Adaptive capture method, device, equipment and storage medium

Abstract

The present application provides an adaptive capture method, device, equipment and storage medium, which relates to the field of security technology and can optimize the computing resources and operating power consumption of a composite capture machine. The method includes: identifying the object type to which the capture target in the picture taken by the capture machine belongs; wherein the capture machine has the ability to identify at least two object types; comparing the identified object type and the preset object type, and determining whether to turn off the capture machine's ability to identify at least one object type based on the comparison result; wherein the preset object type is the object type that the capture machine can identify. The present application can be used in the process of security.

Description

Technical Field

[0001] The present application relates to the field of security technology, and in particular to an adaptive capture method, device, equipment and storage medium. Background Art

[0002] With the development of image recognition and image processing technology, snapshot machines with automatic target recognition capabilities are gradually being used in various security scenarios. In addition, in order to increase the range of identifiable objects, there is currently a composite snapshot machine that can simultaneously recognize faces, bodies, motor vehicles, non-motor vehicles, gait, etc., further improving the security effect.

[0003] After being powered on, traditional composite capture machines will simultaneously enable the recognition function of all types of objects to achieve the recognition of various types of targets and ensure the security effect in all aspects. However, in actual application environments, only certain types of objects pass through a certain capture point, such as only motor vehicles. In this case, if all types of recognition functions are turned on, it will cause a huge waste of computing resources and high operating power consumption for the composite capture machine, which is likely to affect the life of the device. Summary of the invention

[0004] The present application provides an adaptive capture method, device, equipment and storage medium, which can optimize the computing resources and operating power consumption of a composite capture machine.

[0005] In a first aspect, the present application provides an adaptive capture method, the method comprising: identifying the object type to which the capture target in a picture taken by a capture machine belongs; wherein the capture machine has the ability to identify at least two object types; comparing the identified object type and a preset object type, and determining whether to turn off the capture machine's ability to identify at least one object type based on the comparison result; wherein the preset object type is an object type that the capture machine can identify.

[0006] The adaptive capture method provided in the embodiment of the present application identifies the object type of the captured target in the picture taken by the capture machine, compares the identified object type with the preset object type, and determines whether to turn off the capture machine's recognition function for certain object types based on the comparison result. This avoids unnecessary function operation from occupying computing resources and operating power consumption, realizes adaptive optimization and adjustment, and improves the service life of the device.

[0007] In one possible implementation, the identified object type is compared with a preset object type, and based on the comparison result, it is determined whether to shut down the capture machine's ability to recognize at least one object type, including: comparing the identified object type with the preset object type, determining a first object type among the preset object types that has not been recognized by the capture machine; and shutting down the capture machine's ability to recognize the first object type.

[0008] In another possible implementation, the identified object type and the preset object type are compared, and based on the comparison result, it is determined whether to shut down the recognition capability of the capture machine for at least one object type. The method also includes: for any object type among the identified object types, determining the number of capture targets belonging to the object type identified within a preset period; when the number meets the first preset condition, shutting down the capture machine's ability to recognize the object type.

[0009] In another possible implementation, the identified object type and the preset object type are compared, and based on the comparison result, it is determined whether to shut down the recognition capability of the capture machine for at least one object type, which also includes: determining the number of capture targets corresponding to each object type in the identified object type within a preset period; comparing the number of capture targets corresponding to each object type, and based on the comparison result, determining whether to shut down the recognition capability of the capture machine for at least one object type.

[0010] In another possible implementation, the number of capture targets corresponding to each object type is compared, and based on the comparison result, it is determined whether to shut down the capture machine's ability to recognize at least one object type, including: determining the difference between the number of capture targets belonging to the second object type and the number of capture targets belonging to the third object type, wherein the number of capture targets belonging to the second object type is less than the number of capture targets belonging to the third object type; if the difference meets a second preset condition, shutting down the capture machine's ability to recognize the second object type.

[0011] In another possible implementation, the method further includes: reporting the object types that can be identified by the capture machine and are not turned off to the server, so that the server can establish a capture machine directory according to the object type.

[0012] In a second aspect, the present application provides an adaptive capture device, which includes: an identification module and a determination module; the identification module is used to identify the object type to which the capture target in the picture taken by the capture machine belongs; wherein the capture machine has the ability to identify at least two object types; the determination module is used to compare the identified object type and the preset object type, and determine whether to turn off the capture machine's ability to recognize at least one object type based on the comparison result; wherein the preset object type is the object type that the capture machine can recognize.

[0013] In a possible implementation, the determination module is specifically used to compare the identified object type and the preset object type, determine the first object type among the preset object types that has not been identified by the capture machine, and disable the capture machine's ability to identify the first object type.

[0014] In another possible implementation, the determination module is specifically used to determine, for any object type among the identified object types, the number of captured targets belonging to the object type identified within a preset period; when the number meets the first preset condition, the ability of the capture machine to identify the object type is turned off.

