Video data processing method, device, equipment, medium and program product

Abstract

The invention provides a video data processing method and device, equipment, a storage medium and a program product, which can be applied to the technical field of video compression. The video data processing method comprises the steps that in response to a video data storage request, to-be-stored video data is acquired, and the video data comprises a plurality of initial videos acquired by a plurality of cameras; performing target detection on the plurality of initial videos based on preset object features to determine a plurality of monitoring objects; extracting video clips related to each monitored object from the plurality of initial videos; and processing the video clips respectively related to the plurality of monitoring objects to obtain compressed video data.

Description

Technical Field

[0001] The present disclosure relates to the field of video compression technology, and more specifically, to a video data processing method, device, equipment, medium and program product. Background Art

[0002] As camera resolution increases and functions become more powerful, video data takes up more and more storage space. Therefore, in order to save storage space, video data needs to be compressed.

[0003] When compressing video data, video data encoding technology is usually used. However, when compressing video data using video data encoding technology, not only the quality of the video picture is reduced, but also the compression range is small for video data within a preset time period. Summary of the invention

[0004] In view of this, the present disclosure provides a video data processing method, apparatus, device, medium and program product.

[0005] One aspect of the present disclosure provides a video processing method, comprising: in response to a video data storage request, obtaining video data to be stored, wherein the video data includes a plurality of initial videos acquired by a plurality of cameras; performing target detection on the plurality of initial videos based on preset object features to determine a plurality of monitoring objects; extracting video clips related to each monitoring object from the plurality of initial videos; and processing the video clips related to each of the plurality of monitoring objects to obtain compressed video data.

[0006] According to an embodiment of the present disclosure, video clips respectively related to a plurality of monitoring objects are processed to obtain compressed video data, including: for each monitoring object, when the number of video clips related to the monitoring object is greater than 1, a time overlap assessment is performed based on the time coverage of the video clips related to the monitoring object to obtain an assessment result; when the assessment result indicates that there is an overlap in the time coverage in the video clips related to the monitoring object, a video cropping strategy is used to perform cropping based on the video clips related to the monitoring object to obtain processed video clips; the processed video clips are merged to obtain a second video related to the monitoring object; and compressed video data is obtained based on the second videos respectively related to the plurality of monitoring objects.

[0007] According to an embodiment of the present disclosure, a video cropping strategy includes cropping based on a clarity priority principle; wherein, the video cropping strategy is used to perform cropping processing based on video clips related to a monitored object to obtain processed video clips, including: for a first clip, when there is an overlap in the time coverage between the first clip and the second clip, a first sub-segment located in the overlapping time coverage is determined from the first clip, and a second sub-segment located in the overlapping time coverage is determined from the second clip, wherein both the first clip and the second clip are video clips related to the monitored object; based on a comparison result of the clarity of the first sub-segment and the clarity of the second sub-segment, a video sub-segment with lower clarity is deleted, and the video sub-segment is the first sub-segment or the second sub-segment; and the video clips related to the monitored object are traversed to complete the cropping processing of the video clips related to the monitored object to obtain the processed video clips.

[0008] According to an embodiment of the present disclosure, the above method also includes determining the clarity of a video sub-segment by any one of the following methods, or a combination of multiple methods: determining the clarity of a video sub-segment based on the distance between a monitored object and a camera in the video sub-segment; determining the clarity of a video sub-segment based on the area of ​​a video screen occupied by the monitored object in the video sub-segment; determining the clarity of a video sub-segment based on the image clarity of each of multiple frames of video images included in the video sub-segment.

[0009] According to an embodiment of the present disclosure, a video cropping strategy includes cropping based on the relative posture of a monitoring target and a camera; wherein, using the video cropping strategy, cropping processing is performed based on video clips related to the monitoring target to obtain processed video clips, including: for a first clip, when there is an overlap in the time coverage range between the first clip and the second clip, a first sub-segment located in the overlapping time coverage range is determined from the first clip, and a second sub-segment located in the overlapping time coverage range is determined from the second clip, wherein both the first clip and the second clip are video clips related to the monitoring target; based on a comparison result of a deviation of the relative posture between the monitoring target and the camera in the first sub-segment compared to the reference posture, and a deviation of the relative posture between the monitoring target and the camera in the second sub-segment compared to the reference posture, deleting the video sub-segment with a larger deviation, and the video sub-segment is the first sub-segment or the second sub-segment; and traversing the video clips related to the monitoring target to complete the cropping processing of the video clips related to the monitoring target to obtain the processed video clips.

[0010] According to an embodiment of the present disclosure, the above method also includes: when the number of video clips related to the monitored object is 1, or when the evaluation result indicates that there is no overlap in time coverage in the video clips related to the monitored object, obtaining a second video related to the monitored object based on the video clips related to the monitored object.

[0011] According to an embodiment of the present disclosure, video clips related to each monitored object are extracted from multiple initial videos, including: for each monitored object, determining from multiple initial videos a first video in which the monitored object exists; and for each first video, extracting video clips related to the monitored object from the first video.

[0012] According to an embodiment of the present disclosure, a video clip related to a monitored object is extracted from a first video, including: obtaining a first time point based on a moment when the monitored object appears in the first video; obtaining a second time point based on a moment when the monitored object disappears in the first video; and extracting a video clip related to the monitored object from the first video based on the first time point and the second time point.

