sensor.

[0065] Combination Figure 2 ,like Figure 4 As shown, in one implementation of the embodiment of the present application, the attribute information of the image sensor to be identified includes the target location type of the image sensor to be identified, and the preset information corresponding to the attribute information of the image sensor to be identified may specifically include S1022.

[0066] S1022: The electronic device obtains second preset information corresponding to the target place type.

[0067] It should be understood that the location type of an image sensor is the type of location where the image sensor is located, or the type of location photographed by the image sensor. The location type may be a shopping mall, a park, a residential area, or a gymnasium.

[0068] In an optional implementation, a preset correspondence may be stored in the electronic device, and the preset correspondence includes multiple place types and second preset information corresponding to each of the multiple place types. After acquiring the target place type of the image sensor to be identified, the electronic device may determine and acquire the second preset information corresponding to the target place type based on the target place type and the preset correspondence.

[0069] Continue as Figure 4 As shown, the above-mentioned comparison and analysis based on the recognition information of the first image and the preset information corresponding to the attribute information of the image sensor to be identified to determine whether the image sensor to be identified is an abnormal image sensor specifically includes S1032.

[0070] S1032: The electronic device performs comparative analysis based on the identification information of the first image and the second preset information corresponding to the target location type to determine whether the image sensor to be identified is an abnormal image sensor.

[0071] It is understandable that one place type corresponds to one second preset information. In the embodiment of the present application, the electronic device can obtain the target place type of the image sensor to be identified by obtaining the attribute information of the image sensor to be identified, and then the electronic device can obtain the second preset information corresponding to the target place type. Since the second preset information may include the identification information of the image captured by a normal image sensor with the target place type, that is, the second preset information includes the identification information of the image captured by the image sensor with the same place type as the image sensor to be identified in a normal state, the electronic device can compare and analyze the identification information of the first image with the identification information of the image captured by the image sensor with the target place type in a normal state, and can quickly and effectively determine whether the image sensor to be identified is an abnormal image sensor.

[0072] In one implementation of the embodiments of the present application, the preset information corresponding to the attribute information of the above-mentioned image sensor to be identified includes at least one of the target category of the identification target contained in the image captured by the normal image sensor with the attribute information, the target number of the identification targets of the same category, and the target position distribution of the identification targets of the same category; the identification target includes at least one of the background target and the foreground target in the image captured by the normal image sensor.

[0073] It should be understood that the foreground target in an image is used to represent the main object in the image, such as a person or a car; and the background target in the image is used to represent other objects in the image, such as a road, a tree, and the sky.

[0074] In an embodiment of the present application, the electronic device may perform a comparative analysis based on the recognition information of the above-mentioned first image (for example, the category of the recognition target included in the first image, the number of recognition targets of the same category included in the first image, and the recognition targets of the same category included in the first image) and at least one of the target category of the recognition targets contained in the image captured by the normal image sensor, the target number of recognition targets of the same category, and the target position distribution of recognition targets of the same category, so as to determine whether the image sensor to be identified is an abnormal image sensor.

[0075] Optionally, the attribute information of an image sensor may further include the name of the image sensor and the location information of the image sensor, etc. The location information is used to represent the installation location of the image sensor.

[0076] Combination Figure 2 ,like Figure 5As shown, in one implementation of the embodiment of the present application, the comparative analysis of the recognition information based on the first image and the preset information corresponding to the attribute information of the image sensor to be identified to determine whether the image sensor to be identified is an abnormal image sensor may specifically include S1033-S1034.

[0077] S1033: The electronic device determines a category of the recognition target included in the first image.

[0078] In one case, the electronic device may perform image recognition processing on the first image to identify the recognition target included in the first image and determine the category of the recognition target included in the first image. In another case, the category of the recognition target included in the first image may also be input into the electronic device after manual review.

[0079] In combination with the description of the above embodiment, it should be understood that since the identified target includes the foreground target and the background target in the image captured by the above normal image sensor, the electronic device can determine the category of the foreground target included in the first image and the category of the background target included in the first image.

[0080] S1034: When the category of the recognition target included in the first image does not belong to the target category of the recognition target included in the image acquired by the normal image sensor, the electronic device determines that the image sensor to be recognized is an abnormal image sensor.

[0081] In combination with the description of the above embodiment, it should be understood that the normal image sensor is an image sensor that has the attribute information of the image sensor to be identified and is in a normal state. The target category of the identification target included in the image captured by the normal image sensor is used to characterize the category of the identification target that should be included in the image captured by the image sensor with the attribute information in a normal state.