[0015] In another possible implementation, the determination module is specifically used to determine the number of capture targets corresponding to each object type in the identified object types within a preset period; compare the number of capture targets corresponding to each object type, and determine whether to turn off the recognition capability of at least one object type of the capture machine based on the comparison result.

[0016] In another possible implementation, the determination module is specifically used to determine the difference between the number of snapshot targets belonging to the second object type and the number of snapshot targets belonging to the third object type, wherein the number of snapshot targets belonging to the second object type is less than the number of snapshot targets belonging to the third object type; if the difference meets the second preset condition, the ability of the snapshot machine to identify the second object type is turned off.

[0017] In another possible implementation, the determination module is specifically used to report the object types that can be identified by the capture machine that is not turned off to the server, so that the server can establish a capture machine directory according to the object type.

[0018] In a third aspect, the present application provides an electronic device, comprising: a processor and a memory; the memory stores instructions executable by the processor; when the processor is configured to execute the instructions, the electronic device implements the method of the first aspect above.

[0019] In a fourth aspect, the present application provides a computer-readable storage medium, which includes: computer software instructions; when the computer software instructions are executed in a computer, the computer implements the method of the first aspect.

[0020] In a fifth aspect, the present application provides a computer program product. When the computer program product is run on a computer, it enables the computer to execute the steps of the related method described in the first aspect above to implement the method of the first aspect above.

[0021] The beneficial effects of the second to fifth aspects mentioned above can be referred to the corresponding description of the first aspect and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A schematic diagram of an application environment of an adaptive capture method provided in this application;

[0023] Figure 2 A flowchart of an adaptive capture method provided in this application;

[0024] Figure 3 A flowchart of a method for determining whether to turn off the recognition capability provided by the present application;

[0025] Figure 4 A flowchart of another method for determining whether to turn off the recognition capability provided by the present application;

[0026] Figure 5 A flowchart of another method for determining whether to turn off the recognition capability provided by the present application;

[0027] Figure 6 A flowchart of another adaptive capture method provided by this application;

[0028] Figure 7 A schematic diagram of the process of constructing a structured information database provided by the present application;

[0029] Figure 8 A flowchart of a search and query method provided in this application;

[0030] Fig. 9 A schematic diagram of a system architecture provided for this application;

[0031] Fig.10 A schematic diagram of the composition of an adaptive capture device provided in this application;

[0032] Fig.11 A schematic diagram of the composition of an electronic device provided in this application. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0034] It should be noted that, in the embodiments of the present application, words such as "exemplarily" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplarily" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplarily" or "for example" is intended to present related concepts in a specific way.

[0035] In order to facilitate the clear description of the technical solutions of the embodiments of the present application, in the embodiments of the present application, the words "first", "second", etc. are used to distinguish the same items or similar items with basically the same functions and effects. Those skilled in the art can understand that the words "first", "second", etc. are not limiting the quantity and execution order.

[0036] To facilitate understanding of the technical solution of the present application, the terms involved in the present application are briefly explained below.

[0037] 1. Composite camera: a smart camera that has both picture taking and image processing functions. The image processing function can simultaneously identify multiple types of objects.

[0038] 2. Structured information: refers to information that can be decomposed into multiple interrelated components after analysis. Each component has a clear hierarchical structure and is generally used to represent further detailed information such as the attribute characteristics of a certain thing.

[0039] As described in the background technology, the traditional composite capture machine will turn on the automatic recognition function of all types of objects at the same time after power-on, which is easy to cause waste of computing resources and high operating power consumption in actual situations, and easily affect the life of the equipment. In the actual application process, on-site staff are required to perform on-site configuration according to the actual scene conditions and turn off unnecessary functions. At the same time, they are also required to manually label the capture machine with types to facilitate subsequent data retrieval. The entire configuration process requires a large amount of manpower costs. In addition, for ordinary capture machines, the pictures they take will be sent to the server for image recognition. If various types of objects are recognized, it will also take up too much computing power resources of the server.

[0040] To sum up, how to optimize computing resources and operating power consumption is an urgent problem that needs to be solved.

[0041] Based on this, the embodiment of the present application provides an adaptive capture method, which identifies the object type of the captured target in the picture taken by the capture machine, compares the identified object type with the preset object type, and determines whether to turn off the capture machine's recognition function for certain object types based on the comparison result. This avoids unnecessary function operation occupying computing resources and operating power consumption, realizes adaptive optimization and adjustment, and improves the service life of the equipment.

[0042] The adaptive capture method provided by this application can be applied to Figure 1 In the application environment shown. Figure 1 As shown, the application environment may include: a plurality of capture machines 101 and an adaptive capture device 102. The server 102 is connected to the plurality of capture machines 101 respectively.