[0013] Another aspect of the present disclosure provides a video data processing device, including: a video acquisition module, used to respond to a video data storage request and acquire video data to be stored, wherein the video data includes multiple initial videos acquired by multiple cameras; a target detection module, used to perform target detection on the multiple initial videos based on preset object features to determine multiple monitoring objects; a segment extraction module, used to extract video segments related to each monitoring object from the multiple initial videos; and a segment processing module, used to process the video segments related to each of the multiple monitoring objects to obtain compressed video data.

[0014] Another aspect of the present disclosure provides an electronic device, including: one or more processors; and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the above method.

[0015] Another aspect of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, which are used to implement the above method when executed.

[0016] Another aspect of the present disclosure provides a computer program product, which includes computer executable instructions, and the instructions are used to implement the above method when executed.

[0017] According to the embodiments of the present disclosure, by extracting video clips related to the monitored object in the initial video, the amount of video data can be significantly reduced, avoiding the waste of storage space due to storing a large amount of invalid video data, thereby achieving compression of the video data, saving storage space and reducing the impact on the video picture quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The above and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0019] Figure 1 The application scenario of the video data processing method according to the embodiment of the present disclosure is schematically shown;

[0020] Figure 2 A flowchart of a video data processing method according to an embodiment of the present disclosure is schematically shown;

[0021] Figure 3 A schematic diagram schematically shows a method of generating a second video according to a specific embodiment of the present disclosure;

[0022] Figure 4 A flowchart of generating a second video according to an embodiment of the present disclosure is schematically shown;

[0023] Figure 5 A block diagram schematically shows a video data processing device according to an embodiment of the present disclosure; and

[0024] Figure 6 A block diagram of an electronic device suitable for implementing a video data processing method according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0025] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0026] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0027] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0028] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0029] In the embodiments of the present disclosure, the collection, updating, analysis, processing, use, transmission, provision, disclosure, storage, etc. of the data involved (for example, including but not limited to user personal information) are in compliance with the provisions of relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. In particular, necessary measures are taken for user personal information to prevent illegal access to user personal information data and maintain the security of user personal information, network security, and national security.

[0030] In the embodiments of the present disclosure, the user's authorization or consent is obtained before obtaining or collecting the user's personal information.

[0031] The size of the video data collected by the camera is related to multiple parameters such as the resolution, bit rate, frame rate, and compression format of the video data. The most important parameter is the bit rate. Bit rate, also known as bit rate, is a parameter used to indicate the size of the space occupied by video data per unit time. Under the same resolution and frame rate, the larger the bit rate, the higher the video quality and the larger the storage space occupied. Conversely, the lower the video quality, the smaller the storage space occupied.

[0032] As camera resolution increases and functions become more powerful, video data takes up more and more storage space. Therefore, in order to save storage space, it is usually necessary to regularly delete historical video data or compress the video data.

[0033] The method of periodically deleting historical video data usually requires setting a time period, releasing the storage space used to store historical video data that exceeds the time period, and using the released storage space to accommodate new video data. However, when there are a large number of cameras, a large amount of initial storage space is still required.

[0034] When compressing video data, video data encoding technology is usually used. However, when compressing video data using video data encoding technology, not only will the video picture quality be reduced, but also for video data within a preset period, the compression range will be small due to the upper limit of the encoding technology.

[0035] An embodiment of the present disclosure provides a video data processing method, including: in response to a video data storage request, obtaining video data to be stored, wherein the video data includes multiple initial videos captured by multiple cameras; based on preset object features, performing target detection on the multiple initial videos to determine multiple monitoring objects; extracting video clips related to each monitoring object from the multiple initial videos; and processing the video clips related to each of the multiple monitoring objects to obtain compressed video data.

[0036] The embodiments of the present disclosure reduce the amount of video data by extracting video clips related to the monitored object from the initial video, avoiding the waste of storage space due to storing a large amount of invalid video data, and reducing the impact on video picture quality while achieving video data compression.

[0037] Figure 1 The application scenario of the video data processing method according to the embodiment of the present disclosure is schematically shown. It should be noted that: Figure 1 What is shown are merely examples of application scenarios to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0038] like Figure 1 As shown, the application scenario 100 according to this embodiment may include a first camera 101, a second camera 102, a third camera 103, a network 104 and a server 105. The network 104 is used to provide a medium for a communication link between the first camera 101, the second camera 102, the third camera 103 and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0039] The first camera 101, the second camera 102, and the third camera 103 can interact with the server 105 through the network 104 to send video data, etc. The first camera 101, the second camera 102, and the third camera 103 can respectively shoot videos in corresponding areas. For example, when a monitored object passes through the shooting area of ​​any camera, its image can be collected.

[0040] The first camera 101 , the second camera 102 , and the third camera 103 may be surveillance cameras, or may be various electronic devices with a camera function.

[0041] The server 105 may be a server that provides various services, such as processing and storing video data collected by the first camera 101 , the second camera 102 , and the third camera 103 .

[0042] It should be noted that the video data processing method provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the video data processing device provided in the embodiment of the present disclosure can generally be set in the server 105. The video data processing method provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the first camera 101, the second camera 102, the third camera 103 and / or the server 105. Accordingly, the video data processing device provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the first camera 101, the second camera 102, the third camera 103 and / or the server 105.

[0043] For example, after capturing the initial video, any one of the first camera 101, the second camera 102, or the third camera 103 (for example, the first camera 101, but not limited thereto) may send a video data storage request and the video data to be stored to the server 105 through the network 104. Then, the server 105 may execute the video data processing method provided in the embodiment of the present disclosure, or send the video data to be stored to other servers or server clusters, and the other servers or server clusters that receive the video data to be stored may execute the video data processing method provided in the embodiment of the present disclosure.

