Method, device and storage medium for processing surveillance video

Abstract

The application discloses a processing method and device of a monitoring video and a storage medium, relates to the technical field of electronic digital data processing, and the method comprises the following steps: when a playback request of a monitoring video is received, determining a storage medium where the monitoring video is located; when the storage medium is a magnetic tape, reading the monitoring video corresponding to the playback request from the magnetic tape and migrating the monitoring video to a disk; and reading and playing the monitoring video corresponding to the playback request in the disk. When the monitoring video is played back, the cold data in the magnetic tape is migrated to the disk, the long-term archiving advantages of low cost and large capacity of the magnetic tape are retained, the data positioning and loading time is significantly shortened through disk reading, and quick playback response is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electronic digital data processing, and in particular to a processing method and device for monitoring video and a storage medium. BACKGROUND

[0002] In a scenario dominated by massive cold data such as video monitoring, magnetic tape is generally used to save massive video. However, the use of a tape library reduces the unit cost, but is limited by sequential reading and writing and mechanical positioning. The retrieval time varies from minutes to hours, and cannot meet the immediate retrieval demand in an emergency. The efficiency of video data retrieval is low. SUMMARY

[0003] The main purpose of the present application is to provide a processing method and device for monitoring video and a storage medium, aiming to solve the technical problem of low efficiency of video data retrieval.

[0004] To achieve the above purpose, the present application provides a processing method for monitoring video, which comprises:

[0005] When a playback request for monitoring video is received, determining the storage medium in which the monitoring video is located;

[0006] When the storage medium is a magnetic tape, reading the monitoring video corresponding to the playback request from the magnetic tape and migrating the monitoring video to a disk;

[0007] Reading and playing the monitoring video corresponding to the playback request in the disk.

[0008] In an embodiment, the method comprises:

[0009] Grouping the monitoring video according to at least one of the spatial logical relationship, the time sequence logical relationship and the event logical relationship of the camera of the monitoring video; the spatial logical relationship includes the physical coordinates, the angle of view coverage and the direction association of the camera; the time sequence logical relationship includes the trigger sequence; and the event logical relationship includes the behavior association;

[0010] According to the grouping, storing the monitoring video in the magnetic tape.

[0011] In an embodiment, the step of reading the monitoring video corresponding to the playback request from the magnetic tape and migrating the monitoring video to the disk comprises:

[0012] According to the grouping corresponding to the playback request, determining the bandwidth adopted for data migration;

[0013] According to the bandwidth, migrating the monitoring video from the magnetic tape to the buffer area of the disk.

[0014] In an embodiment, the step of determining the bandwidth for data migration according to the group corresponding to the playback request comprises:

[0015] determining the priority of the playback request according to user authority and / or event urgency;

[0016] determining the bandwidth for data migration according to the data amount of the group corresponding to the playback request and the priority.

[0017] In an embodiment, the step of reading the surveillance video corresponding to the playback request from the magnetic tape and migrating the surveillance video to the disk comprises:

[0018] reading the surveillance video corresponding to the playback request from the magnetic tape and caching the read surveillance video to a disk buffer;

[0019] determining the playback rate of the surveillance video according to the playback request, selecting key frames in the surveillance video in the disk buffer according to the playback rate, and discarding video frames other than the key frames;

[0020] generating processed surveillance video according to the key frames and storing the processed surveillance video to the disk.

[0021] In an embodiment, the method comprises:

[0022] when the surveillance video is stored in a magnetic tape, acquiring video features corresponding to the surveillance video, wherein the video features comprise at least one of basic features, content features and historical features; the basic features comprise camera identification and / or labels; the content features comprise content importance scores and / or key event types; the historical features comprise historical access frequency of the surveillance video and / or average access time of similar videos;

[0023] inputting the video features into a prediction model to acquire a predicted migration time of the surveillance video output by the prediction model; wherein the prediction model is trained based on video training features corresponding to video training data and historical migration records;

[0024] reading the surveillance video from the magnetic tape at the predicted migration time and migrating the surveillance video to a disk.

[0025] In an embodiment, before the step of determining the storage medium where the surveillance video is located when a playback request of the surveillance video is received, the method further comprises:

[0026] determining camera identification and at least one label corresponding to a video segment of each of the surveillance videos;

[0027] According to the camera identifier and the at least one label, a video clip of the monitoring video is stored in the magnetic tape;

[0028] The step of reading the monitoring video corresponding to the playback request from the magnetic tape and migrating the monitoring video to a disk comprises:

[0029] According to the playback request, a label corresponding to the monitoring video is determined;

[0030] According to a correspondence between the label and an address of the monitoring video, an address of the monitoring video corresponding to the label is determined; the address comprises a start byte offset and an end byte offset of each video clip of the monitoring video;

[0031] According to the start byte offset and the end byte offset, the monitoring video is read from the magnetic tape and migrated to a disk.

[0032] In an embodiment, the method further comprises:

[0033] Scanning the monitoring video stored in the disk and a corresponding label;

[0034] According to a type of the label of the monitoring video, a call heat of the monitoring video is determined;

[0035] According to the call heat, a storage duration corresponding to the monitoring video is determined, and the monitoring video is migrated from the disk to the magnetic tape according to the storage duration;

[0036] Wherein, the higher the call heat is, the longer the storage duration of the monitoring video in the disk is, and the lower the call heat is, the shorter the storage duration of the monitoring video in the disk is.

[0037] In addition, to achieve the above-mentioned purpose, the present application also proposes a processing device of a monitoring video, the device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the processing method of the monitoring video as described above.

[0038] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer readable storage medium, the storage medium storing a computer program, the computer program being executed by a processor to implement the steps of the processing method of the monitoring video as described above.

[0039] In addition, to achieve the above object, the application further provides a computer program product, which comprises a computer program, and the computer program realizes the steps of the processing method of the monitoring video when executed by a processor.

