Video recording management method, storage medium and computer program product

Abstract

The present application discloses a video management method, a storage medium and a computer program product, and relates to the field of data processing technology. The video management method includes: obtaining video data, identifying the target to be identified in each frame of the video data through a preset image recognition algorithm, obtaining the target recognition result of each frame, and determining the target video score of each frame based on the target recognition result, managing the frames of the video data whose target video scores are higher than the preset management score through the video management method, obtaining the target video data and saving it. When it is detected that the video data is missing, the missing video data can be synthesized through the video data of other cameras, and when the video needs to be deleted, the target video data with the lowest video value is deleted. Therefore, the present application can manage the video data based on the target video score, and improve the information value of the video data by synthesizing the missing video data and deleting the video data with the lowest information value.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a video recording management method, a storage medium and a computer program product. Background Art

[0002] At present, video data obtained by cameras is commonly used in fields such as security control and video analysis. However, the method of managing video data usually does not process the video data but directly saves the video data, resulting in low information value of the video data. Summary of the invention

[0003] The main purpose of this application is to provide a video management method, a storage medium and a computer program product, aiming to solve the technical problem of low information value of video data.

[0004] To achieve the above purpose, the present application proposes a video recording management method, wherein the method comprises:

[0005] Get video data;

[0006] Based on the target to be identified, the video data is identified and processed by a preset image recognition algorithm to obtain a target identification result, wherein the target identification result includes the type of target that exists or the absence of the target to be identified;

[0007] Determine a target video score based on the target recognition result and / or the target type in the target recognition result;

[0008] Based on the target video score, the video data is managed, and the target video data is obtained and saved.

[0009] In one embodiment, the target to be identified includes an environment to be identified and an object to be identified. Based on the target to be identified, the step of performing identification processing on the video data by a preset image recognition algorithm to obtain a target identification result includes:

[0010] By using a preset image recognition algorithm, based on the environment to be recognized, the video data is subjected to environment recognition processing to obtain an environment recognition result;

[0011] Based on the environment recognition result, the environment object association matrix and the target to be recognized, the video data is recognized and processed to obtain a target recognition result, wherein the environment object association matrix is ​​established based on the environment to be recognized and the target to be recognized.

[0012] In one embodiment, the step of performing recognition processing on the video data based on the environment recognition result, the environment object association matrix and the target to be recognized to obtain the target recognition result includes:

[0013] By using a preset image recognition algorithm, feature extraction is performed on the video data to obtain time features and image features;

[0014] Based on a preset weight parameter, the time feature and the image feature are weighted and summed to obtain a spatiotemporal fusion feature;

[0015] Based on the spatiotemporal fusion features, the environment recognition result, the environment object association matrix and the target recognition result, the video data is recognized and processed to obtain a target recognition result.

[0016] In one embodiment, before the step of managing the video data based on the target video score, obtaining the target video data and saving the data, the step further includes:

[0017] When missing video data is detected, the disconnected camera and the time of disconnection are determined based on the missing video data;

[0018] Determine a surveillance camera in the same area that is associated with the disconnected camera;

[0019] If the video data corresponding to the disconnected camera is restored, the time point of video data restoration is used as the video restoration time point;

[0020] Based on the disconnection time point, the video recording recovery time point and the video recording data acquired by the surveillance cameras in the same area, the missing video recording data is obtained through a preset image synthesis algorithm.

[0021] In one embodiment, the video data is a plurality of continuous frames of images, and the target recognition result is a recognition result corresponding to each frame of the image;

[0022] The step of determining a target video score based on the target recognition result and / or the target type in the target recognition result includes:

[0023] Based on the target type in each frame of image, determine the value score of each target type in each frame of image;

[0024] Based on the target type in each frame of image and the value score of each target type, the target video score corresponding to each frame of image is determined.

[0025] In one embodiment, the step of managing the video data based on the target video score, obtaining the target video data and saving the target video data includes:

[0026] If the target video score of the target frame reaches the preset management score, and the target video score of the previous frame of the target frame is lower than the preset management score, the time of the target frame is used as the video start time;

[0027] If the target video score of the target frame is lower than the preset management score, and the target video score of the previous frame is not lower than the preset management score, the time of the target frame is used as the end time of the video recording;

[0028] Determine target video data based on the video start time and the video end time;

[0029] Based on the target video score, calculating the total video score of the target video data;

[0030] The video recording start time, the video recording end time, the video recording total score and the target video recording data are saved in a video recording storage device.