[0044] It should be understood that Figure 1 The number of cameras, networks and servers in the embodiment is only for illustration. Any number of cameras, networks and servers may be provided as required.

[0045] Figure 2 The flowchart of the video data processing method according to the embodiment of the present disclosure is schematically shown.

[0046] like Figure 2 As shown, the video data processing method includes operations S210 to S240.

[0047] In operation S210, in response to a video data storage request, video data to be stored is acquired.

[0048] According to an embodiment of the present disclosure, the video data includes a plurality of initial videos acquired by a plurality of cameras.

[0049] According to an embodiment of the present disclosure, the video data storage request may be sent by a camera. Specifically, the camera may generate a video data storage request based on the initial video collected within a predetermined time interval, and send the video data storage request to a server that executes the video data processing method.

[0050] According to an embodiment of the present disclosure, video data to be stored can be obtained from video data storage requests of multiple cameras respectively, and camera identifiers can also be obtained from the video data storage requests at the same time to facilitate distinguishing initial videos captured by different cameras in the video data.

[0051] In operation S220, object detection is performed on the plurality of initial videos based on preset object features to determine a plurality of monitoring objects.

[0052] According to an embodiment of the present disclosure, preset object features can characterize features of preset objects. Specifically, preset objects may include pedestrians, animals, vehicles, and other items that need to be monitored, and preset object features may include features such as appearance, structure, and shape of the preset objects.

[0053] According to an embodiment of the present disclosure, the monitoring object may be a preset object included in a plurality of initial videos, and specifically, may be a pedestrian, an animal, a vehicle, or other objects to be monitored that appear in a plurality of initial videos.

[0054] According to an embodiment of the present disclosure, when performing target detection on multiple initial videos, feature matching can be used. Specifically, feature matching can be performed on multiple initial videos using preset object features to determine that the objects in the initial videos that match the preset object features are the monitored objects.

[0055] According to an embodiment of the present disclosure, when performing target detection on multiple initial videos, a machine learning model can also be used to identify the monitoring objects in the multiple initial videos. Specifically, the machine learning model can be trained using sample videos and preset object features so that it can identify the preset objects in the video, and then the trained machine learning model can be used to perform target detection on the initial video to determine the multiple monitoring objects in the initial video.

[0056] In operation S230, a video segment related to each monitored object is extracted from the plurality of initial videos.

[0057] According to an embodiment of the present disclosure, the video clip related to the monitored object can be a video clip including the monitored object in the initial video. Specifically, the appearance time and disappearance time of each monitored object in the initial video can be determined, and the appearance time of the monitored object in the initial video is determined as the starting time of the video clip, and the disappearance time is determined as the ending time of the video clip, and the video clip is cut out from the initial video.

[0058] In operation S240, the video segments related to each of the plurality of monitored objects are processed to obtain compressed video data.

[0059] According to an embodiment of the present disclosure, when processing video clips related to multiple monitored objects, multiple video clips of the same monitored object can be screened. Specifically, multiple video clips of the same monitored object can be screened according to the clarity, angle or other screening requirements of the monitored object in the video clip.

[0060] For example, in the initial video A captured by camera A, there is a video segment A related to the monitored object, the start time of video segment A is time 1, and the end time is time 2. In addition, in the initial video B captured by camera B, there is a video segment B related to the monitored object, the start time of video segment B is time 1, and the end time is time 2. At this time, the video segment with higher definition between video segment A and video segment B can be retained.

[0061] According to an embodiment of the present disclosure, after processing the video clips related to each of the multiple monitored objects, they can be arranged according to their respective time coverage to obtain video data for the monitored objects, and compressed video data can be obtained based on the video data of each of the multiple monitored objects.

[0062] According to the embodiments of the present disclosure, by extracting video clips related to the monitored object in the initial video, the amount of video data can be significantly reduced, avoiding the waste of storage space due to storing a large amount of invalid video data, thereby achieving compression of the video data, saving storage space and reducing the impact on the video picture quality.

[0063] According to an embodiment of the present disclosure, video clips related to each of a plurality of monitoring objects are processed to obtain compressed video data, including: for each monitoring object, when the number of video clips related to the monitoring object is greater than 1, a time overlap assessment is performed based on the time coverage of the video clips related to the monitoring object to obtain an assessment result; when the assessment result indicates that there is an overlap in the time coverage in the video clips related to the monitoring object, a video cropping strategy is used to perform cropping based on the video clips related to the monitoring object to obtain processed video clips; the processed video clips are merged to obtain a second video related to the monitoring object; and compressed video data is obtained based on the second videos related to each of the plurality of monitoring objects.

[0064] According to an embodiment of the present disclosure, since there may be overlapping shooting areas between different cameras, the same monitored object may appear in the same period of time in different initial videos, resulting in the number of video clips related to the monitored object being greater than one.

[0065] According to an embodiment of the present disclosure, since the monitored object may also pass through the non-overlapping shooting areas of different cameras in sequence, the same monitored object may also appear in different time periods of different initial videos, resulting in the number of video clips related to the monitored object being greater than 1.

[0066] According to an embodiment of the present disclosure, since the monitored object may pass through the shooting area of ​​the same camera multiple times, the same monitored object may appear in different time periods of the same initial video, resulting in the number of video clips related to the monitored object being greater than 1.

[0067] According to an embodiment of the present disclosure, the time coverage of a video clip may be a time period between a start time and an end time of the video clip.