[0040] The one or more technical solutions provided by the application have at least the following technical effects:

[0041] When receiving the playback request, it is firstly judged whether the monitoring video is stored on the tape; if it is confirmed that the monitoring video is stored on the tape, the monitoring video is automatically migrated to the disk, and then read and played from the disk. When the monitoring video is played back, the cold data in the tape is migrated to the disk, which not only retains the long-term archiving advantage of low cost and large capacity of the tape, but also significantly shortens the data positioning and loading time through disk reading, realizes fast playback response, and improves user experience and system availability. BRIEF DESCRIPTION OF DRAWINGS

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

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced as follows. Obviously, for those skilled in the art, other drawings can also be obtained based on these drawings without creative labor.

[0044] Figure 1 A flowchart is provided for the first embodiment of the processing method of the monitoring video of the application;

[0045] Figure 2 A brief flowchart is provided for the first embodiment of the processing method of the monitoring video of the application;

[0046] Figure 3 Another brief flowchart is provided for the first embodiment of the processing method of the monitoring video of the application;

[0047] Figure 4 A flowchart is provided for the second embodiment of the processing method of the monitoring video of the application;

[0048] Figure 5 A structural diagram is provided for the second embodiment of the processing method of the monitoring video of the application;

[0049] Figure 6 A flowchart is provided for the third embodiment of the processing method of the monitoring video of the application;

[0050] Figure 7Brief flowchart schematic diagram provided for the fourth embodiment of the method for processing surveillance video of the present application;

[0051] Figure 8 Brief flowchart schematic diagram provided for the fifth embodiment of the method for processing surveillance video of the present application;

[0052] Figure 9 Device structure schematic diagram of the hardware running environment involved in the method for processing surveillance video in the embodiments of the present application.

[0053] The object implementation, functional features and advantages of the present application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0054] It should be understood that the specific embodiments described herein are merely intended to explain the technical solutions of the present application, and are not intended to limit the present application.

[0055] In order to better understand the technical solutions of the present application, the following will be described in detail in conjunction with the drawings and specific embodiments of the specification.

[0056] In the scenario dominated by massive cold data such as video surveillance, magnetic tape is generally used to save massive video. However, the use of tape library reduces the unit cost, but is limited by sequential reading and writing and mechanical positioning, and the retrieval time consumption varies from minutes to hours, which cannot meet the immediate retrieval demand in emergency events, and the efficiency of video data retrieval is low.

[0057] The main solution of the embodiments of the present application is that when a playback request of surveillance video is received, the storage medium in which the surveillance video is located is determined; when the storage medium is a magnetic tape, the surveillance video corresponding to the playback request is read from the magnetic tape, and the surveillance video is migrated to a disk; the surveillance video corresponding to the playback request is read and played in the disk.

[0058] In the present embodiment, for the convenience of description, the following describes the processing device of surveillance video as the execution subject.

[0059] The present application provides a solution, when a playback request is received, first determine whether the surveillance video is stored on a magnetic tape; if it is confirmed to be stored on a magnetic tape, automatically migrate the surveillance video to a disk, and then read and play from the disk. When playing back the surveillance video, the cold data in the magnetic tape is migrated to the disk, which not only retains the long-term archiving advantage of low cost and large capacity of the magnetic tape, but also significantly shortens the data positioning and loading time through disk reading, realizes fast playback response, and improves user experience and system availability.

[0060] It should be noted that the execution subject of the 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 or the like, or an electronic device capable of realizing the above functions, a monitoring video processing device or the like. The embodiment and the following embodiments will be described below by taking the monitoring video processing device as an example.

[0061] Based on this, the embodiment of the present application provides a monitoring video processing method, which refers to Figure 1 , Figure 1 The figure is a flowchart of the first embodiment of the monitoring video processing method of the present application.

[0062] In the embodiment, the monitoring video processing method comprises steps S10-S30:

[0063] Step S10, when receiving a playback request of a monitoring video, determining a storage medium where the monitoring video is located.

[0064] In the embodiment, the storage medium of the monitoring video can be a disk or a magnetic tape or the like. The disk is used for real-time writing and high-frequency playback of data, and the magnetic tape is used for long-term storage of data.

[0065] In an embodiment, the playback request of the monitoring video comprises a playing demand of the monitoring video, the playing demand comprising a playing rate and / or a playing definition demand and the like, and the playing definition demand corresponding to a resolution, a code rate and an encoding standard demand and the like.

[0066] Optionally, the playback request of the monitoring video further comprises an identification of the monitoring video, a monitoring time period, a monitoring target and the like, a type of an alarm event and the like.

[0067] In an embodiment, before step S10, further comprising: writing a monitoring video stream as video data into a disk according to time slicing, and generating a storage medium mark of metadata of the video data; after the video data is migrated from the disk to the magnetic tape, updating the storage medium mark to locate the storage medium where the video data is located; step S10 comprises: determining the storage medium where the monitoring video is located according to the storage medium mark in the metadata, and realizing medium non-sensing access through metadata indexing.

[0068] Optionally, after step S10, further comprising: when the storage medium where the monitoring video is located is the disk, reading the monitoring video corresponding to the playback request in the disk, and when the storage medium is the magnetic tape, reading the monitoring video corresponding to the playback request from the magnetic tape, and migrating the monitoring video to the disk. For example, when the business system reads data, the data is stored in the disk storage subsystem, and the data is directly read from the disk storage subsystem, and the data is stored in the tape library subsystem, and the data is migrated back to the disk storage subsystem, and the data is read from the disk storage subsystem. Figure 2 ,

[0069] Optionally, a metadata index library is constructed to record the time stamp or storage location of the video in the tape or disk, and the locating of the monitoring video is accelerated by the time stamp or storage location.