[0031] In one embodiment, after the step of managing the video data based on the target video score, obtaining the target video data and saving the data, the method further includes:

[0032] Acquire the first available space of the video storage device;

[0033] When it is detected that the first available space is smaller than the preset available space, target video data in the video storage device is deleted based on a preset video deletion algorithm until the first available space is larger than the preset available space.

[0034] In one embodiment, when it is detected that the first available space is smaller than a preset available space, the step of deleting target video data in the video storage device based on a preset video deletion algorithm until the first available space is larger than the preset available space includes:

[0035] Based on the total video score, video start time and current time of each target video data, the video value of each target video data is calculated by a preset video value algorithm;

[0036] Deleting the target video data with the lowest video value among the target video data to obtain a second available space;

[0037] If the second available space is smaller than the preset available space, the total video score, video start time and current time of each target video data are returned, and the video value step of each target video data is calculated by a preset video value algorithm until the second available space is larger than the preset available space.

[0038] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the video recording management method described above are implemented.

[0039] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the video recording management method described above are implemented.

[0040] One or more technical solutions proposed in this application have at least the following technical effects:

[0041] Acquire video data, identify and process the video data through a preset image recognition algorithm, identify whether there is a target to be identified in the video data, and the type of the identified target, and determine and save the target video score based on whether there is a target to be identified in the video data and / or the type of the identified target; manage the video data based on the target video score as an indicator, and improve the information value of the video data by processing the video data before saving. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0043] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0044] Figure 1 A flowchart of the first embodiment of the video recording management method of the present application is provided;

[0045] Figure 2 A flowchart of the second embodiment of the video recording management method of the present application is provided;

[0046] Figure 3 A flowchart of the third embodiment of the video recording management method of the present application is provided;

[0047] Figure 4 A flowchart of the fourth embodiment of the video recording management method of the present application is provided;

[0048] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0049] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0050] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0051] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a video management system, etc. The following takes the video management system as an example to illustrate this embodiment and the following embodiments.

[0052] Based on this, the present application embodiment provides a video recording management method, referring to Figure 1 , Figure 1 This is a flowchart of the first embodiment of the video recording management method of the present application.

[0053] In this embodiment, the video recording management method includes steps S10 to S40:

[0054] Step S10, obtaining video data;

[0055] It should be noted that the acquired video data is video data obtained by multiple cameras monitoring the same area. The acquired video data is first stored in the camera, and then the video data is processed.

[0056] Step S20, based on the target to be identified, the video data is identified by a preset image recognition algorithm to obtain a target identification result, wherein the target identification result includes the type of the target that exists or the absence of the target to be identified;

[0057] It should be noted that the preset image recognition algorithm can be a deep learning algorithm such as a convolutional neural network, or a machine learning algorithm such as a support vector machine, a random forest, etc. This embodiment uses a convolutional neural network to identify whether there is a target to be identified in the image in the video data. The target to be identified is set by the user in the system, such as a car, a person, gas, various materials, etc.

[0058] It is understandable that the video data obtained by the camera will be used in security management, video analysis and other aspects. In different application scenarios, the specific objects that need to be paid attention to will also be different. Therefore, users can set different targets to be identified and process the video data through convolutional neural networks to identify the targets to be identified in the video data.

[0059] Step S30, determining a target video score based on the target recognition result and / or the target type in the target recognition result;

[0060] It should be noted that the target video score is determined by the identified object in the target video identified by the image recognition algorithm and is mainly used to describe the value of the video.

[0061] It is understandable that the value of different parts of the video data is different. When there is an object that needs attention in one part of the video data, the value of the video of that part will be higher. When there is no image that needs attention in other parts of the video data, the value of the video of that part will be lower. Therefore, the video management system recognizes the video data through the convolutional neural network and obtains the corresponding recognition results, so that the value of each part of the video can be determined by the recognition results.

[0062] Step S40: managing the video data based on the target video score, obtaining and saving the target video data.

[0063] It should be noted that the operation of managing the video data may be operations such as filtering out part of the video data, deleting unnecessary data in the video data, and saving necessary video data.

[0064] It is understandable that by determining the target video score, the video management system can determine the value of each part of the video. Therefore, the video management system can perform operations such as screening video data with higher value, deleting video data with lower value, and saving video data with higher value, thereby increasing the value of the saved video data.