[0043] The adaptive capture device 102 can be applied to a server. The server mentioned here can be a server cluster composed of multiple servers, or a single server, or a computer. The adaptive capture device 102 can specifically be a processor or a processing chip in the server. The embodiment of the present application does not limit the specific device form of the above-mentioned server. Figure 1 In the figure, the adaptive capturing device 102 is applied to a single computer as an example.

[0044] It should be noted that the above description is based on the example that the capture machine and the adaptive capture device are different devices. In other scenarios, the capture machine and the adaptive capture device can be the same device, that is, the capture machine is a composite capture machine with an intelligent processing module, and the composite capture machine has both the shooting function of a camera and the image processing function of a processing device, and the image processing function can recognize information such as faces, bodies, motor vehicles, non-motor vehicles, gait, etc. in the picture. This application does not limit the specific form of the capture machine.

[0045] When it is necessary to perform security protection on a target scene, multiple capture cameras can be set up at different points of the target scene. For example, N capture cameras, where N is greater than or equal to 1. One capture camera is corresponding to capturing a picture of one point in the target scene. The N capture cameras cooperate with each other to achieve security protection on the target scene. The target scene can be an underground garage, a shopping mall, a factory, and other scenes that require security protection.

[0046] It should be noted that for each of the N capture machines, the steps for implementing the adaptive capture method of the embodiment of the present application are consistent. The adaptive capture method provided by the present application is described in detail below using any one of the N capture machines as an example.

[0047] Figure 2 The following is a flow chart of an adaptive snapshot method provided in an embodiment of the present application. For example, the adaptive snapshot method provided in the present application can be applied to Figure 1 In the application environment shown.

[0048] like Figure 2 As shown, the adaptive capture method provided by the present application may specifically include the following steps:

[0049] S201: Identify the object type to which the captured target in the picture taken by the capture device belongs.

[0050] Among them, the capture machine has the ability to recognize at least two types of objects.

[0051] In some embodiments, the capture machine can periodically capture pictures of its field of view. The field of view is the maximum field of view that the capture machine can observe. The picture of the capture machine's field of view reflects the surrounding environment information of the point in the target scene corresponding to the capture machine. There may be multiple capture targets in the picture, such as motor vehicles, people, etc. For ordinary capture machines, the pictures they capture will be sent to the adaptive capture device, which can identify the object type to which the capture target belongs in the picture. For a composite capture machine, it can identify the object type to which the target in the picture it captures belongs.

[0052] Exemplarily, each recognition function can be implemented through a deep learning algorithm. Specifically, the motor vehicle recognition function is taken as an example. First, a large number of pictures including motor vehicles are collected, and the recognition model is repeatedly trained through a deep learning algorithm. When the recognition model converges, the training can be considered completed, and the trained recognition model is stored (in a server or a composite capture machine). After capturing the picture, the adaptive capture device can input the picture into the trained recognition model to obtain the recognition result of the motor vehicle object in the picture. Similarly, for the non-motor vehicle recognition function and the person recognition function, the implementation method is the same as the above-mentioned motor vehicle recognition function, and will not be repeated here.

[0053] S202: Compare the identified object type with the preset object type, and determine whether to disable the recognition capability of at least one object type of the capture device according to the comparison result.

[0054] The preset object type is an object type that can be recognized by the capture machine.

[0055] In some embodiments, after determining the object type to which the target in the image belongs, the adaptive capture device can compare the object type identified in the image with the preset object type, and determine whether to turn off the recognition capability of at least one object type of the capture device according to the comparison result. Exemplarily, the preset object type may include: human face, human face, gait, motor vehicle, non-motor vehicle, etc.

[0056] It should be noted that, for a composite capture machine, turning off a certain recognition capability means directly turning off the function, for example, a composite capture machine directly turns off the recognition capability of a motor vehicle. For an ordinary capture machine, its image recognition function is implemented in the server, so turning off the recognition capability of a certain capture machine (such as capture machine A) for a certain object type (such as a motor vehicle) means that the server does not recognize the type of motor vehicle for the image from capture machine A, so as to reduce the waste of computing resources.

[0057] In one possible implementation, Figure 3Comparing the identified object type with the preset object type, and determining whether to disable the recognition capability of at least one object type of the capture machine according to the comparison result, includes the following steps S202a-S202b.

[0058] S202a, comparing the identified object type with the preset object type, and determining a first object type among the preset object types that has not been identified by the capture device.

[0059] S202b, turning off the ability of the capture machine to recognize the first object type.

[0060] In some embodiments, the adaptive capture device may compare the identified object type with the preset object type, determine a first object type among the preset object types that is not recognized by the capture machine, and then disable the capture machine's ability to recognize the first object type.

[0061] Exemplarily, the adaptive capture device can identify multiple pictures taken by the capture machine within a preset period to determine the object type to which the target in the picture belongs. Among them, the selection of multiple pictures can be all pictures taken by the capture machine during this period, or multiple pictures selected according to certain rules (for example, every two pictures are selected once). The embodiment of the present application does not limit the specific selection method. Further, the selected pictures are identified to determine the identifiable object type, and compared with the preset object type, it is determined that the object type that has not been recognized by the capture machine in the preset object type is the first object type, and then the first object type is closed. Among them, the preset period can be set to different durations according to the actual scene requirements, such as one week or one month.