[0082] It can be understood that when the category of the identification target included in the first image does not belong to the target category, it means that the category of the identification target included in the first image is the category of the identification target included in the image captured by the image sensor with the attribute information in an abnormal state. It can also be understood that the first image is an image captured by the image sensor to be identified in an abnormal state. In this way, the electronic device can determine that the image sensor to be identified is an abnormal image sensor.

[0083] In one case, due to an abnormal state of the image sensor to be identified (for example, the shooting direction of the image sensor to be identified is offset), the image sensor to be identified may be unable to capture a normal image, that is, it may be unable to capture an image whose category of the identification target belongs to the above-mentioned target category. At this time, the electronic device can determine that the image sensor to be identified is an abnormal image sensor, and the image captured by the image sensor to be identified (for example, the first image) is an abnormal image.

[0084] In an optional implementation, when the target detection type of the image to be identified is a portrait recognition image sensor, the target categories may include: face, portrait, road, tree, and building, etc.; when the target detection type of the image to be identified is a vehicle recognition image sensor, the target categories may include: motor vehicle, non-motor vehicle, pedestrian, and road, etc.

[0085] Exemplarily, assuming that the categories of the identification targets included in the first image include clouds and sky, and the target categories include faces, portraits, roads and trees, the electronic device determines that the image sensor to be identified is an abnormal image sensor.

[0086] Optionally, when the category of the identification target included in the first image belongs to the target category, the electronic device may determine that the image sensor to be identified is a normal image sensor.

[0087] In another implementation of the embodiment of the present application, after determining the category of the identification target included in the first image as described above, the abnormality determination method provided by the embodiment of the present application may further include step A.

[0088] Step A: When the difference between the category of the identification target included in the first image and the target category of the identification target included in the image captured by the normal image sensor is greater than or equal to a first difference threshold, the electronic device determines that the image sensor to be identified is an abnormal image sensor.

[0089] It should be understood that when the difference between the category of the identified target included in the first image and the target category of the identified target included in the image captured by the normal image sensor is greater than or equal to the first difference threshold, it means that the difference between the category of the identified target included in the first image and the category of the identified target included in the image captured by the image sensor with the attribute information under normal conditions (i.e., the target category) is large. It can also be understood that the first image is an image captured by the image sensor to be identified under abnormal conditions. In this way, the electronic device can determine that the image sensor to be identified is an abnormal image sensor.

[0090] Optionally, when the difference between the category of the identification target included in the first image and the target category is smaller than the first difference threshold, the electronic device may determine that the image sensor to be identified is a normal image sensor.

[0091] In an implementation of the embodiment of the present application, the comparative analysis based on the recognition information of the first image and the preset information corresponding to the attribute information of the image sensor to be identified to determine whether the image sensor to be identified is an abnormal image sensor may specifically include steps B to C.

[0092] Step B: The electronic device determines the number of recognition targets of the same category included in the first image.

[0093] It should be noted that the explanation of the electronic device determining the number of recognition targets of the same category included in the first image is the same or similar to the above-mentioned process of determining the category of the recognition targets included in the first image, and will not be repeated here.

[0094] It should be understood that the electronic device can determine the category of each recognition target included in the first image, and then determine the number of recognition targets of the same category.

[0095] Step C: When the difference between the number of recognition targets of the same category included in the first image and the number of recognition targets of the same category included in the image captured by the normal image sensor is greater than or equal to a second difference threshold, the electronic device determines that the image sensor to be identified is an abnormal image sensor.

[0096] In combination with the description of the above embodiment, it should be understood that the normal image sensor is an image sensor that has the attribute information of the image sensor to be identified and is in a normal state. The number of identification targets of the same category included in the image captured by the normal image sensor is used to characterize the number of identification targets of the same category that should be included in the image captured by the image sensor with the attribute information in a normal state.

[0097] It can be understood that when the difference between the number of recognition targets of the same category included in the first image and the number of targets is greater than or equal to the second difference threshold, it means that the difference between the number of recognition targets of the same category included in the first image and the number of recognition targets of the same category included in the image captured by the image sensor with the attribute information under normal conditions (i.e., the number of targets) is large. It can also be understood that the first image is an image captured by the image sensor to be identified under abnormal conditions. In this way, the electronic device can determine that the image sensor to be identified is an abnormal image sensor.