[0065] In a feasible implementation manner, the video data is a plurality of continuous frames of images, and the target recognition result is a recognition result corresponding to each frame of the image. In step S30, the target video score is determined based on the target recognition result and / or the target type in the target recognition result, and may also be:

[0066] Based on the target type in each frame image, determine the value score of each target type in each frame image; based on the target type in each frame image and the value score of each target type, determine the target video score corresponding to each frame image.

[0067] It should be noted that the target type is a specific object identified in the video data, such as a person, a car, smoke, colored gas, etc. The above objects have different value scores in different environments. The value score is a score used to evaluate the value information in the video. The higher the value score, the higher the value information in the video.

[0068] The value information of each target type is not only related to the current environment, but also to other target types. For example, in a chemical gas processing environment, there will be scenes where only the processing personnel appear, and scenes where the processing personnel and colored chemical gases appear together. Since the scene where the processing personnel and colored chemical gases appear together is a situation where the processing personnel are processing, the value score of the processing personnel in this scene will be higher.

[0069] It is understandable that the preset image recognition algorithm processes the video data by processing each frame of the video data. The video management system determines the value score of each target object based on the current specific environment and the target object appearing in the environment. As the target object appearing in each frame of the image changes, the value score of each target object may change. The video management system determines the target video score corresponding to each frame of the image based on the target type in each frame of the image and the value score of each target type.

[0070] In a feasible implementation manner, in step S40, the video data is managed based on the target video score, and before the target video data is obtained and saved, the following may also be performed:

[0071] When missing video data is detected, the disconnected camera and the disconnection time point are determined based on the missing video data; the surveillance camera in the same area associated with the disconnected camera is determined; if the video data corresponding to the disconnected camera is restored, the time point of the video data recovery is used as the video recovery time point; based on the disconnection time point, the video recovery time point and the video data obtained by the surveillance camera in the same area, the missing video data is obtained through a preset image synthesis algorithm.

[0072] It should be noted that the situation of missing video data may be that some cameras cannot transmit video data due to network connection problems, or some cameras are damaged and cannot capture images. In this case, the video management system will detect the situation of missing images, and determine the disconnected camera based on the missing images, and use the time point when the missing images are detected as the disconnection time point.

[0073] If a camera is disconnected due to network connection or other reasons, the video management system will receive the video information taken by the camera again when the network connection is restored. At this time, the video management system will use the time point when the camera is restored as the time point when the video is restored, and synthesize the missing data through the preset image synthesis method. The preset image synthesis method can be a generative adversarial network (a model that generates new data samples through the competition between two neural networks), a convolutional neural network, and other models.

[0074] It is understandable that, since the video management system obtains the disconnected camera, the time point when the disconnection started, and the time point when the disconnection ended, the video management system can determine the cameras in the same area as the disconnected camera, and obtain the video data taken by other cameras in the same area during the disconnection period, and process the obtained video data taken by other cameras through a preset image synthesis algorithm to obtain a synthesized missing picture.

[0075] In summary, in this embodiment, the video management system obtains video data, identifies and processes the video data through a preset image recognition algorithm, identifies whether there is a target to be identified in the video data, and the category of the identified target object, and determines the target video score based on the identification result; the video data is managed with the target video score as an indicator, so that the required video data can be accurately found. When problems such as camera disconnection occur, the missing video data can be supplemented by image synthesis, thereby improving the information value of the video data.

[0076] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 2 The target to be identified includes an environment to be identified and an object to be identified. Step S20, based on the preset identification object, the video data is identified by a preset image recognition algorithm to obtain an object recognition result, including steps S21 to S22:

[0077] Step S21, performing environment recognition processing on the video data based on the environment to be recognized by using a preset image recognition algorithm to obtain an environment recognition result;

[0078] It should be noted that the environment to be identified is a specific environment category, such as a construction area, a chemical gas processing area, an item storage area, a general area, etc. After the environment is identified by a preset image recognition algorithm, the specific type of the area currently monitored by the camera can be determined to provide assistance for subsequent processing.

[0079] Step S22, based on the environment recognition result, the environment object association matrix and the target to be recognized, the video data is recognized and processed to obtain a target recognition result, wherein the environment object association matrix is ​​established based on the environment to be recognized and the target to be recognized.

[0080] It should be noted that the environmental object association matrix is ​​the weight of the appearance of different targets to be identified in different environments. For example, in the item storage area, the weight of targets such as people and cars will be greater than the weight of chemical gases, thereby improving the recognition accuracy of objects with higher weights such as people and cars when performing image recognition through a preset image recognition algorithm.