[0062] For example, for the capture device A, within the preset period, the object types it recognizes are motor vehicles and non-motor vehicles, and compared with the preset object types, it does not recognize faces, bodies, and gaits. Therefore, the adaptive capture device turns off the recognition functions of faces, bodies, and gaits.

[0063] It should be noted that the above process of using various recognition functions to determine the type of object to which the target in the picture belongs can be performed in each capture cycle, that is, the capture machine captures a picture and performs recognition once. It can also be performed uniformly after accumulating multiple pictures over a period of time. The embodiments of the present application do not impose specific restrictions on this.

[0064] In another possible implementation, Figure 4 As shown, comparing the identified object type and the preset object type, and determining whether to turn off the recognition capability of at least one object type of the capture machine according to the comparison result, includes the following steps S202c-S202d.

[0065] S202c: For any object type among the identified object types, determine the number of captured targets belonging to the object type identified within a preset period.

[0066] In some embodiments, the adaptive capture device can count each time a target of any object type among the identified object types is identified, thereby determining the number of capture targets of the object type identified within a preset period.

[0067] Exemplarily, the number of captured targets belonging to an object type can be represented by the count value of the object type. For a certain picture, the adaptive capture device recognizes an object type from the picture, and adds M to the count value of the object type. Among them, M is a fixed threshold or the number of targets of an object type included in the picture. The count value corresponding to the type to which an object belongs is the number of captured targets of the object type, which can be used to indicate the frequency of occurrence of targets of this type at the current capture machine point.

[0068] In simple terms, if the image 1 is identified, and three objects are identified in the image 1, such as motor vehicle 1, non-motor vehicle 1, and non-motor vehicle 2, then the adaptive capture device performs an operation of adding 1 to the count value of the motor vehicle object type. Therefore, for the image 1, if two non-motor vehicles are identified, then the count value of the motor vehicle object type needs to be added 2.

[0069] S202d: When the number meets the first preset condition, the ability of the capture machine to identify the object type is turned off.

[0070] In some embodiments, after a preset period ends, if the number of a certain object type meets a first preset condition, the ability of the capture machine to identify the object type is turned off.

[0071] Exemplarily, the first preset condition is that the number is less than the preset number threshold. For example, the preset number threshold is set to 10, and after the preset period ends, the number of face object types is 300 and the number of human body object types is 200. However, the number of non-motor vehicle object types is only 8, which is less than the preset number threshold 10, so it is determined that the number of non-motor vehicles passing by the capture camera is small, so the ability to identify non-motor vehicle object types is turned off to save computing resources.

[0072] As another example, the first preset condition is that the frequency of the object type is less than the preset frequency threshold. The frequency of the object type can be determined based on the ratio between the number of object types and the preset period. For example, the preset period is set to 10 days, and the preset frequency threshold is set to 10 times / day. During these ten days, the number of motor vehicle object types identified is 98, and the corresponding frequency is 9.8 times / day, which is less than the preset frequency threshold. Therefore, the adaptive capture device can turn off the ability to identify motor vehicle object types.

[0073] It should be noted that the above Figure 3 and Figure 4 The two methods shown in the figure determine whether to disable the recognition capability of the capture machine for at least one object type based on the comparison results, and can be applied separately in a certain scenario. Figure 3 For the steps shown, to determine whether the recognition capability is turned off, it is necessary to see which object type has never been recognized within a preset period. Figure 4 For the steps shown in the figure, to determine whether the recognition capability is turned off, it is determined by looking at which object type is recognized less frequently within a preset period, i.e., turned off. Figure 3 and Figure 4 The possible implementation methods shown can also be combined and applied in certain scenarios. Figure 3 In the implementation shown, if the adaptive capture device determines that the object type is a face, a body, a motor vehicle, or a gait, the recognition capability of the capture device for non-motor vehicles is turned off. Figure 4 In the implementation shown, the adaptive capture device determines that the number of face object types is small, and then turns off the recognition capability of recognizing faces.

[0074] In another possible implementation, Figure 5 As shown, the identified object type and the preset object type are compared, and it is determined whether to turn off the recognition capability of at least one object type of the capture machine according to the comparison result, and the following steps S202e-S202f are also included.

[0075] S202e: Determine the number of captured targets corresponding to each object type in the identified object types within a preset period.

[0076] In some embodiments, the adaptive capture device can determine the number of capture targets corresponding to each object type in the object type that can be identified within a preset period. The specific determination method can refer to the above Figure 4 The description of the corresponding embodiments will not be repeated here.

[0077] S202f, comparing the number of capture targets corresponding to each object type, and determining whether to disable the recognition capability of at least one object type of the capture machine according to the comparison result.