[0068] According to the embodiments of the present disclosure, a time overlap evaluation can be performed on multiple video clips related to the monitored object according to the start time and end time of each video clip to obtain an evaluation result. Specifically, when the start time of one video clip is within the time coverage of another video clip, or the end time of one video clip is within the time coverage of another video clip, or the time coverage of one video clip is within the time coverage of another video clip, it can be determined that the two video clips have overlapping time coverage.

[0069] According to an embodiment of the present disclosure, a video cropping strategy may represent a strategy for cropping video segments with overlapping time coverage when there is overlap in the time coverage of video segments related to the monitored object. Specifically, the principles of the video cropping strategy may include clarity priority and priority for smaller relative posture offset, etc.

[0070] According to an embodiment of the present disclosure, when a video clip is cropped using a video cropping strategy, clips in the video clips that overlap in time coverage and do not comply with the video cropping strategy can be deleted. Specifically, clips in the video clips that overlap in time coverage and have low definition, or clips with large relative posture offsets of the monitored object can be deleted.

[0071] According to the embodiments of the present disclosure, when merging the processed video segments, the segments with overlapping time coverage and conforming to the video cropping strategy can be used to merge with the cropped video segments to obtain multiple video segments with non-overlapping time coverage. Specifically, the segments with overlapping time coverage and high definition, or with small relative position deviation of the monitored object, can be used to merge with the cropped video segments.

[0072] According to an embodiment of the present disclosure, multiple video clips with non-overlapping time coverage ranges may be merged according to the sequence of the time coverage ranges to obtain a second video related to the monitored object.

[0073] According to an embodiment of the present disclosure, the compressed video data may include second videos related to each of the multiple monitored objects.

[0074] According to an embodiment of the present disclosure, by utilizing a video cropping strategy, video segments with overlapping temporal coverage are cropped, and segments that comply with the video cropping strategy are retained, thereby further reducing the amount of video data while improving the video picture quality.

[0075] According to an embodiment of the present disclosure, a video cropping strategy is used to perform cropping processing based on video clips related to a monitored object to obtain processed video clips, including: for a first clip, when there is an overlap in the time coverage between the first clip and the second clip, a first sub-segment located in the overlapping time coverage is determined from the first clip, and a second sub-segment located in the overlapping time coverage is determined from the second clip; based on a comparison result of the clarity of the first sub-segment and the clarity of the second sub-segment, the video sub-segment with lower clarity is deleted, and the video sub-segment is the first sub-segment or the second sub-segment; and the video clips related to the monitored object are traversed to complete the cropping processing of the video clips related to the monitored object to obtain the processed video clips.

[0076] According to an embodiment of the present disclosure, the video cropping strategy includes cropping based on the definition priority principle. Specifically, based on the definition priority principle, it can be characterized by cropping out segments with lower definition.

[0077] According to an embodiment of the present disclosure, both the first segment and the second segment are video segments related to the monitored object. The first sub-segment and the second sub-segment have the same time coverage.

[0078] According to an embodiment of the present disclosure, when the start time of the first segment is within the time coverage of the second segment, and the end time of the first segment is not within the time coverage of the second segment, it can be determined that the start time of the first segment and the end time of the second segment are overlapping time coverage.

[0079] According to an embodiment of the present disclosure, when the end time of the first segment is within the time coverage of the second segment, and the start time of the first segment is within the time coverage of the second segment, it can be determined that the start time of the second segment and the end time of the first segment are overlapping time coverage.

[0080] According to an embodiment of the present disclosure, when the time coverage of the first segment is within the time coverage of the second segment, it can be determined that the time coverage of the first segment is an overlapping time coverage.

[0081] According to an embodiment of the present disclosure, when the video cropping strategy is based on the definition priority principle, the definition of the first sub-segment and the definition of the second sub-segment can be compared. Specifically, the video sub-segment with lower definition in the first sub-segment or the second sub-segment can be deleted.

[0082] According to an embodiment of the present disclosure, when traversing video clips related to the monitored object, it is possible to determine for each video clip whether there is any overlap in time coverage with other video clips, and if there is any overlap in time coverage, the video clip can be cropped based on the clarity priority principle.

[0083] According to the embodiments of the present disclosure, a video clip is cropped through a video cropping strategy based on the definition priority principle, and video sub-segments with higher definition are retained, thereby saving storage space and improving the quality of the video picture.

[0084] According to an embodiment of the present disclosure, the video data processing method also includes determining the clarity of a video sub-segment by any one of the following methods, or a combination of multiple methods: determining the clarity of a video sub-segment based on the distance between a monitored object and a camera in the video sub-segment; determining the clarity of a video sub-segment based on the area of ​​a video screen occupied by the monitored object in the video sub-segment; determining the clarity of a video sub-segment based on the image clarity of each of multiple frames of video images included in the video sub-segment.

[0085] According to the embodiments of the present disclosure, the closer the distance between the monitored object and the camera is, the higher the definition of the video sub-segment can be determined, and vice versa. Specifically, the position of the monitored object in the camera coordinate system can be determined according to the camera coordinate system of the camera, and then the distance between the monitored object and the camera can be determined.

[0086] According to an embodiment of the present disclosure, the larger the area of ​​the video screen occupied by the monitored object is, the higher the definition of the video sub-segment can be determined, and vice versa.

[0087] According to an embodiment of the present disclosure, the higher the image definition, the higher the definition of the video sub-segment, and vice versa. Specifically, the definition of the video sub-segment can be determined based on the average value of the image definition of multiple frames of video images.

[0088] According to an embodiment of the present disclosure, when determining the clarity of a video sub-segment by combining multiple methods, weights may be assigned to the distance, area, and image clarity, and the clarity of the video sub-segment may be determined based on the distance, area, image clarity, and their respective weights.