[0081] It is understandable that there will be different objects to be identified in different environments, and the probability of the same object to be identified in each environment is different. For example, in the chemical gas processing area, there is a high probability of chemical gas appearing, while in other areas, the probability of chemical gas appearing is reduced. In the item storage area, items need to be transported and stored by cars and people, and the probability of people and cars appearing is higher than the probability of chemical gas appearing. It is necessary to improve the accuracy of identifying items such as people and cars.

[0082] In a feasible implementation, in step S22, the video data is identified based on the environment identification result, the environment object association matrix and the target to be identified, and a feasible implementation method for obtaining the target identification result may also be:

[0083] The video data is subjected to feature extraction through a preset image recognition algorithm to obtain time features and image features; the time features and the image features are weighted and summed based on preset weight parameters to obtain time-space fusion features; based on the time-space fusion features, the environment recognition results, the environment object association matrix and the target recognition results, the video data is subjected to recognition processing to obtain a target recognition result.

[0084] It should be noted that there is a time feature extraction layer and a spatial feature extraction layer in the preset image recognition algorithm. The time feature extraction layer can be a model for processing time series information such as a recurrent neural network, a Transforemr network (a deep learning model based on an attention mechanism), and the spatial feature extraction layer can be a model for processing image data such as ResNet (Residual Network).

[0085] The extracted time features and space features need to be fused into one feature, and the fused features are used to learn the relevant information in the video data. The weight parameter is used to perform weighted summation on the extracted time features and space features to fuse the time features and space features. The weight parameter used can be a preset weight parameter or a learnable weight parameter. The preset weight parameter will not change during the model learning process, that is, the time features and space features are added according to a fixed weight. The learnable weight parameter can be changed during the model training process based on the model's prediction results, so as to adjust the weight parameter and improve the model training effect.

[0086] In summary, in the training process of the model, this embodiment extracts and fuses the temporal and spatial features of the video data to obtain a better training effect. In a specific image recognition task, the environmental information in the video data is first identified, and then the specific object in the video data is identified based on the identified environmental information combined with the weight of the target object corresponding to each environment in the environmental object association matrix. Therefore, the image recognition method of this embodiment can improve the recognition accuracy of the target object.

[0087] Based on the first embodiment and the second embodiment of the present application, in the third embodiment of the present application, the contents that are the same as the first embodiment or similar to the second embodiment can refer to the above introduction, and will not be repeated later. Figure 3 Step S40: Based on the target video score, the video data is managed to obtain the target video data and save the data, including steps S41 to S45:

[0088] Step S41, if the target video score of the target frame reaches the preset management score, and the target video score of the previous frame of the target frame is lower than the preset management score, the time of the target frame is used as the video start time;

[0089] It should be noted that the preset management score is set in the video management system and is used to determine the video data that needs to be managed. The video data is determined in frames, the target frame is the frame whose target video score reaches the preset management score, and the time of the target frame is the time when the corresponding camera obtains the frame of the image when monitoring.

[0090] It can be understood that if the target video score of the target frame reaches the preset management score, and the target video score of the previous frame of the target frame is lower than the preset management score, it means that the video data corresponding to the time of the frame is the video data that needs to be managed, and the video data before the frame is the video data that does not need to be managed. It means that the time of the frame is the start time of the video data that needs to be managed, so the time of the frame can be used as the video start time.

[0091] Step S42, if the target video score of the target frame is lower than the preset management score, and the target video score of the previous frame is not lower than the preset management score, the time of the target frame is used as the video end time;

[0092] It can be understood that if the target video score of the target frame is lower than the preset management score, and the target video score of the previous frame is not lower than the preset management score, it means that the video corresponding to the time of the frame is a video that does not need to be managed, and the video before the frame is a video that needs to be managed. It means that the time of the frame is the end time of the video data that needs to be managed, so the time of the frame can be used as the end time of the video.

[0093] Step S43, determining target video data based on the video start time and the video end time;

[0094] It is understandable that the recording start time is the start time of the recording data to be managed, and the recording end time is the end time of the recording data to be managed. Therefore, the recording data from the recording start time to the recording end time can be determined as the target recording data.

[0095] Step S44, calculating the total video score of the target video data based on the target video score;

[0096] It is understandable that the target video score includes a target video score for each frame of the video data. Therefore, the total video score of the target video data can be obtained by summing the target video scores of each frame from the video start frame to the video end frame of the target video data.