[0070] In an optional embodiment, before step S10, there is further included: scanning the video data stored in the disk based on a preset period; migrating the video data from the disk to the tape when the storage duration of the video data is greater than a preset duration threshold value and / or the access frequency is less than a preset frequency threshold value; deleting the video data in the tape when the storage duration of the video data is greater than a preset upper limit of duration value. Optionally, when the storage duration of the video data is less than or equal to the preset duration threshold value and the access frequency is greater than the preset frequency threshold value, the video data is retained in the tape. The cold data is automatically migrated from the disk to the low-cost tape according to the double thresholds of the storage duration and the access frequency, and is completely deleted after the expiration, which ensures that the recent high-access video always resides in the disk and can be played back in seconds, maximally releases the expensive disk space and reduces the long-term archiving cost, and realizes the dynamic balance of performance and cost.

[0071] In an embodiment, referring to Figure 3 , the data is scanned according to a rule, the data migration is started when the data storage duration exceeds the hot data storage duration, the data is migrated from the disk storage subsystem to the tape library storage subsystem, and the data is deleted when the data storage duration expires.

[0072] In an embodiment, the video data is migrated from the disk to the tape according to the access frequency of the video data. Optionally, when the access frequency is less than a preset frequency threshold value, the video data is migrated from the disk to the tape. When the access frequency is greater than or equal to the preset frequency threshold value, the video data is retained in the disk.

[0073] In an embodiment, the video data is migrated to the tape according to the storage duration of the video data. When the storage duration is greater than a preset duration threshold value, the video data is migrated from the disk to the tape. When the storage duration is less than or equal to the preset duration threshold value, the video data is retained in the disk.

[0074] In an embodiment, the video data is migrated from the disk to the tape according to the access frequency and the access period of the video data. Optionally, when the access frequency is less than a preset frequency threshold value and is outside the access period, the video data is migrated from the disk to the tape. When the access frequency is greater than or equal to the preset frequency threshold value or is within the access period, the video data is retained in the disk.

[0075] In step S20, when the storage medium is a tape, the monitoring video corresponding to the playback request is read from the tape, and the monitoring video is migrated to a disk.

[0076] In a monitoring system, if the monitoring video stored in the tape needs to be played back, the video data in the tape should be sequentially read and completely migrated to a high-speed disk buffer such as an SSD (Solid State Drive) cache pool. Then, the video data is randomly read from the disk buffer according to the timestamp, restored to a playable format through demultiplexing and decoding, and finally output to a display terminal. Among them, the disk buffer is a temporary storage such as a dedicated cache disk, not a long-term storage, which can be persisted to the disk after data migration. Alternatively, a ring buffer is used to automatically overwrite expired data to avoid overflow. Among them, the storage is classified according to time or camera identifier, supplemented by database records of the path, retains a copy of the buffer, supports concurrent access, and deletes after migration.

[0077] If the tape data is a complete file such as an MP4 segment, it needs to be completely migrated to the disk before decoding and playing. If it is a streaming data such as TS (Transport Stream), it can be decoded while migrating, but the characteristics of sequential reading of the tape may cause delay fluctuations. If the tape stores raw encoded streams, it needs to be separated by a demultiplexer before decoding. If the tape stores a private format, it needs to be converted to a standard format before decoding.

[0078] When reading the monitoring video in the tape, the mechanical positioning of the tape takes time, and adjacent time period data can be preloaded, such as requesting 10:00-10:30, and additionally loading 9:50-10:40, using parallel reading of the tape library.

[0079] Alternatively, the periodicity of the monitoring video is determined according to the type of the monitoring video, and the predicted migration time of the monitoring video is determined according to the periodicity. The monitoring video corresponding to the playback request is read from the tape at the predicted migration time, and the monitoring video is migrated to the disk.

[0080] In an embodiment, when the monitoring video is stored in the tape, the camera identifier and the label corresponding to the monitoring video are obtained; the camera identifier and the label are input into a prediction model to obtain a predicted migration time of the monitoring video output by the prediction model; wherein the prediction model is trained based on the camera identifier, the label and the historical migration record corresponding to the video training data; the monitoring video is read from the tape at the predicted migration time, and the monitoring video is migrated to the disk. Determine the camera identifier and at least one label corresponding to each video segment of the monitoring video; according to the camera identifier and the at least one label, the video segments of the monitoring video are stored in the tape.

[0081] In an embodiment, the playback request is used to determine the playback requirement of the surveillance video, the playback requirement including resolution and / or bit rate; the surveillance video corresponding to the playback request is read from the tape and cached in a disk buffer; the surveillance video in the disk buffer is processed according to the resolution and / or bit rate, and the processed surveillance video is migrated to a disk.

[0082] In an embodiment, the surveillance video in the disk buffer is processed according to the resolution, and the processed surveillance video is migrated to the disk. Alternatively, the surveillance video in the disk buffer is encoded according to the bit rate, and the encoded surveillance video is migrated to the disk. Alternatively, the surveillance video in the disk buffer is processed according to the resolution, and the processed surveillance video is encoded according to the bit rate, and the encoded surveillance video is migrated to the disk.

[0083] In an embodiment, the surveillance video in the disk buffer is encoded according to the bit rate, and the encoded surveillance video is migrated to the disk. By dynamically re-encoding the original surveillance video in the disk buffer according to the adjusted bit rate, the file size can be compressed within an acceptable range of image quality, and the valuable online disk space is immediately released; the low-bit-rate file after re-encoding is still first stored on the disk to ensure the second-level review of the emergency event, and is batch-migrated to the tape for long-term archiving after it is completely cooled down, thereby significantly reducing the disk expansion, depreciation and tape offline capacity costs without sacrificing instant availability. Alternatively, the bit rate is dynamically adjusted according to the scene complexity, wherein a high bit rate is used in a motion state and a low bit rate is used in a static state.