[0089] According to the embodiments of the present disclosure, by determining the definition of a video sub-segment from multiple perspectives, the definition of the obtained video sub-segment can meet different requirements, thereby improving the user experience.

[0090] According to an embodiment of the present disclosure, a video cropping strategy is used to perform cropping processing based on video clips related to a monitored object to obtain processed video clips, including: for a first clip, when there is an overlap in the time coverage between the first clip and the second clip, a first sub-segment located in the overlapping time coverage is determined from the first clip, and a second sub-segment located in the overlapping time coverage is determined from the second clip; based on a comparison result of a deviation of a relative posture between a monitored object and a camera in the first sub-segment compared to a reference posture, and a deviation of a relative posture between the monitored object and the camera in the second sub-segment compared to the reference posture, a video sub-segment with a larger deviation is deleted, and the video sub-segment is the first sub-segment or the second sub-segment; and the video clips related to the monitored object are traversed to complete the cropping processing of the video clips related to the monitored object to obtain processed video clips.

[0091] According to an embodiment of the present disclosure, the video cropping strategy includes cropping based on the relative position of the monitoring target and the camera. Specifically, when cropping based on the relative position of the monitoring target and the camera, a segment with a larger relative position can be cropped.

[0092] According to an embodiment of the present disclosure, both the first segment and the second segment are video segments related to the monitored object. Specifically, the time coverage of the first sub-segment and the second sub-segment is the same.

[0093] According to an embodiment of the present disclosure, the reference posture may be a posture of the monitored object facing the camera. Specifically, the reference posture may be set according to actual business needs. For example, when the monitored object is a vehicle, the reference posture may be a posture of the front of the vehicle facing the camera.

[0094] According to an embodiment of the present disclosure, when the video cropping strategy is to crop based on the relative posture of the monitoring target and the camera, the deviation of the relative posture between the monitoring target and the camera in the first sub-segment compared to the reference posture can be compared with the deviation of the relative posture between the monitoring target and the camera in the second sub-segment compared to the reference posture. Specifically, the video sub-segment with a larger offset in the first sub-segment or the second sub-segment can be deleted.

[0095] According to an embodiment of the present disclosure, when traversing video clips related to the monitored object, it is possible to determine for each video clip whether there is any overlap in time coverage with other video clips, and if there is any overlap in time coverage, the video clip can be cropped based on the relative posture of the monitored object and the camera.

[0096] According to an embodiment of the present disclosure, video clips are cropped through a video cropping strategy based on the relative posture of the monitoring target and the camera, and video sub-segments in which the relative posture between the monitoring target and the camera deviates less than the reference posture are retained, thereby improving the quality of the video image while saving storage space.

[0097] Figure 3 A schematic diagram of generating a second video according to a specific embodiment of the present disclosure is schematically shown.

[0098] like Figure 3 As shown, there is an overlapping time coverage between the first segment 310 and the second segment 320, wherein the first segment includes a first sub-segment 330 located in the overlapping time coverage and a sub-segment 350 not located in the overlapping time coverage, and the second segment includes a second sub-segment 340 in the overlapping time coverage and a sub-segment 360 not located in the overlapping time coverage. Based on the video cropping strategy, the second sub-segment 340 is deleted, and the sub-segment 350, the first sub-segment 330 and the sub-segment 360 are merged to obtain a second video 370.

[0099] According to an embodiment of the present disclosure, the video data processing method also includes: when the number of video segments related to the monitored object is 1, or when the evaluation result indicates that there is no overlap in time coverage in the video segments related to the monitored object, obtaining a second video related to the monitored object based on the video segments related to the monitored object.

[0100] According to an embodiment of the present disclosure, when the number of video clips related to the monitored object is 1, since there are no other video clips related to the monitored object, there is no need to crop the video clips, and the video clip related to the monitored object can be directly determined as the second video.

[0101] According to an embodiment of the present disclosure, when the evaluation results indicate that there is no overlap in the time coverage of the video clips related to the monitored object, the multiple video clips can be merged according to the order of their respective time coverage to obtain a second video related to the monitored object.

[0102] According to an embodiment of the present disclosure, when the number of video segments related to the monitored object is 1, or when the evaluation result indicates that there is no overlap in the time coverage in the video segments related to the monitored object, a second video is directly generated to improve the processing efficiency of video data.

[0103] Figure 4 The flowchart of generating the second video according to the embodiment of the present disclosure is schematically shown.

[0104] like Figure 4 As shown, generating the second video includes operations S410 to S450.

[0105] In operation S410, it is determined whether the number of video segments related to the monitoring object is greater than 1. If the number of video segments related to the monitoring object is greater than 1, operation S420 is performed, otherwise operation S450 is performed.

[0106] In operation S420, it is determined whether there is overlap in time coverage in the video segments related to the monitored object. If there is overlap in time coverage in the video segments related to the monitored object, operation S430 is performed, otherwise operation S450 is performed.

[0107] In operation S430, a video cropping strategy is used to perform a cropping process based on the video segments related to the monitored object.

[0108] In operation S440, the processed video segments are merged to obtain a second video related to the monitored object.

[0109] In operation S450, a second video related to the monitored object is obtained based on the video segment related to the monitored object.

[0110] According to an embodiment of the present disclosure, video clips related to each monitored object are extracted from multiple initial videos, including: for each monitored object, determining from multiple initial videos a first video in which the monitored object exists; and for each first video, extracting video clips related to the monitored object from the first video.