[0098] In an optional implementation, the electronic device may represent the difference between the number of recognition targets of the same category included in the first image and the number of targets by the difference between the number of recognition targets of the same category included in the first image and the number of targets.

[0099] Optionally, when the difference between the number of identification targets of the same category included in the first image and the number of targets is less than the second difference threshold, the electronic device determines that the image sensor to be identified is a normal image sensor.

[0100] Combination Figure 2 ,like Figure 6 As shown, in one implementation of an embodiment of the present application, the comparative analysis of the recognition information based on the first image and the preset information corresponding to the attribute information of the image sensor to be identified to determine whether the image sensor to be identified is an abnormal image sensor may specifically include S1035-S1037.

[0101] S1035: The electronic device determines position information of each recognition target of the same category included in the first image.

[0102] Optionally, the electronic device may represent the location information of each recognition target of the same category in the form of coordinates.

[0103] S1036: The electronic device determines the position distribution of the recognition targets of the same category included in the first image according to the position information of each recognition target of the same category included in the first image.

[0104] In an optional implementation, the electronic device may divide each acquired image (e.g., the first image) into multiple regions of the same or different sizes. The electronic device determines the position distribution of the recognition targets of the same category included in the first image, which can be understood as determining the distribution of the recognition targets of the same category included in the first image in the multiple regions, such as in which region of the multiple regions each recognition target of the same category included in the first image is located, or what is the proportion of each region of the multiple regions of the recognition targets of the same category included in the first image, etc.

[0105] S1037. When the difference between the position distribution of the same category of recognition targets included in the first image and the target position distribution of the same category of recognition targets included in the image captured by the normal image sensor meets a preset condition, the electronic device determines that the image sensor to be identified is an abnormal image sensor.

[0106] It should be understood that the target position distribution is used to characterize the target position distribution of the same category of recognition targets that should be included in the image captured by the image sensor with the attribute information of the image sensor to be recognized in a normal state. When the difference between the position distribution of the same category of recognition targets included in the first image and the target position distribution meets the preset conditions, it means that the position distribution of the same category of recognition targets included in the first image and the position distribution of the same category of recognition targets included in the image captured by the image sensor with the attribute information in a normal state (i.e., the target position distribution) are significantly different, and it can also be understood that the first image is an image captured by the image sensor to be recognized in an abnormal state, so that the electronic device can determine that the image sensor to be recognized is an abnormal image sensor.

[0107] In one case, the target position distribution may indicate that the recognition targets of the same category included in the image captured by the normal image sensor are located in each of the multiple areas, and S1037 may specifically include step D.

[0108] Step D: When each recognition target of the same category included in the first image is located in a preset area, the electronic device determines that the image sensor to be recognized is an abnormal image sensor.

[0109] The preset area is one of the multiple areas.

[0110] It should be understood that since the target position distribution is used to characterize that the recognition targets of the same category included in the image captured by the normal image sensor are located in each of the multiple areas, that is, the recognition targets of the same category exist in each of the multiple areas. When each recognition target of the same category included in the first image is located in a preset area, it means that the recognition targets of the same category included in the first image only exist in one of the multiple areas, and the other areas (areas other than the preset area in the multiple areas) do not include the recognition targets of the same category. At this time, the electronic device can determine that the image sensor to be identified is an abnormal image sensor.

[0111] In another case, the target position distribution may also represent the target proportion of the same category of identified targets in each of the multiple regions included in the image captured by the normal image sensor. The above S1037 may specifically include step E.

[0112] Step E: When the proportion of the identification targets of the same category included in the first image in each area is different from the target proportion, the electronic device determines that the image sensor to be identified is an abnormal image sensor.

[0113] It should be understood that the proportion of the same category of recognition targets included in the first image in each area includes the ratio between the number of the same category of recognition targets included in the first image in each area and the number of the same category of recognition targets included in the first image; the target proportion includes the ratio between the number of the same category of recognition targets included in each area of ​​the image acquired by the normal image sensor and the number of the same category of recognition targets included in the image acquired by the normal image sensor. When the proportion of the same category of recognition targets included in each area of ​​the first image is different from the target proportion, it means that the position distribution of the same category of recognition targets included in the first image is significantly different from the above-mentioned target position distribution, that is, the electronic device determines that the image sensor to be identified is an abnormal image sensor.