[0078] In some embodiments, after determining the number of capture targets corresponding to each object type, the adaptive capture device can compare the number of capture targets corresponding to each object type to determine whether to turn off the recognition capability of at least one object type of the capture machine according to the comparison result.

[0079] In a possible implementation, S202f specifically includes the following steps ab:

[0080] a. Determine a difference between the number of captured objects belonging to the second object type and the number of captured objects belonging to the third object type.

[0081] The number of captured targets belonging to the second object type is less than the number of captured targets belonging to the third object type.

[0082] In some embodiments, the adaptive capture device can determine the difference between the number of capture targets belonging to the second object type and the number of capture targets belonging to the third object type, so as to subsequently determine whether to turn off the recognition function for the second object. The second object type and the third object type are any object type in the preset object type except the turned-off first object type, and the number of capture targets belonging to the second object type is less than the number of capture targets belonging to the third object type.

[0083] b. If the difference satisfies a second preset condition, the ability of the capture device to identify the second object type is disabled.

[0084] In some embodiments, if the difference satisfies a second preset condition, the ability to identify the second object type is turned off. Exemplarily, the second preset condition is that the difference is greater than a preset difference threshold. For example, the preset difference threshold is set to 100, the number corresponding to the motor vehicle object type is 13, the number corresponding to the non-motor vehicle object type is 58, and the number corresponding to the face object type is 200. Then the corresponding difference between the motor vehicle object type and the non-motor vehicle object type is 45, and the corresponding difference between the motor vehicle object type and the face object type is 187, which is greater than the preset difference threshold of 100, then the ability to identify the motor vehicle object type is turned off. Similarly, for the comparison of other object types, refer to the above process, which will not be repeated here.

[0085] In another exemplary embodiment, the ratio between the number of captured targets of the second object type and the difference is less than the preset ratio threshold under the second preset condition. For example, the above example is used for explanation. The preset ratio threshold is set to 0.01. Taking the difference between the motor vehicle object type and the face object type as 187 as an example, the ratio between the number and the difference corresponding to the motor vehicle object type is approximately 0.07, which is less than the preset ratio threshold of 0.1, and the recognition capability of the second object type, i.e., the motor vehicle object type, is turned off.

[0086] In another possible implementation, 202f specifically includes the following steps cd:

[0087] c. Determine the average value between the number of captured targets corresponding to each object type.

[0088] d. If the number and average value of the captured targets of the fourth object type meet the third preset condition, the ability of the capture machine to identify the third object type is turned off.

[0089] In some embodiments, the average value is determined based on the sum of the number of each object type within a preset period. Further, based on the relationship between the number of the fourth object type and the average value, it is determined whether the third preset condition is met, and if so, the ability of the capture device to identify the third object type is turned off.

[0090] Exemplarily, the third preset condition is that the difference between the number of captured targets belonging to the fourth object type and the average value is greater than the threshold. It can be understood that if the difference is too large, it means that the number corresponding to the fourth object type is small, and the recognition capability of the fourth object type can be turned off to save computing power and optimize resources. Another exemplary example is that the third threshold condition is that the ratio between the number of captured targets of the fourth object type and the average value is too small, which also means that the number of targets belonging to this object type appearing at the current capture machine point is small, and the recognition capability of the fourth object type can be turned off.

[0091] In addition, after turning off the recognition of certain object types, such as Figure 6 As shown, the adaptive capture device can also perform the following S203.

[0092] S203: Report the object types that can be identified by the capture machine that is not turned off to the server, so that the server can establish a capture machine directory according to the object type.

[0093] In some embodiments, the adaptive capture device can also be connected to a server (also called a retrieval application server), and can report to the server the object types that the capture machine is not turned off and can identify, for example, the reported type label indicates the correspondence between the capture machine and the identifiable object type, so that the server can establish a capture machine directory based on these object types. It should also be noted that if the capture machine is a composite capture machine, the capture machine can be directly connected to the server to report data.

[0094] For example, for capture machine A, if the object types it can identify are motor vehicles, non-motor vehicles and human faces. For capture machine B, if the object types it can identify are motor vehicles and human faces. Then the adaptive capture device reports the recognizable object types of capture machines A and B to the server, and the server can establish a capture machine directory based on these object types. For example, there are identifiers of capture machines A and B under the motor vehicle type and the face type, so that when it is convenient to query the image data of a certain object type, it can be further screened based on the identifier of the capture machine to improve the retrieval efficiency.

[0095] In addition, the adaptive capture device of this solution can also extract structured information to build a database to meet the user's information query needs. Figure 7 As shown, it specifically includes the following S701-S702.

[0096] S701: extract structured information of a target of identifiable object type and send it to a server.

[0097] In some embodiments, for each of the N capture machines, the adaptive capture device can use a deep learning algorithm to extract structured information of targets of identifiable object types in the pictures taken by the capture machine and send it to the server.