[0084] In an optional embodiment, before step S10, there is further included: determining the camera identifier and at least one label corresponding to each video segment of the surveillance video; and storing the video segments of the surveillance video in the tape according to the camera identifier and the at least one label. Step S20 includes: determining the label corresponding to the surveillance video according to the playback request; determining the address of the surveillance video corresponding to the label according to the correspondence between the label and the address of the surveillance video; the address including the start byte offset and the end byte offset of each video segment of the surveillance video; reading the surveillance video from the tape according to the start byte offset and the end byte offset, and migrating the surveillance video to the disk.

[0085] It should be noted that a monitoring video is divided into at least two video segments, each video segment is labeled with a label, for example, the label is a person, when storing the monitoring video, the video segments of the monitoring video are sequentially stored in the tape according to the camera identifier and the label, so that the longer monitoring video can be sequentially read during playback, and the reading efficiency is improved. The video is segmented into segments, each segment has a clear byte offset, which is particularly suitable for linear storage media such as tapes. The tape is a sequential access device and does not support random read and write, so the data position can be accurately positioned by the offset, and the reading time is reduced. The segment design also facilitates processing of large video files, allows partial reading, and improves efficiency.

[0086] A mapping relationship such as a database table or a configuration file is maintained to associate the label with the physical storage address of the video. The address includes the start byte offset and the end byte offset of each video segment. This step is logically coherent, the label serves as an intermediary to connect the abstract request and the specific storage location, avoiding the complexity of directly operating the underlying storage.

[0087] In step S30, the monitoring video corresponding to the playback request is read and played in the disk.

[0088] In the embodiment, the data stream of the monitoring video is read, the data stream is video decoded, and the decoded video frame sequence is rendered and output according to the playback timing.

[0089] In an optional embodiment, since the monitoring video may be discontinuous physical addresses when written to the disk, the storage location information of the monitoring video in the disk is obtained, the storage location information includes the start byte offset and the end byte offset of each video segment of the monitoring video; the monitoring video is obtained and decoded according to the start byte offset and the end byte offset, and the decoded monitoring video is played. The start byte offset and the end byte offset abstract the physical fragmentation of the file system or the RAID (Redundant Array of Independent Disks, independent disk redundancy array) into a logically continuous data stream, and only one I / O (Input / Output, input / output) scheduling is required during reading, which greatly reduces the head movement or flash random read amplification, reduces the delay and CPU (Central Processing Unit, central processing unit) occupation. The offset directly corresponds to the recording time point, and millisecond-level jumping can be achieved. Compared with the traditional two-level index of finding the file first and then finding the GOP (Group of Pictures, image group), the overhead of parsing the index table in the container layer is saved, which is suitable for random playback and alarm backtracking of massive monitoring.

[0090] In an embodiment, when the playback request of the monitoring video comprises a request for monitoring video of a preset target, storage media where at least two monitoring videos of the preset target are respectively located are determined; when the storage media comprises a magnetic tape, the monitoring video is migrated from the magnetic tape to a disk, and the monitoring video corresponding to the playback request is read in the disk; when the storage media comprises a disk, the monitoring video corresponding to the playback request is read in the disk; and finally, the at least two monitoring videos of the preset target are outputted in combination. Optionally, a user-selected face region and / or scene region are acquired; and the preset target corresponding to the playback request is determined according to the face region and / or scene region.

[0091] In an embodiment, when the playback request of the monitoring video comprises a type of alarm event, the monitoring video associated with the type of alarm event is determined according to the type of alarm event, and storage media where the associated monitoring video is located are determined; when the storage media is a magnetic tape, the monitoring video corresponding to the playback request is read from the magnetic tape and migrated to a disk; the monitoring video corresponding to the playback request is read and played in the disk. When the storage media comprises a disk, the monitoring video corresponding to the playback request is read in the disk; and finally, the associated monitoring video is outputted in combination.

[0092] In the technical solution of the embodiment, when a playback request is received, it is firstly judged whether the monitoring video is stored in a magnetic tape; if it is confirmed that the monitoring video is stored in the magnetic tape, the monitoring video is automatically migrated to a disk, and then read and played from the disk. When the monitoring video is played back, cold data in the magnetic tape is migrated to the disk, so that the long-term archiving advantage of low cost and large capacity of the magnetic tape is retained, the data positioning and loading time is significantly shortened through disk reading, fast playback response is realized, and user experience and system availability are improved.

[0093] Based on the first embodiment, in the second embodiment, the same or similar contents as the above embodiments can be referred to the above description, and will not be described hereinafter. On this basis, please refer to Figure 4 , the method further comprises:

[0094] In step S40, the monitoring video is grouped according to at least one of a spatial logical relationship, a time sequence logical relationship and an event logical relationship of a camera of the monitoring video; the spatial logical relationship comprises physical coordinates, angle coverage and direction association of the camera; the time sequence logical relationship comprises triggering sequence; and the event logical relationship comprises behavior association.

[0095] In step S50, the monitoring video is stored in the magnetic tape according to the grouping.

[0096] Please refer to Figure 5The magnetic tapes can be multiple, and the magnetic disks can be multiple, video data is read from different magnetic tapes to the disk buffer based on a playback request, and the video data is processed in the disk buffer, and the processed video data is stored in the disk. Alternatively, video data is read from different magnetic tapes to the disk buffer based on different playback requests, and the video data is processed in the disk buffer, and the processed video data is stored in the disk.

[0097] In the embodiment, the spatial logical relationship includes physical coordinates of the camera, angle coverage, and direction association. The physical coordinates include absolute or relative positions of the camera in three-dimensional space, such as building coordinates or relative distances. The angle coverage includes an overlapping field of view to form a stereoscopic monitoring, and the angle coverage includes a blind area complement, which is not seen by B. The direction association, for example, camera A shoots the entrance facing east, and camera B shoots the exit facing west, forming an entry and exit relationship. The time logical relationship includes trigger sequence and time zone synchronization. The trigger sequence, for example, when camera A detects a license plate in a parking lot, triggers camera B to capture the driver. The time zone synchronization is because the time stamps of the cameras across time zones need to be unified, otherwise the event sequence will be disordered. The event logical relationship includes behavior association, for example, if camera A identifies a person who drops suspicious garbage, and camera B tracks the person within 5 seconds.