[0097] Step S45, saving the video recording start time, the video recording end time, the video recording total score and the target video recording data in a video recording storage device.

[0098] It should be noted that the video storage device is a device used to store the video data that needs to be managed. In addition to the target video data, the target video data also includes data such as the total video score, video start time, and video end time for subsequent operations of the video management system.

[0099] In summary, it can be seen that this embodiment determines the recording start time and the recording end time by comparing the target recording score of the target frame with the preset management score, and comparing the target recording score of the previous frame of the target frame with the preset management score, so as to determine the recording data that needs to be managed and calculate the total recording score, and saves the recording data that needs to be managed, as well as the corresponding recording start time, recording end time and total recording score, thereby improving the information value of the recording data.

[0100] Based on the first embodiment to the third embodiment of the present application, in the fourth embodiment of the present application, the contents that are the same as the first embodiment to the third embodiment can refer to the above introduction, and will not be repeated later. Figure 4 Step S40, based on the target video score, manage the video data, obtain the target video data and save it, and further include steps A41 to A42:

[0101] Step A41, obtaining the first available space of the video storage device;

[0102] It should be noted that the first available space of the video storage device is the available space obtained by subtracting the used space of the video storage device from the total available space of the video storage device.

[0103] Step A42: when it is detected that the first available space is smaller than the preset available space, target video data in the video storage device is deleted based on a preset video deletion algorithm until the first available space is larger than the preset available space.

[0104] It should be noted that the preset available space is set in the system to limit the space usage of the storage device to ensure that the storage device has enough space to save the video. When it is detected that the first available space of the storage device is less than the preset available space, in order to ensure that the storage device has enough space, the video in the storage device needs to be deleted until the first available space is greater than the preset available space.

[0105] The video deletion operation is performed based on a preset video deletion algorithm, which ensures that the information value of the video data in the storage device is high by deleting the video data with low video value or that has been stored for a long time in the storage device.

[0106] In a feasible implementation manner, in step A42, when it is detected that the first available space is smaller than the preset available space, the target video data in the video storage device is deleted based on a preset video deletion algorithm until the first available space is larger than the preset available space. Alternatively, the method may be:

[0107] Based on the total video score, video start time and current time of each target video data, the video value of each target video data is calculated by a preset video value algorithm; the target video data with the lowest video value among the target video data is deleted to obtain a second available space; if the second available space is smaller than the preset available space, the step of calculating the video value of each target video data by a preset video value algorithm based on the total video score, video start time and current time of each target video data is returned until the second available space is larger than the preset available space.

[0108] It should be noted that the video value is used to describe the value of each video data in the storage device, which is calculated by a preset video value algorithm. The parameters that affect the video value mainly include the total video score, the video start time and the current time.

[0109] It is understandable that the videos in the storage device have two parameters: the total video score and the video start time. Since videos with high total video scores have higher information value than videos with low total video scores, and videos with a video start time close to the current time have higher information value than videos with a video start time far from the current time. Therefore, the preset deletion algorithm deletes the video data with the lowest comprehensive video value at the current time by comprehensively considering the total video score and the video start time, and then the second available space can be obtained. The second available space is the available space after the video management system deletes the video data in the storage device.

[0110] Since the video recording time of the saved video data is different, after the video recording management system deletes the video recording data with the lowest comprehensive video recording value, it is still possible that the second available space obtained is smaller than the preset available space. In this case, it is necessary to continue to repeat the above video recording deletion operation to delete the video recording data with the lowest video recording value until the second available space is larger than the preset available space.

[0111] In summary, it can be seen that this embodiment uses a preset video deletion algorithm to delete the video with the lowest video value in the storage device. When the available space of the storage device is less than the preset available space, firstly, the video value of each video is calculated by comprehensively considering information such as the total score of the video, the start time of the video recording, and the current time, and the video with the lowest video value is deleted. If the available space of the storage device is still less than the preset lower limit of the available space after the deletion, the above-mentioned video deletion operation is continued to be repeated until the available space of the storage device is higher than the preset lower limit of the available space. Therefore, this embodiment can make the storage device always have a certain amount of available space, and at the same time make the videos in the storage device have higher information value.

[0112] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the video recording management method of the present application. More simple transformations based on this technical concept are all within the protection scope of the present application.

[0113] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0114] The computer-readable storage medium may be included in the video management device; or may exist independently without being assembled into the video management device.

[0115] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the video management device, the video management device executes the video management method.