[0111] According to the embodiments of the present disclosure, the initial video can be identified based on the features related to the monitored object in the preset object features to determine the first video containing the monitored object. It is also possible to identify the monitored object in one of the multiple initial videos and then use the features related to the monitored object in the initial video to identify the other initial videos to determine the first video containing the monitored object.

[0112] According to an embodiment of the present disclosure, when performing target recognition on an initial video, multiple frames of video images in the initial video can be obtained. When it is determined that there are video images including a monitored object in the multiple frames of video images, the initial video is determined to be the first video containing the monitored object.

[0113] According to an embodiment of the present disclosure, the first video may be extracted according to the features of the monitored object to obtain video clips related to the monitored object.

[0114] According to an embodiment of the present disclosure, by determining a first video in which a surveillance object exists from a plurality of initial videos, and determining a video segment related to the surveillance object from the first video, the efficiency of extracting video segments is improved.

[0115] According to an embodiment of the present disclosure, a video clip related to a monitored object is extracted from a first video, including: obtaining a first time point based on a moment when the monitored object appears in the first video; obtaining a second time point based on a moment when the monitored object disappears in the first video; and extracting a video clip related to the monitored object from the first video based on the first time point and the second time point.

[0116] According to an embodiment of the present disclosure, the first time point may represent the moment when the monitored object appears in the first video, and the second time point may represent the moment when the monitored object disappears in the first video. Specifically, the second time point is later than the first time point.

[0117] According to an embodiment of the present disclosure, a video segment between a first time point and a second time point in a first video may be captured to obtain a video segment related to a monitored object.

[0118] According to an embodiment of the present disclosure, the method of extracting the video clip related to the monitored object from the second video may be the same as the method of extracting the video clip related to the monitored object from the first video, which will not be repeated here.

[0119] According to an embodiment of the present disclosure, the video is intercepted to obtain video clips according to the time when the monitored object appears and disappears in the video, thereby reducing the amount of video data.

[0120] Figure 5 The block diagram schematically shows a video data processing device according to an embodiment of the present disclosure.

[0121] like Figure 5 As shown, the video data processing device 500 includes a video acquisition module 510 , a target detection module 520 , a segment extraction module 530 and a segment processing module 540 .

[0122] The video acquisition module 510 is used to respond to the video data storage request and acquire the video data to be stored, wherein the video data includes multiple initial videos acquired by multiple cameras. In one embodiment, the video acquisition module 510 can be used to perform the operation S210 described above, which will not be repeated here.

[0123] The target detection module 520 is used to perform target detection on the multiple initial videos based on the preset object features to determine the multiple monitoring objects. In one embodiment, the target detection module 520 can be used to perform the operation S220 described above, which will not be described in detail here.

[0124] The segment extraction module 530 is used to extract video segments related to each monitored object from the multiple initial videos. In one embodiment, the segment extraction module 530 can be used to perform the operation S230 described above, which will not be described in detail here.

[0125] The segment processing module 540 is used to process the video segments related to the multiple monitored objects to obtain compressed video data. In one embodiment, the segment processing module 540 can be used to perform the operation S240 described above, which will not be described in detail here.

[0126] According to an embodiment of the present disclosure, the segment processing module 540 includes a time evaluation submodule, a segment cropping submodule, a segment merging submodule and a video compression submodule.

[0127] The time evaluation submodule is used to perform a time overlap evaluation based on the time coverage of the video clips related to each monitored object when the number of video clips related to the monitored object is greater than 1, and obtain an evaluation result.

[0128] The segment cropping submodule is used to, when the evaluation result indicates that there is an overlap in the time coverage of the video segments related to the monitored object, use the video cropping strategy to perform cropping processing based on the video segments related to the monitored object to obtain processed video segments.

[0129] The segment merging submodule is used to merge the processed video segments to obtain a second video related to the monitored object.

[0130] The video compression submodule is used to obtain compressed video data based on the second videos respectively related to the multiple monitored objects.

[0131] According to an embodiment of the present disclosure, the video cropping strategy includes cropping based on a definition priority principle. The segment cropping submodule includes a first overlap determination unit, a segment deletion unit, and a first traversal unit.

[0132] The first overlap determination unit is used to determine, for a first segment, a first sub-segment located in the overlapping time coverage range from the first segment and a second sub-segment located in the overlapping time coverage range from the second segment when there is an overlap in the time coverage range of the first segment and the second segment, wherein both the first segment and the second segment are video segments related to the monitored object.

[0133] The segment deletion unit is used to delete a video sub-segment with lower definition based on a comparison result of the definition of the first sub-segment and the definition of the second sub-segment, where the video sub-segment is the first sub-segment or the second sub-segment.

[0134] The first traversal unit is used to traverse the video segments related to the monitored object to complete the cropping process of the video segments related to the monitored object to obtain the processed video segments.

[0135] According to an embodiment of the present disclosure, the segment cropping submodule further includes a first determining unit, a second determining unit and a third determining unit.

[0136] The first determining unit is used to determine the clarity of the video sub-segment based on the distance between the monitored object and the camera in the video sub-segment.

[0137] The second determination unit is used to determine the definition of the video sub-segment based on the area of ​​the video screen occupied by the monitored object in the video sub-segment.

[0138] The third determining unit is used to determine the definition of the video sub-segment based on the image definition of each of the multiple frames of video images included in the video sub-segment.

[0139] According to an embodiment of the present disclosure, the video cropping strategy includes cropping based on the relative position of the monitoring target and the camera. The segment cropping submodule includes a second overlap determination unit, an offset determination unit and a second traversal unit.