[0098] In an optional embodiment, the step of reading the monitoring video corresponding to the playback request from the magnetic tape and migrating the monitoring video to the disk includes: determining a bandwidth for data migration according to a group corresponding to the playback request; and migrating the monitoring video from the magnetic tape to the buffer of the disk according to the bandwidth. The larger the data amount of the group corresponding to the playback request, the larger the required bandwidth, and the smaller the data amount of the group, the smaller the required bandwidth.

[0099] In an optional embodiment, the step of determining the bandwidth for data migration according to the group corresponding to the playback request includes: determining a priority of the playback request according to user authority and / or event urgency; and determining the bandwidth for data migration according to the data amount of the group corresponding to the playback request and the priority.

[0100] In the embodiment, the data consumption amount is the total amount of video data that needs to be read and decoded from the data source per second in the video playback and migration scenario.

[0101] Optionally, the user authority is a high-level management authority, and the priority of the playback request is high, the user authority is a normal management authority, and the priority of the playback request is low. Optionally, the higher the event urgency, the higher the priority of the playback request, and vice versa, the lower the event urgency, the lower the priority of the playback request. Optionally, a first priority of the playback request is determined according to the user authority, a second priority of the playback request is determined according to the time urgency, and the priority of the playback request is determined according to a preset weight parameter, the first priority, and the second priority.

[0102] Optionally, when the data volume is greater than the preset data volume threshold and the priority is greater than the preset priority threshold, it is determined that the data migration adopts the first bandwidth; when the data volume is greater than the preset data volume threshold or the priority is greater than the preset priority threshold, it is determined that the data migration adopts the second bandwidth; when the data volume is less than or equal to the preset data volume threshold and the priority is less than or equal to the preset priority threshold, it is determined that the data migration adopts the third bandwidth, wherein the first bandwidth is greater than the second bandwidth, and the second bandwidth is greater than the third bandwidth.

[0103] In the technical scheme of the embodiment, the monitoring video is written into the tape after being intelligently grouped according to the space between cameras, the time sequence or the event logical relationship, so that the data carries index information of a scene, behavior and time at a physical layer; when searching, the required segment can be quickly located according to the logical relationship without sequentially scanning the whole tape, so that the search time is significantly shortened, the reading cost is reduced, irrelevant data is reduced, the storage utilization rate and the overall response efficiency of the system are improved.

[0104] Based on the first or second embodiment of the present application, in the third embodiment of the present application, the same or similar contents as the above embodiments can be referred to the above introduction, and will not be described in detail. On this basis, please refer to Figure 6 , step S20 comprises:

[0105] Step S21, reading the monitoring video corresponding to the playback request from the tape and caching the read monitoring video to a disk buffer;

[0106] Step S22, determining a playing rate of the monitoring video according to the playback request, selecting a key frame in the monitoring video in the disk buffer according to the playing rate, and discarding video frames other than the key frame;

[0107] Step S23, generating a processed monitoring video according to the key frame, and storing the processed monitoring video to the disk.

[0108] Optionally, in the scene of high-speed playing, only I frames, i.e. key frames, are extracted to reduce the data volume. In the scene of low-speed playing, intermediate frames are generated by interpolation to increase motion blur processing to avoid lag.

[0109] In an embodiment, the key frame is selected in the monitoring video in the disk buffer according to the playing rate; and the frame-extracted processed monitoring video is generated according to the key frame. By accurately selecting the key frame in the disk buffer according to the playing rate and generating the frame-extracted video, the data volume can be compressed without losing the overall picture of the event, and the expensive disk space is immediately released; at the same time, the key frame sequence still retains the complete time sequence, and the disk end can continue to provide second-level fast browsing.

[0110] Optionally, the monitoring video is uniformly or key frame extracted. Optionally, in high-speed playback, key frames or I frames are extracted, in low-speed playback, difference frames are filled, and in normal speed, complete frames are retained.

[0111] Key frame extraction of the monitoring video is to eliminate redundant frames while retaining key information, thereby improving storage efficiency and subsequent analysis efficiency. The key information includes dynamic target behavior, abnormal event, important state change, etc.

[0112] In an embodiment of extracting key frames, a target detection model is used to identify targets in the video in real time, such as people, vehicles, and objects, and then a behavior recognition model is used to analyze the semantic behavior of the targets, such as people falling, vehicles suddenly braking, and objects abnormally moving. A semantic key event library is set, such as people gathering and fighting, vehicles reversing and being dangerous, and objects being left suspiciously, and when an event in the semantic key event library is detected, key frame extraction is automatically triggered and the event type is marked, such as people falling at 15 o'clock.

[0113] Optionally, meaningless motion is semantically filtered, and only frames related to target key behavior are retained as key frames. For example, in a campus monitoring, the motion of a tree branch blown by the wind is filtered, while the action of a student climbing over a fence is determined as a key event, and the video frame at that moment is extracted as a key frame.

[0114] In an embodiment of extracting key frames, multi-modal information outside the video is fused to extract key frames, including audio, sensors, environmental data, etc., breaking through the information limitation of relying only on video frames, and capturing key events that cannot be found by a single modality.

[0115] Optionally, in a monitoring scene, audio signals such as glass breaking, cries for help, and abnormal sounds are often strongly related to key events such as theft and conflict. An audio event detection model is used to identify abnormal audio, such as screams indicating an emergency event and continuous knocking indicating damage, and the video frame at the corresponding moment is extracted synchronously.