[0114] For example, Figure 7 As shown, an example of a first image captured by an image sensor to be identified and obtained by an electronic device within a preset time period. Specifically, the first image includes two areas, namely, a wall area and a rest area. The wall area does not include an identification target, and the rest area includes two identification targets. The electronic device can determine that the identification target included in the first image accounts for 0% in the wall area and 100% in the rest area.

[0115] like Figure 8 As shown, it is an example of an image captured by a normal image sensor within a preset time period. Specifically, the image includes three areas, namely, a wall area, a rest area, and a motion area. The wall area does not include a recognition target, the rest area includes two recognition targets, and the motion area includes three recognition targets. The electronic device can determine that the recognition targets included in the image account for 0% in the wall area, 40% in the rest area, and 60% in the motion area.

[0116] Thus, the electronic device determines that the proportion of the identification targets of the same category included in the first image in each area is different from the above-mentioned target proportion, and the electronic device determines that the image sensor to be identified is an abnormal image sensor.

[0117] Specifically, from the above Figure 7 , Figure 8 Analysis shows that the image sensor to be identified may have an abnormal shooting direction (specifically, the shooting direction is offset to the left), causing the image sensor to be identified to capture the first image that only includes the wall area and the rest area.

[0118] Optionally, when the difference between the position distribution of the identification targets of the same category included in the first image and the target position distribution does not meet a preset condition, the electronic device may determine that the image sensor to be identified is a normal image sensor.

[0119] In an optional implementation, the abnormality determination method provided in the embodiment of the present application may also include steps F to H.

[0120] Step F: The electronic device acquires a plurality of images captured by each of the plurality of normal image sensors within a preset time period.

[0121] The plurality of normal image sensors are image sensors that have attribute information of the image sensors to be identified and are in a normal state.

[0122] It should be understood that the normal state may be that the shooting direction of the image sensor is normal (for example, no offset occurs) or the position information of the image sensor is normal. A normal image sensor may also be understood as an image sensor that can capture normal images, and the above-mentioned multiple images are normal images captured by the multiple normal image sensors within the preset time period.

[0123] Optionally, the detection type of the multiple normal image sensors is the above-mentioned target detection type, and / or the location type of the multiple normal image sensors is the above-mentioned target location type.

[0124] Step G: The electronic device determines the category of the identification target included in each of the multiple images.

[0125] Step H: The electronic device determines the category of the identification target included in each of the multiple images as the above target category.

[0126] In another optional implementation, the electronic device may also determine the number of recognition targets of the same category included in each of the multiple images, and determine the above target number based on the number of recognition targets of the same category included in each of the multiple images.

[0127] In another optional implementation, the electronic device may also determine the position distribution of the recognition targets of the same category included in each of the multiple images, and determine the above-mentioned target position distribution based on the position distribution of the recognition targets of the same category included in each of the multiple images.

[0128] It is understandable that, in actual implementation, the electronic device described in the embodiment of the present application may include one or more hardware structures and / or software modules for implementing the aforementioned corresponding abnormal determination method, and these execution hardware structures and / or software modules may constitute an electronic device. It should be easily appreciated by those skilled in the art that, in conjunction with the algorithm steps of each example described in the embodiment applied for herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present application.

[0129] Based on this understanding, the embodiment of the present application also provides an abnormality determination device. Fig. 9 FIG. 2 shows a schematic diagram of the structure of an abnormality determination device provided in an embodiment of the present application. Fig. 9 As shown, the abnormality determination device 10 may include: an acquisition module 101 and a determination module 102 .

[0130] The acquisition module 101 is used to acquire attribute information of the image sensor to be identified and a first image captured by the image sensor to be identified within a preset time period.

[0131] The acquisition module 101 is further used to acquire preset information corresponding to the attribute information; wherein the preset information includes identification information of an image captured by a normal image sensor having the attribute information.

[0132] The determination module 102 is configured to perform a comparative analysis based on the identification information of the first image and the preset information to determine whether the image sensor to be identified is an abnormal image sensor.

[0133] Optionally, the attribute information of the image sensor to be identified includes a target detection type of the image sensor to be identified.

[0134] The acquisition module 101 is specifically configured to acquire first preset information corresponding to the target detection type.

[0135] The determination module 102 is specifically configured to perform a comparative analysis based on the identification information of the first image and the first preset information to determine whether the image sensor to be identified is an abnormal image sensor.

[0136] Optionally, the attribute information of the image sensor to be identified includes a target location type of the image sensor to be identified.

[0137] The acquisition module 101 is specifically configured to acquire second preset information corresponding to the target location type.