[0098] Specifically, when the object type is a motor vehicle, the corresponding structured information includes one or more of the following: a small image of a motor vehicle license plate, a large background image, a motor vehicle license plate number, a motor vehicle body color, a motor vehicle brand, and a passing speed. When the object type is a non-motor vehicle, the corresponding structured information includes one or more of the following: a small image of a non-motor vehicle, a large background image, a non-motor vehicle license plate number, a non-motor vehicle body color, and whether there is a rearview mirror. When the object type is a face, the corresponding structured information includes one or more of the following: a small image of a face, a large background image, gender, age, whether wearing glasses, and whether smiling. When the second type is a human body, the corresponding structured information includes one or more of the following: a small image of a human body, a large background image, a top color, a bottom color, and a shoe color. When the object type is a gait, the corresponding structured information includes one or more of the following: a gait human body cover image and a gait snapshot sequence. It can be understood that the recognition of a person can be realized by combining the three features of face, human body, and gait to further improve the accuracy of person recognition. In addition, obtaining structured information for faces, bodies, and gaits separately can meet the diverse needs of users, adapt to information retrieval needs in various scenarios, and improve the user experience.

[0099] S702. The server builds a structured information database based on the structured information.

[0100] In some embodiments, the server can use the structured information to construct a structured information library based on the structured information sent by the N connected capture machines, wherein the structured information library includes preset object types, directory information of different capture machines under each object type, and corresponding structured information.

[0101] It can be understood that the server can obtain different types of structured information based on the front-end capture machine, build resource pools of motor vehicles, non-motor vehicles, faces, etc., to facilitate users to retrieve and query information according to their own needs. Figure 8 As shown, the server specifically executes the following S801-S802.

[0102] S801. The server obtains the type to be searched.

[0103] The types to be searched include any of the following: face, body, gait, motor vehicle, and non-motor vehicle.

[0104] In some embodiments, when structured information retrieval is required, the user can directly operate the application retrieval server to operate, or access the application retrieval server through a terminal device such as a mobile phone to operate, so as to initiate a retrieval request including the type to be retrieved. The embodiment of the present application does not limit this specific implementation method. Further, the server can receive the retrieval request and obtain the type to be retrieved.

[0105] S802: The server queries the structured information database based on the type to be retrieved, and displays the structured information of the type to be retrieved extracted by the target capture machine.

[0106] The target capture machine is one or more capture machines among the N capture machines connected to the server, which have object type labels corresponding to the type to be retrieved.

[0107] In some embodiments, after obtaining the type to be retrieved, the server can query the pre-established structured information library according to the type to be retrieved, and then display the identification information of the target capture machine. That is, the server displays the identification information of the target capture machine so that the user can determine which capture machines correspond to the points where the target type to be retrieved will appear. Furthermore, the server displays the structured information of the type to be retrieved collected by the target capture machine, so that the user can more clearly understand the various attribute parameters of the type to be retrieved and meet the user's information retrieval needs.

[0108] For example, the target scene is provided with capture devices 1 to 5, and each capture device is responsible for a point in the target scene. If the user wants to retrieve relevant information about a person, he or she can query by operating the server. The server obtains the type of "face" to be retrieved, and based on the "face" type, determines that capture devices 1 and 5 have labels of the "face" object type, that is, they are the target capture devices. Furthermore, the structured information of the target belonging to the "face" type collected by capture devices 1 and 5 is displayed, so that the user can retrieve and analyze the structured information according to the identifier of the capture device.

[0109] Fig. 9 A system architecture diagram provided in an embodiment of the present application. Fig. 9 As shown, it includes a composite intelligent capture machine (which can be referred to as a capture machine) and a retrieval application server. The composite intelligent capture machine can capture pictures of moving objects such as people, motor vehicles and non-motor vehicles. The composite intelligent capture machine includes: a person detection and extraction module, a motor vehicle detection and extraction module and a non-motor vehicle detection and extraction module. Among them, the person retrieval and extraction module further includes: a face detection and extraction module, a human body detection and extraction module and different gait detection and extraction modules. It should be noted that the algorithm models for identifying motor vehicles, faces, etc. in the above examples are set in the corresponding modules, so that the composite intelligent capture machine can realize the type recognition of objects in the picture and the extraction of structured information. The retrieval application server constructs a structured information library according to the object type label, and can realize various types of structured information retrieval functions, including: face retrieval application, motor vehicle retrieval application, non-motor vehicle retrieval application, human body retrieval application and gait retrieval application.

[0110] The technical solution provided by the above embodiment brings at least the following beneficial effects: the adaptive capture method provided by the embodiment of the present application identifies the object type to which the capture target belongs in the picture taken by the capture machine, compares the identified object type with the preset object type, and determines whether to turn off the capture machine's recognition function for certain object types according to the comparison result. This avoids unnecessary function operation occupying computing resources and operating power consumption, realizes adaptive optimization adjustment, and improves the service life of the equipment.