[0116] Optionally, environmental sensor data is fused to extract key frames, such as environmental sensor data including light intensity, temperature and humidity, and vibration sensors. When the light changes dramatically on a rainy or night, the video motion sensitivity is reduced to avoid misjudging frames with raindrops or light changes as key frames. When a vibration sensor detects a severe vibration such as wall knocking, the video sensitivity to small motion is increased to capture abnormalities near the vibration source.

[0117] In an embodiment of extracting key frames, based on the continuity of video timing, fewer frames are used to retain complete event logic, avoiding repeated extraction of consecutive similar frames, and improving storage efficiency.

[0118] Optionally, a time sequence model such as a Transformer or an LSTM (Long Short-Term Memory) is used to learn the time sequence correlation between frames, such as the continuous action logic of personnel walking, turning, and staying, and to identify the information inflection point in the time sequence, that is, the frame that can represent the core logic of a continuous behavior, such as the turning being the key transition from walking to staying. For example, in a video of a vehicle from entering to parking, the time sequence model only extracts the three key frames of entering the intersection, turning on the turn signal, and stopping, and the complete process can be restored through the time sequence correlation between the frames.

[0119] Optionally, redundant time sequence segments such as static backgrounds without targets are time compressed, and only the first and last frames of the segments are retained; and high information density segments such as multi-person interaction are time expanded, and the key frame extraction frequency is increased.

[0120] In an embodiment of extracting key frames, in a large amount of unannotated monitoring videos, the model learns key frame features through self-learning of positive and negative samples, wherein the positive samples represent representative frames in the same event, such as frames of the initial fire and the expanding fire; and the negative samples represent redundant frames, such as repeated frames of static backgrounds. The model automatically masters the rule that a key frame is a frame with significant information increment through contrastive learning. The model incorporates diversified scenes such as shopping malls, factories, communities, and highways in the training, and through domain adaptation technology, the model can still accurately extract frames in new scenes, solving the problem of adjusting parameters in traditional solutions when changing scenes.

[0121] In the technical solution of the embodiment, by extracting frames of the monitoring video in the disk buffer at a play rate before migration to the disk, both key pictures required for event backtracking and redundant frames are greatly reduced, thereby compressing the volume of cold data, directly reducing the long-term archiving capacity and bandwidth occupation of the tape end, and at the same time, the monitoring video after frame extraction is written to the disk, and can continue to meet the requirement of second-level fast retrieval.

[0122] Based on any one of the first to third embodiments of the present application, in the fourth embodiment of the present application, the same or similar contents as the above embodiments can be referred to the above introduction, and will not be described in detail. On this basis, please refer to Figure 7 , the method comprises:

[0123] Step S60, when the monitoring video is stored in the tape, acquiring video features corresponding to the monitoring video, wherein the video features include at least one of basic features, content features, and historical features; the basic features include camera identification and / or labels; the content features include content importance scores and / or key event types; and the historical features include historical access frequencies of the monitoring video and / or average retrieval times of similar videos;

[0124] Step S70, input the video features into a prediction model to obtain a predicted migration time of the monitoring video output by the prediction model; wherein the prediction model is trained based on video training features corresponding to video training data and historical migration records;

[0125] Step S80, read the monitoring video from the magnetic tape at the predicted migration time and migrate the monitoring video to the disk.

[0126] In this embodiment, the predicted migration time is prior to the time when the playback request is received, or the predicted migration time is prior to the time when the video playback of the playback request is played back. Alternatively, the predicted migration time can be a time point or a time period.

[0127] The basic features include camera identifiers and / or labels, wherein the camera identifiers are used to distinguish different area or angle cameras, and the labels can be person labels, event labels, object labels, etc.

[0128] The content features include content importance scores and / or key event types, content analysis is performed on the monitoring video stored in the magnetic tape to identify whether a key event is contained and determine the key event type, wherein the key event includes an abnormal event such as a personnel conflict or a vehicle accident, and the key event includes an event of a high access probability scene such as a dynamic picture of an entrance or an accident-prone area. The content importance score quantifies the content importance, and an exemplary content importance score is 0.9 for an abnormal event, 0.1 for a static picture without a key target. The key target includes a specified person or a suspicious object.

[0129] The historical features include a historical access frequency of the monitoring video and / or an average review time of similar videos. The similar videos are videos of the same type as the monitoring video, or multiple videos corresponding to the same event.

[0130] Alternatively, the prediction model is trained based on video training features of video training data and migration records migrated from the magnetic tape to the disk, and the video training data is composed of historical monitoring videos. In this embodiment, the prediction model can be an LSTM model. By using the prediction model trained based on the historical migration records, the predicted migration time of the monitoring video most likely to be reviewed during the storage of the magnetic tape can be calculated in advance, and the monitoring video can be pre-fetched from the magnetic tape to the disk before the playback request actually arrives; in this way, the advantages of low-cost long-term storage of the magnetic tape can be continued, and the mechanical loading delay of minutes or even hours is compressed to almost zero, which significantly improves the instant review experience in emergency events.

[0131] Optionally, based on the prediction model, the monitoring video to be migrated and the predicted migration time are determined, before receiving the playback request, the monitoring video to be migrated is read from the tape at the predicted migration time, and the monitoring video to be migrated is migrated to the disk. By predicting the most likely playback of the monitoring video and its time point in advance through the prediction model, the corresponding monitoring video is prefetched from the tape to the disk before the user actually initiates the playback request, so that the data is ready when the user clicks to play back, realizing a near-disk zero-waiting experience, while avoiding the waste of disk space caused by blind preloading, and balancing the response speed and storage resource utilization.

[0132] In the technical solution of the embodiment, the prediction migration time of the monitoring video is calculated in advance through the prediction model, the corresponding monitoring video is prefetched from the tape to the disk before the user actually initiates the playback request, so that the data is ready when the user clicks to play back, realizing a near-disk zero-waiting experience, while avoiding the waste of disk space caused by blind preloading, and balancing the response speed and storage resource utilization.