[0138] The determination module 102 is specifically configured to perform comparative analysis based on the identification information of the first image, the first preset information, and the second preset information to determine whether the image sensor to be identified is an abnormal image sensor.

[0139] Optionally, the above-mentioned preset information includes at least one of the target category of the recognition target contained in the image captured by the normal image sensor, the target number of the recognition targets of the same category, and the target position distribution of the recognition targets of the same category; the recognition target includes at least one of the background target and the foreground target in the image captured by the normal image sensor.

[0140] Optionally, the determination module 102 is specifically configured to determine a category of a recognition target included in the first image.

[0141] The determination module 102 is further configured to determine that the image sensor to be identified is an abnormal image sensor when the category of the identification target included in the first image does not belong to the target category.

[0142] Optionally, the determination module 102 is specifically configured to determine the position information of each recognition target of the same category included in the first image.

[0143] The determination module 102 is further specifically configured to determine the position distribution of the recognition targets of the same category according to the position information of each recognition target of the same category.

[0144] The determination module 102 is further specifically configured to determine that the image sensor to be identified is an abnormal image sensor when the difference between the position distribution and the target position distribution meets a preset condition.

[0145] As described above, the embodiment of the present application can divide the functional modules of the abnormal determination device according to the above method example. Among them, the above integrated modules can be implemented in the form of hardware or in the form of software functional modules. In addition, it should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. For example, each functional module can be divided corresponding to each function, or two or more functions can be integrated in one processing module.

[0146] Regarding the abnormality determination device in the above embodiment, the specific manner in which each module performs operations and the beneficial effects possessed have been described in detail in the above method embodiment and will not be repeated here.

[0147] Fig.10 is a schematic diagram of the structure of another abnormality determination device provided by the present application. Fig.10The abnormality determination device 20 may include at least one processor 201 and a memory 203 for storing processor executable instructions. The processor 201 is configured to execute instructions in the memory 203 to implement the abnormality determination method in the above embodiment.

[0148] In addition, the abnormality determination device 20 may further include a communication bus 202 and at least one communication interface 204 .

[0149] The processor 201 may be a central processing unit (CPU), a microprocessing unit, an ASIC, or one or more integrated circuits for controlling the execution of the program of the present application.

[0150] The communication bus 202 may include a pathway for transmitting information between the above-mentioned components.

[0151] The communication interface 204 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0152] The memory 203 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory may exist independently and be connected to the processing unit through a bus. The memory may also be integrated with the processing unit.

[0153] The memory 203 is used to store instructions for executing the solution of the present application, and the execution is controlled by the processor 201. The processor 201 is used to execute the instructions stored in the memory 203, so as to realize the functions in the method of the present application.

[0154] In a specific implementation, as an embodiment, the processor 201 may include one or more CPUs, such as Fig.10 CPU0 and CPU1 in.

[0155] In a specific implementation, as an embodiment, the abnormality determination device 20 may include multiple processors, such as Fig.10 201 and processor 207 in the embodiment of the present invention. Each of these processors may be a single-CPU processor or a multi-CPU processor. The processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0156] In a specific implementation, as an embodiment, the abnormality determination device 20 may also include an output device 205 and an input device 206. The output device 205 communicates with the processor 201 and can display information in a variety of ways. For example, the output device 205 may be a liquid crystal display (LCD), a light emitting diode (LED) display device, a cathode ray tube (CRT) display device, or a projector. The input device 206 communicates with the processor 201 and can accept user input in a variety of ways. For example, the input device 206 may be a mouse, a keyboard, a touch screen device, or a sensor device.

[0157] Those skilled in the art will understand that Fig.10 The structure shown in the figure does not constitute a limitation on the abnormality determination device 20, and may include more or less components than those shown in the figure, or combine certain components, or adopt a different component arrangement.

[0158] In addition, the present application also provides a computer-readable storage medium, including instructions, which, when executed by an electronic device, enable the electronic device to execute the abnormality determination method provided in the above embodiment.

[0159] In addition, the present application also provides a computer program product, including instructions, which, when executed by an electronic device, enable the electronic device to execute the abnormality determination method provided in the above embodiment.

[0160] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the claims.