[0116] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0117] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to each embodiment of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0118] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0119] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned video management method, and can solve the technical problem that the information value of the video data is low. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the video management method provided by the above-mentioned embodiment, and will not be repeated here.

[0120] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned video recording management method when executed by a processor.

[0121] The computer program product provided by this application can solve the technical problem that the information value of video data is low. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the video management method provided by the above embodiment, which will not be repeated here.

[0122] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A video recording management method, characterized in that: The method includes: Get video data; Based on the target to be identified, the video data is identified and processed by a preset image recognition algorithm to obtain a target identification result, wherein the target identification result includes the type of target that exists or the absence of the target to be identified; Determine a target video score based on the target recognition result and / or the target type in the target recognition result; Based on the target video score, the video data is managed, and the target video data is obtained and saved.

2. The method according to claim 1, characterized in that The target to be identified includes an environment to be identified and an object to be identified. Based on the target to be identified, the step of identifying and processing the video data by a preset image recognition algorithm to obtain a target recognition result includes: By using a preset image recognition algorithm, based on the environment to be recognized, the video data is subjected to environment recognition processing to obtain an environment recognition result; Based on the environment recognition result, the environment object association matrix and the target to be recognized, the video data is recognized and processed to obtain a target recognition result, wherein the environment object association matrix is ​​established based on the environment to be recognized and the target to be recognized.

3. The method according to claim 2, characterized in that The step of performing recognition processing on the video data based on the environment recognition result, the environment object association matrix and the target to be recognized to obtain the target recognition result comprises: By using a preset image recognition algorithm, feature extraction is performed on the video data to obtain time features and image features; Based on a preset weight parameter, the time feature and the image feature are weighted and summed to obtain a spatiotemporal fusion feature; Based on the spatiotemporal fusion features, the environment recognition result, the environment object association matrix and the target recognition result, the video data is recognized and processed to obtain a target recognition result.

4. The method according to claim 1, characterized in that: Before the step of managing the video data based on the target video score, obtaining the target video data and saving the target video data, the method further includes: When missing video data is detected, the disconnected camera and the time of disconnection are determined based on the missing video data; Determine a surveillance camera in the same area that is associated with the disconnected camera; If the video data corresponding to the disconnected camera is restored, the time point of video data restoration is used as the video restoration time point; Based on the disconnection time point, the video recording recovery time point and the video recording data acquired by the surveillance cameras in the same area, the missing video recording data is obtained through a preset image synthesis algorithm.

5. The method according to claim 3, characterized in that The video data is a plurality of continuous frames of images, and the target recognition result is the recognition result corresponding to each frame of the image; The step of determining a target video score based on the target recognition result and / or the target type in the target recognition result includes: Based on the target type in each frame of image, determine the value score of each target type in each frame of image; Based on the target type in each frame of image and the value score of each target type, the target video score corresponding to each frame of image is determined.

6. The method according to claim 5, characterized in that The step of managing the video data based on the target video score, obtaining the target video data and saving the target video data comprises: If the target video score of the target frame reaches the preset management score, and the target video score of the previous frame of the target frame is lower than the preset management score, the time of the target frame is used as the video start time; If the target video score of the target frame is lower than the preset management score, and the target video score of the previous frame is not lower than the preset management score, the time of the target frame is used as the end time of the video recording; Determine target video data based on the video start time and the video end time; Based on the target video score, calculating the total video score of the target video data; The video recording start time, the video recording end time, the video recording total score and the target video recording data are saved in a video recording storage device.

7. The method according to claim 6, characterized in that After the step of managing the video data based on the target video score, obtaining the target video data and saving the target video data, the method further includes: Acquire the first available space of the video storage device; When it is detected that the first available space is smaller than the preset available space, target video data in the video storage device is deleted based on a preset video deletion algorithm until the first available space is larger than the preset available space.

8. The method according to claim 7, characterized in that: The step of deleting target video data in the video storage device based on a preset video deletion algorithm when detecting that the first available space is smaller than a preset available space until the first available space is larger than the preset available space includes: Based on the total video score, video start time and current time of each target video data, the video value of each target video data is calculated by a preset video value algorithm; Deleting the target video data with the lowest video value among the target video data to obtain a second available space; If the second available space is smaller than the preset available space, the total video score, video start time and current time of each target video data are returned, and the video value step of each target video data is calculated by a preset video value algorithm until the second available space is larger than the preset available space.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the video recording management method according to any one of claims 1 to 8 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the video recording management method according to any one of claims 1 to 8 are implemented.

Images