[0133] Based on any one of the first to fourth embodiments of the present application, in the fifth embodiment of the present application, the same or similar contents as the above embodiments can be referred to the above introduction, and will not be described hereinafter. On this basis, please refer to Figure 8 , the method further comprises:

[0134] Step S90, scanning the monitoring video stored in the disk and the corresponding label;

[0135] Step S100, determining the call heat of the monitoring video according to the type of the label of the monitoring video;

[0136] Step S110, determining the storage duration corresponding to the monitoring video according to the call heat, and migrating the monitoring video from the disk to the tape according to the storage duration.

[0137] In the embodiment, the higher the call heat, the longer the storage duration of the monitoring video in the disk, and the lower the call heat, the shorter the storage duration of the monitoring video in the disk.

[0138] Optionally, for the high-heat label video, the scanning period is shortened to ensure that the heat change can be captured in time, such as the heat rising after a sudden call, and the video is not temporarily migrated; for the low-heat label video, the scanning period is extended to reduce the occupation of the disk performance by invalid scanning. For example, when a certain video is called ≤1 time in the last 1 hour, and the total call in the last 7 days is ≤3 times, a low-heat warning is automatically triggered, and the preset period is not needed to wait, and the migration evaluation process is directly entered. For example, the monitoring label of a certain warehouse is a goods storage area, but there is no call for 15 consecutive days, and the system detects it in real time, and the migration to the tape is started in advance to release the disk space.

[0139] Optionally, the labels of the monitoring video include people, animals, objects, events, etc., different label types correspond to different call heat, and different labels correspond to different call heat in different time periods.

[0140] In an embodiment, the call heat of the monitoring video is determined according to the type of the label of the monitoring video and the label corresponding to the high-frequency event of the current time period.

[0141] Optionally, after determining the call heat of the monitoring video according to the type of the label of the monitoring video, if the monitoring video contains an abnormal event or a key target, the call heat is increased, and if the monitoring video is a pure static picture or meaningless repeated content, the call heat is reduced.

[0142] Optionally, the call heat of the monitoring video is determined according to at least two of the type of the label of the monitoring video, the call duration, the call subject, and the associated call. Wherein, the call duration, such as single viewing is greater than a preset duration, determines that the call heat is high, and only quick browsing determines that the call heat is low; the call subject, such as multiple calls by security personnel, determines that the call heat is high, and occasional viewing by ordinary employees determines that the call heat is low; the associated call, such as a video being called multiple times as event-associated evidence, determines that the call heat is high.

[0143] In an embodiment, the storage duration corresponding to the monitoring video is determined according to the call heat, including: storage duration = max (heat determined duration, compliance minimum duration).

[0144] In the technical scheme of the embodiment, by dynamically determining the retention duration of data in the disk according to the call heat, the high-value video with frequent access is kept in the high-speed disk as much as possible, and the low-frequency video is migrated to the low-cost tape as soon as possible, so that the hot data is quickly responded while the online storage capacity and the overall cost are significantly reduced, and the optimal balance between performance and cost of the monitoring video storage is realized.

[0145] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the processing method of the monitoring video of the present application. More forms of simple transformation based on this technical concept are within the protection scope of the present application.

[0146] The present application provides a monitoring video processing device, which comprises at least one processor and a memory in communication connection with the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the monitoring video processing method in the above-mentioned embodiment one.

[0147] The following refers to Figure 9The diagram illustrates a structural schematic of a video processing device suitable for implementing embodiments of this application. The video processing device in these embodiments may include, but is not limited to, mobile terminals such as laptops, tablets (PADs), portable multimedia players (PMPs), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 9 The video processing device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0148] like Figure 9 As shown, the video surveillance processing device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the video surveillance processing device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the video surveillance processing equipment to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows video surveillance processing equipment with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems may be implemented alternatively.

[0149] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program codes for executing the method shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiments disclosed in the present application are executed.

[0150] The processing device for monitoring video provided by the present application adopts the monitoring video processing method in the above-mentioned embodiments, and can solve the technical problem of low efficiency of video data retrieval. Compared with the prior art, the processing device for monitoring video provided by the present application has the same beneficial effects as the monitoring video processing method provided by the above-mentioned embodiments, and other technical features in the processing device for monitoring video are the same as the features disclosed in the previous embodiment method, which will not be repeated here.

[0151] It should be understood that various parts of the present application can be realized by hardware, software, firmware or a combination thereof. In the description of the above-mentioned embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0152] The above is merely specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0153] The present application provides a computer readable storage medium having stored thereon computer readable program instructions (i.e. computer program) for executing the monitoring video processing method in the above-mentioned embodiments.

[0154] The computer readable storage medium provided in the application may be, for example, a U disk, but is not limited to an electric, magnetic, optical, electromagnetic, infrared, or semiconductor system or device, or any combination thereof. More specific examples of the computer readable storage medium may include, but are not limited to, an electric connection with one or more conductive 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 thereof. In the embodiment, the computer readable storage medium may be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, a system, or a device. The program code contained in the computer readable storage medium can be transmitted by any suitable medium, including but not limited to an electric wire, an optical cable, a radio frequency (RF), or the like, or any suitable combination thereof.

[0155] The computer readable storage medium described above may be contained in a processing device for monitoring video, or may exist separately without being assembled into the processing device for monitoring video.

[0156] The computer readable storage medium described above carries one or more programs, which, when executed by the processing device for monitoring video, cause the processing device for monitoring video to: when a playback request is received, first determine whether the monitoring video is stored on a tape; if it is confirmed that the monitoring video is stored on the tape, automatically migrate the monitoring video to a disk, and then read and play from the disk. When the monitoring video is played back, the cold data in the tape is migrated to the disk, which not only retains the low-cost and large-capacity long-term archiving advantage of the tape, but also significantly shortens the data positioning and loading time through disk reading, realizes fast playback response, and improves user experience and system availability.