Claims

1. A method for determining an abnormality, characterized in that: include: Acquire attribute information of an image sensor to be identified and a first image captured by the image sensor to be identified within a preset time period; Acquire preset information corresponding to the attribute information; wherein the preset information includes identification information of an image acquired by a normal image sensor having the attribute information; Performing comparative analysis based on the identification information of the first image and the preset information to determine whether the image sensor to be identified is an abnormal image sensor; The preset information includes at least one of a target category of a recognition target contained in an image acquired by the normal image sensor and a target position distribution of recognition targets of the same category; wherein the recognition target includes at least one of a background target and a foreground target in an image acquired by the normal image sensor; The comparing and analyzing the identification information based on the first image and the preset information to determine whether the image sensor to be identified is an abnormal image sensor includes: determining a category of a recognition target included in the first image; when the category of the recognition target included in the first image does not belong to the target category, determining that the image sensor to be recognized is an abnormal image sensor; or, Determine the position information of each recognition target of the same category included in the first image; determine the position distribution of the recognition targets of the same category based on the position information of each recognition target of the same category; when the difference between the position distribution and the target position distribution meets a preset condition, determine that the image sensor to be recognized is an abnormal image sensor.

2. The abnormality determination method according to claim 1, characterized in that: The attribute information of the image sensor to be identified includes the target detection type of the image sensor to be identified; The obtaining of preset information corresponding to the attribute information includes: obtaining first preset information corresponding to the target detection type; The comparing and analyzing the identification information based on the first image and the preset information to determine whether the image sensor to be identified is an abnormal image sensor includes: comparing and analyzing the identification information based on the first image and the first preset information to determine whether the image sensor to be identified is an abnormal image sensor.

3. The abnormality determination method according to claim 1, characterized in that: The attribute information of the image sensor to be identified includes the target location type of the image sensor to be identified; The obtaining of preset information corresponding to the attribute information includes: obtaining second preset information corresponding to the target place type; The comparing and analyzing the identification information based on the first image and the preset information to determine whether the image sensor to be identified is an abnormal image sensor includes: comparing and analyzing the identification information based on the first image and the second preset information to determine whether the image sensor to be identified is an abnormal image sensor.

4. The abnormality determination method according to any one of claims 1 to 3, characterized in that: The preset information also includes the number of targets of the same category contained in the image captured by the normal image sensor.

5. An abnormality determination device, characterized in that: include: Get module and determine module; The acquisition module is used to acquire the attribute information of the image sensor to be identified and the first image captured by the image sensor to be identified within a preset time period; The acquisition module is further used to acquire preset information corresponding to the attribute information; wherein the preset information includes identification information of an image acquired by a normal image sensor having the attribute information; The determination module is used to perform comparative analysis based on the identification information of the first image and the preset information to determine whether the image sensor to be identified is an abnormal image sensor; The preset information includes at least one of a target category of the recognition target contained in the image acquired by the normal image sensor and a target position distribution of the recognition targets of the same category; the recognition target includes at least one of a background target and a foreground target in the image acquired by the normal image sensor; The determination module is specifically configured to determine the category of the recognition target included in the first image; The determination module is further configured to determine that the image sensor to be identified is an abnormal image sensor when the category of the identification target included in the first image does not belong to the target category; The determination module is specifically used to determine the position information of each recognition target of the same category included in the first image; The determination module is further configured to determine the position distribution of the recognition targets of the same category according to the position information of each recognition target of the same category; The determination module is further specifically configured to determine that the image sensor to be identified is an abnormal image sensor when the difference between the position distribution and the target position distribution meets a preset condition.

6. The abnormality determination device according to claim 5, characterized in that: The attribute information of the image sensor to be identified includes the target detection type of the image sensor to be identified; The acquisition module is specifically used to acquire first preset information corresponding to the target detection type; The determination module is specifically configured to perform comparative analysis based on the identification information of the first image and the first preset information to determine whether the image sensor to be identified is an abnormal image sensor; The attribute information of the image sensor to be identified includes the target location type of the image sensor to be identified; The acquisition module is specifically used to acquire second preset information corresponding to the target place type; The determination module is specifically configured to perform comparative analysis based on the identification information of the first image and the second preset information to determine whether the image sensor to be identified is an abnormal image sensor; The preset information also includes the number of targets of the same category contained in the image captured by the normal image sensor.

7. An electronic device, characterized in that: The electronic device comprises: processor; a memory configured to store instructions executable by the processor; The processor is configured to execute the instructions to implement the abnormality determination method according to any one of claims 1 to 4.

8. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions in the computer-readable storage medium are executed by an electronic device, the electronic device is enabled to execute the abnormality determination method according to any one of claims 1 to 4.

Images