[0111] Furthermore, the adaptive capture method provided by the present application can automatically and adaptively close the corresponding recognition function according to the object type to which the target in the scene belongs after the device is powered on, thereby realizing automatic optimization of computing resources without the involvement of excessive human costs. In addition, in the embodiment of the present application, the structured information of the target can also be extracted to construct a structured information library to meet the user's information retrieval needs. In addition, a structured information library is constructed based on the capture machine directory, and the structured information of an object type is divided according to different capture machines, so that when the user queries a certain type of structured information, the user can intuitively determine the point where the structured information is generated (i.e., the point corresponding to the capture machine), so as to filter and retrieve the information based on the point, thereby improving the retrieval efficiency and the user's experience.

[0112] It can be seen that the above mainly introduces the solution provided by the embodiment of the present application from the perspective of the method. In order to achieve the above functions, the embodiment of the present application provides a hardware structure and / or software module corresponding to each function. It should be easily appreciated by those skilled in the art that, in combination with the modules and algorithm steps of each example described in the embodiment disclosed herein, the embodiment of 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 exceed the scope of the present application.

[0113] In an exemplary embodiment, the present application further provides an adaptive capture device, which may include one or more functional modules for implementing the adaptive capture method of the above method embodiment.

[0114] For example, Fig.10 The following is a schematic diagram of the composition of an adaptive capture device provided in an embodiment of the present application. Fig.10 As shown, the adaptive capture device includes: a recognition module 1001 and a determination module 1002. The recognition module 1001 is connected to the determination module 1002.

[0115] The recognition module 1001 is used to recognize the object type to which the captured target in the picture taken by the capture machine belongs; wherein the capture machine has the ability to recognize at least two object types.

[0116] The determination module 1002 is used to compare the identified object type and the preset object type, and determine whether to turn off the recognition capability of at least one object type of the capture machine according to the comparison result; wherein the preset object type is the object type that the capture machine can recognize.

[0117] In some embodiments, the determination module 1002 is specifically used to compare the identified object type and the preset object type, determine the first object type in the preset object type that has not been recognized by the capture machine, and disable the capture machine's ability to recognize the first object type.

[0118] In some embodiments, the determination module 1002 is specifically used to determine, for any object type among the identified object types, the number of captured targets belonging to the object type identified within a preset period; when the number meets the first preset condition, turn off the ability of the capture machine to identify the object type.

[0119] In some embodiments, the determination module 1002 is specifically used to determine the number of capture targets corresponding to each object type in the identified object types within a preset period; compare the number of capture targets corresponding to each object type, and determine whether to turn off the recognition capability of at least one object type of the capture machine based on the comparison result.

[0120] In some embodiments, the determination module 1002 is specifically used to determine the difference between the number of capture targets belonging to the second object type and the number of capture targets belonging to the third object type, wherein the number of capture targets belonging to the second object type is less than the number of capture targets belonging to the third object type; if the difference satisfies a second preset condition, the ability of the capture machine to recognize the second object type is turned off.

[0121] In some embodiments, the determination module 1002 is specifically used to report the object types that can be identified by the capture machine that is not turned off to the server, so that the server can establish a capture machine directory according to the object type.

[0122] In the case of implementing the functions of the above-mentioned integrated modules in the form of hardware, an embodiment of the present application provides a schematic diagram of the structure of an electronic device, which may be the above-mentioned adaptive capture device. Fig.11 As shown, the electronic device 1100 includes: a processor 1102 , a communication interface 1103 , and a bus 1104 . Optionally, the electronic device may further include a memory 1101 .

[0123] The processor 1102 may be a device that implements or executes various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of the present application. The processor 1102 may be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of the present application. The processor 1102 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0124] The communication interface 1103 is used to connect with other devices via a communication network, such as Ethernet, wireless access network, wireless local area network (WLAN), etc.

[0125] The memory 1101 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 disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program codes in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0126] As a possible implementation, the memory 1101 may exist independently of the processor 1102, and the memory 1101 may be connected to the processor 1102 via a bus 1104 for storing instructions or program codes. When the processor 1102 calls and executes the instructions or program codes stored in the memory 1101, the adaptive capture method provided in the embodiment of the present application can be implemented.

[0127] In another possible implementation, the memory 1101 may also be integrated with the processor 1102 .

[0128] The bus 1104 may be an extended industry standard architecture (EISA) bus, etc. The bus 1104 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.11 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0129] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and conciseness of the description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the adaptive capture system is divided into different functional modules to complete all or part of the functions described above.