[0157] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can 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 the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0158] The flow diagrams and the block diagrams in the drawings are meant as possible implementations of systems, methods, and computer program products according to the embodiments of the application. In this regard, each block in the flow diagrams and the block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks can sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flow diagrams, and combinations thereof, can be implemented by special purpose hardware-based systems that perform the specified functions or operations, or combinations of special purpose hardware and computer instructions.

[0159] The modules involved in the embodiments of the present application can be implemented in software or hardware. In some cases, the names of the modules do not constitute a limitation on the modules themselves.

[0160] 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 processing method of the monitoring video, and can solve the technical problem of low efficiency of video data retrieval. Compared with the prior art, the computer readable storage medium provided by the present application has the same beneficial effects as the processing method of the monitoring video provided by the above-mentioned embodiments, which will not be repeated here.

[0161] The application further provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of the method for processing monitoring video as described above.

[0162] The computer program product provided by the application can solve the technical problem of low efficiency of video data retrieval. Compared with the prior art, the beneficial effects of the computer program product provided by the application are the same as those of the method for processing monitoring video provided by the above-mentioned embodiments, and are not described here.

[0163] The above only describes some embodiments of the application, and does not limit the patent scope of the application. Any equivalent structural transformation, direct / indirect application in other related technical fields, or direct / indirect application in other related technical fields based on the technical concept of the application and the content of the specification and drawings are included in the patent protection scope of the application.

Claims

1. A processing method of monitoring video, characterized by, The method for processing the monitoring video comprises: When the monitoring video is stored in a tape, obtaining video features corresponding to the monitoring video; Inputting the video features into a prediction model to obtain a predicted migration time of the monitoring video output by the prediction model; wherein the prediction model is trained based on video training features corresponding to video training data and historical migration records; Reading the monitoring video from the tape at the predicted migration time and migrating the monitoring video to a disk; When a playback request of the monitoring video is received, determining a storage medium in which the monitoring video is located; the storage medium comprises a tape or a disk; When the storage medium in which the monitoring video is located is a disk, reading the monitoring video corresponding to the playback request in the disk; When the storage medium is a tape, reading the monitoring video corresponding to the playback request from the tape and migrating the monitoring video to a disk; Reading and playing the monitoring video corresponding to the playback request in the disk; When the monitoring video is stored, grouping the monitoring video according to a spatial logical relationship, a time sequence logical relationship and an event logical relationship of a camera of the monitoring video; the spatial logical relationship comprises physical coordinates, angle coverage and direction association of the camera; the time sequence logical relationship comprises a trigger sequence; the event logical relationship comprises behavior association; and storing the monitoring video in the tape according to the grouping.

2. The processing method of claim 1, wherein, The step of reading the monitoring video corresponding to the playback request from the tape and migrating the monitoring video to a disk comprises: Determining a bandwidth adopted for data migration according to a grouping corresponding to the playback request; Migrating the monitoring video from the tape to a buffer area of the disk according to the bandwidth.

3. The processing method of claim 2, wherein, The step of determining the bandwidth adopted for data migration according to the grouping corresponding to the playback request comprises: Determining a priority of the playback request according to user authority and / or event emergency level; Determining the bandwidth adopted for data migration according to a data amount of the grouping corresponding to the playback request and the priority.

4. The processing method of claim 1, wherein, The step of reading the monitoring video corresponding to the playback request from the tape and migrating the monitoring video to a disk comprises: Reading the monitoring video corresponding to the playback request from the tape and buffering the read monitoring video to a disk buffer area; Determining a playing rate of the monitoring video according to the playback request, selecting key frames in the monitoring video in the disk buffer area according to the playing rate, and discarding video frames other than the key frames; Generating a processed monitoring video according to the key frames and storing the processed monitoring video to the disk.

5. The processing method of claim 1, wherein, The video features comprise at least one of a basic feature, a content feature and a historical feature; the basic feature comprises a camera identifier and / or a label; the content feature comprises a content importance score and / or a key event type; and the historical feature comprises a historical access frequency of the monitoring video and / or an average review time of similar videos.

6. The processing method of claim 1, wherein, Before the step of determining the storage medium in which the monitoring video is located when the playback request of the monitoring video is received, the method further comprises: determining a camera identifier and at least one label corresponding to each video clip of the surveillance video; storing the video clip of the surveillance video in the tape according to the camera identifier and the at least one label; the step of reading the surveillance video corresponding to the playback request from the tape and migrating the surveillance video to a disk comprises: determining a label corresponding to the surveillance video according to the playback request; determining an address of the surveillance video corresponding to the label according to a correspondence between the label and the address of the surveillance video; the address comprising a start byte offset and an end byte offset of each video clip of the surveillance video; reading the surveillance video from the tape and migrating the surveillance video to a disk according to the start byte offset and the end byte offset.

7. The processing method of claim 1, wherein, The method further comprises: scanning the surveillance video stored in the disk and a corresponding label; determining a call heat of the surveillance video according to a type of the label of the surveillance video; determining a storage duration corresponding to the surveillance video according to the call heat, and migrating the surveillance video from the disk to the tape according to the storage duration; wherein the higher the call heat, the longer the storage duration of the surveillance video in the disk, and the lower the call heat, the shorter the storage duration of the surveillance video in the disk.

8. A processing device for monitoring video, characterized in that The processing device of the surveillance video comprises a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the processing method of the surveillance video according to any one of claims 1 to 7.

9. A storage medium, characterized by The storage medium is a computer readable storage medium, and the storage medium stores a computer program, the computer program being executed by the processor to implement the steps of the processing method of the surveillance video according to any one of claims 1 to 7.

Images