[0140] The second overlap determination unit is used to determine, for the first segment, a first sub-segment located in the overlapping time coverage range from the first segment and a second sub-segment located in the overlapping time coverage range from the second segment when there is an overlap in the time coverage range of the first segment and the second segment, wherein both the first segment and the second segment are video segments related to the monitored object.

[0141] The offset determination unit is used to delete the video sub-segment with a larger deviation based on the comparison result of the deviation of the relative posture between the monitoring target and the camera in the first sub-segment compared with the reference posture and the deviation of the relative posture between the monitoring target and the camera in the second sub-segment compared with the reference posture, and the video sub-segment is the first sub-segment or the second sub-segment.

[0142] The second traversal determination unit is used to traverse the video segments related to the monitored object to complete the cropping process of the video segments related to the monitored object to obtain the processed video segments.

[0143] According to an embodiment of the present disclosure, the segment processing module 540 further includes a video determination submodule.

[0144] The video determination submodule is used to obtain a second video related to the monitored object based on the video clips related to the monitored object when the number of video clips related to the monitored object is 1, or when the evaluation result indicates that there is no overlap in the time coverage among the video clips related to the monitored object.

[0145] According to an embodiment of the present disclosure, the segment extraction module 530 includes a video determination submodule and a segment extraction submodule.

[0146] The video determination submodule is used to determine, for each monitored object, from a plurality of initial videos, a first video containing the monitored object.

[0147] The segment extraction submodule is used to extract, for each first video, a video segment related to the monitored object from the first video.

[0148] According to an embodiment of the present disclosure, the segment extraction submodule includes a first time determination unit, a second time determination unit and a segment interception unit.

[0149] The first time determination unit is used to obtain a first time point based on the moment when the monitored object appears in the first video.

[0150] The second time determination unit is used to obtain a second time point based on the moment when the monitored object disappears in the first video.

[0151] The segment capture unit is used to capture a video segment related to the monitored object from the first video based on the first time point and the second time point.

[0152] According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits, or at least part of the functions of any one of them can be implemented in one module. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be split into multiple modules for implementation. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be at least partially implemented as hardware circuits, such as field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), systems on chips, systems on substrates, systems on packages, application specific integrated circuits (ASICs), or can be implemented by hardware or firmware in any other reasonable way of integrating or packaging circuits, or can be implemented in any one of the three implementation methods of software, hardware, and firmware, or in any appropriate combination of any of them. Alternatively, according to the embodiments of the present invention, one or more of the modules, submodules, units, and subunits can be at least partially implemented as computer program modules, and when the computer program modules are run, the corresponding functions can be performed.

[0153] For example, any of the video acquisition module 510, the target detection module 520, the fragment extraction module 530, and the fragment processing module 540 can be combined in one module / unit / sub-unit for implementation, or any of the modules / units / sub-units can be split into multiple modules / units / sub-units. Alternatively, at least part of the functions of one or more of these modules / units / sub-units can be combined with at least part of the functions of other modules / units / sub-units and implemented in one module / unit / sub-unit. According to an embodiment of the present disclosure, at least one of the video acquisition module 510, the target detection module 520, the fragment extraction module 530, and the fragment processing module 540 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or by any one of the three implementation methods of software, hardware, and firmware, or by a suitable combination of any of them. Alternatively, at least one of the video acquisition module 510, the object detection module 520, the segment extraction module 530 and the segment processing module 540 may be at least partially implemented as a computer program module, and when the computer program module is executed, the corresponding function may be performed.

[0154] It should be noted that the video data processing device part in the embodiment of the present disclosure corresponds to the video data processing method part in the embodiment of the present disclosure. The description of the video data processing device part specifically refers to the video data processing method part, which will not be repeated here.

[0155] Figure 6 A block diagram of an electronic device suitable for implementing a video data processing method according to an embodiment of the present disclosure is schematically shown. Figure 6 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0156] like Figure 6 As shown, the electronic device 600 according to an embodiment of the present disclosure includes a processor 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 to a random access memory (RAM) 603. The processor 601 may include, for example, a general-purpose microprocessor (such as a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (for example, an application-specific integrated circuit (ASIC)), etc. The processor 601 may also include an onboard memory for caching purposes. The processor 601 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0157] In RAM 603, various programs and data required for the operation of electronic device 600 are stored. Processor 601, ROM 602 and RAM 603 are connected to each other via bus 604. Processor 601 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 602 and / or RAM 603. It should be noted that the program can also be stored in one or more memories other than ROM 602 and RAM 603. Processor 601 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in one or more memories.

[0158] According to an embodiment of the present disclosure, the electronic device 600 may further include an input / output (I / O) interface 605, which is also connected to the bus 604. The electronic device 600 may further include one or more of the following components connected to the input / output (I / O) interface 605: an input portion 606 including a keyboard, a mouse, etc.; an output portion 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 608 including a hard disk, etc.; and a communication portion 609 including a network interface card such as a LAN card, a modem, etc. The communication portion 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the input / output (I / O) interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage portion 608 as needed.

[0159] According to an embodiment of the present disclosure, the method flow according to an embodiment of the present disclosure can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the processor 601, the above-mentioned functions defined in the system of the embodiment of the present disclosure are executed. According to an embodiment of the present disclosure, the system, equipment, device, module, unit, etc. described above can be implemented by a computer program module.

[0160] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0161] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium. For example, it may include, but is not limited to: 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), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device.

[0162] For example, according to an embodiment of the present disclosure, the computer-readable storage medium may include the ROM 602 and / or the RAM 603 described above and / or one or more memories other than the ROM 602 and the RAM 603 .