[0130] The embodiment of the present application also provides a computer-readable storage medium. All or part of the processes in the above method embodiments can be completed by computer instructions to instruct the relevant hardware, and the program can be stored in the above computer-readable storage medium. When the program is executed, it may include the processes of the above method embodiments. The computer-readable storage medium can be the memory or memory of any of the aforementioned embodiments. The above computer-readable storage medium can also be an external storage device of the above adaptive capture system, such as a plug-in hard disk, a smart memory card (smart media card, SMC), a secure digital (secure digital, SD) card, a flash card (flash card), etc. equipped on the above adaptive capture system. Further, the above computer-readable storage medium can also include both the internal storage unit of the above adaptive capture system and an external storage device. The above computer-readable storage medium is used to store the above computer program and other programs and data required by the above adaptive capture system. The above computer-readable storage medium can also be used to temporarily store data that has been output or is to be output.

[0131] An embodiment of the present application also provides a computer program product, which includes a computer program. When the computer program product is run on a computer, the computer is enabled to execute any one of the adaptive capture methods provided in the above embodiments.

[0132] Although the present application is described herein in conjunction with various embodiments, in the process of implementing the claimed application, those skilled in the art may understand and implement other changes to the disclosed embodiments by viewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "one" or "an" does not exclude multiple situations. A single processor or other unit can implement several functions listed in the claims. Certain measures are recorded in different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0133] Although the present application has been described in conjunction with specific features and embodiments thereof, it is obvious that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the drawings are merely exemplary illustrations of the present application as defined by the appended claims, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art may make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

[0134] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An adaptive snapshot method, characterized in that: The method comprises: Identify the object type to which the captured target in the picture taken by the capture machine belongs; wherein the capture machine has the ability to identify at least two object types; Comparing the identified object type with a preset object type, and determining whether to disable the recognition capability of at least one object type of the capture device according to the comparison result; wherein the preset object type is an object type that the capture device can recognize; The comparing the identified object type and the preset object type, and determining whether to disable the recognition capability of at least one object type of the capture device according to the comparison result, includes: Comparing the identified object type with a preset object type, and determining a first object type among the preset object types that has not been identified by the capture device; The ability of the capture machine to recognize the first object type is disabled.

2. The method according to claim 1, characterized in that The comparing the identified object type and the preset object type, and determining whether to disable the recognition capability of at least one object type of the capture device according to the comparison result, further includes: For any object type among the identified object types, determining the number of captured targets belonging to the object type identified within a preset period; When the number meets a first preset condition, the ability of the capture machine to identify the object type is turned off.

3. The method according to claim 1, characterized in that The comparing the identified object type and the preset object type, and determining whether to disable the recognition capability of at least one object type of the capture device according to the comparison result, further includes: Determine the number of captured targets corresponding to each object type in the identified object type within a preset period; The number of captured targets corresponding to each object type is compared, and according to the comparison result, it is determined whether to disable the recognition capability of at least one object type of the capture machine.

4. The method according to claim 3, characterized in that The comparing the number of capture targets corresponding to each object type and determining whether to disable the recognition capability of at least one object type of the capture machine according to the comparison result includes: Determine a difference between the number of snap targets belonging to the second object type and the number of snap targets belonging to the third object type, wherein the number of snap targets belonging to the second object type is less than the number of snap targets belonging to the third object type; If the difference satisfies a second preset condition, the ability of the capture device to identify the second object type is disabled.

5. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: Report the object types that can be identified by the capture machine that is not turned off to the server, so that the server can establish a capture machine directory according to the object type.

6. An adaptive capture device, characterized in that: The device comprises: an identification module and a determination module; The recognition module is used to identify the object type to which the captured target in the picture taken by the capture machine belongs; wherein the capture machine has the ability to recognize at least two object types; The determination module is used to compare the identified object type and the preset object type, determine the first object type among the preset object types that has not been recognized by the capture machine, and turn off the ability of the capture machine to recognize the first object type; wherein the preset object type is an object type that can be recognized by the capture machine.

7. The device according to claim 6, characterized in that The determination module is specifically used to determine, for any object type among the identified object types, the number of captured targets belonging to the object type identified within a preset period; when the number meets a first preset condition, turn off the ability of the capture machine to identify the object type; The determination module is specifically used to determine the number of capture targets corresponding to each object type in the identified object types within a preset period; compare the number of capture targets corresponding to each object type, and determine whether to turn off the recognition capability of at least one object type of the capture machine according to the comparison result; The determination module is specifically used to determine the difference between the number of captured targets belonging to the second object type and the number of captured targets belonging to the third object type, wherein the number of captured targets belonging to the second object type is less than the number of captured targets belonging to the third object type; if the difference meets a second preset condition, then turning off the ability of the capture machine to identify the second object type; The determination module is specifically used to report the object types that are not shut down and can be identified by the capture machine to the server, so that the server can establish a capture machine directory according to the object type.

8. An electronic device, characterized in that: The electronic device comprises: a processor and a memory; The memory stores instructions executable by the processor; When the processor is configured to execute the instructions, the electronic device implements the method according to any one of claims 1 to 5.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes: computer software instructions; When the computer software instructions are executed in a computer, the computer is enabled to implement the method according to any one of claims 1 to 5.

Images