[0163] The embodiments of the present disclosure also include a computer program product, which includes a computer program, and the computer program contains program code for executing the method provided by the embodiments of the present disclosure. When the computer program product runs on an electronic device, the program code is used to enable the electronic device to implement the video data processing method provided by the embodiments of the present disclosure.

[0164] When the computer program is executed by the processor 601, the above functions defined in the system / device of the embodiment of the present disclosure are executed. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0165] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 609, and / or installed from a removable medium 611. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0166] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0167] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings. For example, two 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 box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, 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. It can be understood by those skilled in the art that the features recorded in the various embodiments of the present disclosure can be combined and / or combined in a variety of ways, even if such a combination or combination is not explicitly recorded in the present disclosure. In particular, without departing from the spirit and teaching of the present disclosure, the features described in the various embodiments of the present disclosure may be combined and / or combined in a variety of ways. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0168] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A video data processing method, comprising: In response to a video data storage request, obtaining video data to be stored, wherein the video data includes a plurality of initial videos acquired by a plurality of cameras; Based on preset object features, performing object detection on the multiple initial videos to determine multiple monitoring objects; Extracting video clips related to each monitored object from the multiple initial videos; and The video clips related to each of the plurality of monitored objects are processed to obtain compressed video data.

2. The method according to claim 1, wherein: The step of extracting video clips related to each monitored object from the multiple initial videos includes: For each monitored object, determining a first video in which the monitored object exists from the multiple initial videos; and For each first video, a video segment related to the monitored object is extracted from the first video.

3. The method according to claim 2, wherein: The step of extracting a video clip related to the monitored object from the first video includes: Obtaining a first time point based on a moment when the monitored object appears in the first video; Obtaining a second time point based on the moment when the monitored object disappears in the first video; and Based on the first time point and the second time point, a video segment related to the monitored object is captured from the first video.

4. The method according to claim 1, wherein: The step of processing the video clips respectively related to the plurality of monitored objects to obtain compressed video data includes: For each monitored object, when the number of video clips related to the monitored object is greater than 1, a time overlap evaluation is performed based on the time coverage of the video clips related to the monitored object to obtain an evaluation result; In a case where the evaluation result indicates that there is an overlap in the time coverage range in the video segments related to the monitored object, using a video cropping strategy to perform cropping processing based on the video segments related to the monitored object to obtain processed video segments; Merging the processed video segments to obtain a second video related to the monitored object; and The compressed video data is obtained based on the second videos respectively related to the multiple monitored objects.

5. The method according to claim 4, wherein: The video cropping strategy includes cropping based on the clarity priority principle; The method of using a video cropping strategy to crop video clips related to the monitored object to obtain processed video clips includes: For a first segment, when the time coverage of the first segment and the second segment overlaps, a first sub-segment located in the overlapping time coverage is determined from the first segment, and a second sub-segment located in the overlapping time coverage is determined from the second segment, wherein both the first segment and the second segment are video segments related to the monitored object; Based on a comparison result between the definition of the first sub-segment and the definition of the second sub-segment, deleting a video sub-segment with a lower definition, the video sub-segment being the first sub-segment or the second sub-segment; and The video segments related to the monitored object are traversed to complete the cropping process of the video segments related to the monitored object to obtain the processed video segments.

6. The method according to claim 5, further comprising determining the definition of the video sub-segment by any one of the following methods, or a combination of multiple methods: Determining the clarity of the video sub-segment based on the distance between the monitored object and the camera in the video sub-segment; Determining the definition of the video sub-segment based on the area of ​​the video screen occupied by the monitored object in the video sub-segment; The definition of the video sub-segment is determined based on the image definition of each of the multiple frames of video images included in the video sub-segment.

7. The method according to claim 4, wherein: The video cropping strategy includes cropping based on the relative position of the monitoring target and the camera; The method of using a video cropping strategy to crop video clips related to the monitored object to obtain processed video clips includes: For a first segment, when the time coverage of the first segment and the second segment overlaps, a first sub-segment located in the overlapping time coverage is determined from the first segment, and a second sub-segment located in the overlapping time coverage is determined from the second segment, wherein both the first segment and the second segment are video segments related to the monitored object; Based on a comparison result of a deviation of a relative posture between a monitoring target and a camera in the first sub-segment compared to a reference posture and a deviation of a relative posture between a monitoring target and a camera in the second sub-segment compared to the reference posture, deleting a video sub-segment with a larger deviation, the video sub-segment being the first sub-segment or the second sub-segment; and The video segments related to the monitored object are traversed to complete the cropping process of the video segments related to the monitored object to obtain the processed video segments.

8. The method according to claim 4, further comprising: When the number of video segments related to the monitored object is 1, or when the evaluation result indicates that there is no overlap in time coverage among the video segments related to the monitored object, a second video related to the monitored object is obtained based on the video segments related to the monitored object.

9. A video data processing device, comprising: A video acquisition module, used for acquiring video data to be stored in response to a video data storage request, wherein the video data includes a plurality of initial videos acquired by a plurality of cameras; An object detection module, configured to perform object detection on the plurality of initial videos based on preset object features to determine a plurality of monitoring objects; a segment extraction module, configured to extract video segments related to each monitored object from the multiple initial videos; and The segment processing module is used to process the video segments related to each of the multiple monitored objects to obtain compressed video data.

10. An electronic device comprising: one or more processors; a memory for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 8.

11. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, enables the processor to implement the method according to any one of claims 1 to 8.

12. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 8.

Images