Intelligent event video retrieval data storage and display method

Abstract

The invention relates to an intelligent event video retrieval data storage and display method, which comprises the following steps: acquiring video data of each video source, and inserting a track area number of a track area where a target appears in a video frame in which the target is identified to exist; according to the target identifier of the target, the time information and the track area number, track data are obtained and stored; based on the track area number and the retrieval condition of the time information, retrieving from the track data to obtain a target identifier of the corresponding target; corresponding target video data are obtained through integration based on the target identifier; and playing the target video data corresponding to the target identifier in a display window, and displaying the corresponding target attribute. By means of the video retrieval method and device, the track area number of the target can be inserted into the video frame with the target, the track data are formed and stored, the target video data of the needed target can be rapidly obtained and played based on the track area number and the time information during retrieval, and the problem that the video retrieval efficiency is low is solved.

Description

Technical Field

[0001] This application relates to the technical field of video surveillance, and particularly to a method for storing and displaying intelligent event video retrieval data. Background Art

[0002] In the field of video surveillance, intelligent applications are becoming increasingly popular. It is possible to find targets that appear in the video frame through video analysis, such as vehicles and pedestrians invading the perimeter, lost items, etc.

[0003] Currently, after analyzing and finding the appeared target, only the image of the target or a related video can be displayed. For users, it is difficult to quickly retrieve the required video frame and present it, resulting in low video retrieval efficiency.

[0004] Regarding the problem of low video retrieval efficiency in the related art, no effective solution has been proposed yet. Summary of the Invention

[0005] Based on this, in view of the above technical problems, it is necessary to provide a method for storing and displaying intelligent event video retrieval data that can improve video retrieval efficiency.

[0006] In a first aspect, in the present embodiment, a method for storing and displaying intelligent event video retrieval data is provided, including:

[0007] Obtain the video data of each video source, and insert the track area number of the track area where the target appears in the video frame where the target is identified;

[0008] Obtain track data according to the target identifier, time information, and the track area number of the target, and store the track data;

[0009] Based on the retrieval condition of the track area number and time information, retrieve the target identifier corresponding to the target from the track data; and integrate the corresponding target video data based on the target identifier;

[0010] Play the target video data corresponding to the target identifier in the display window, and display the corresponding target attributes.

[0011] In some of the embodiments, the method further includes:

[0012] Pre-divide the picture of the video data into different track areas, and set the corresponding track area numbers; the track areas adopt a multi-level structure.

[0013] In some of the embodiments, the inserting the track area number of the track area where the target appears in the video frame where the target is identified includes:

[0014] Identify video frames with a target in the video data;

[0015] Compare the position where the target appears with a pre-divided trajectory area, determine the trajectory area number corresponding to the target, and insert the trajectory area number into the video frame.

[0016] In some embodiments, the method further includes:

[0017] Insert a target entry flag into the video frame when it is identified that the target enters the screen;

[0018] Insert a target exit flag into the video frame when it is identified that the target leaves the screen.

[0019] In some embodiments, the trajectory data includes frame description information and the trajectory area numbers, target identifiers, target entry flags, or target exit flags of different targets in each time information.

[0020] In some embodiments, the method further includes:

[0021] When it is identified that the target enters and / or leaves the screen, report a target event, and store the time information of the target event, the target identifier, and the target attributes of the target as event data;

[0022] When the target identifier corresponding to the target is retrieved from the trajectory data, retrieve the target attributes from the event data based on the target identifier.

[0023] In some embodiments, the method further includes:

[0024] When playing the video data of each video source in the display window, synchronously detect the trajectory area number in the video data, and the target entry flag or the target exit flag;

[0025] When detecting the trajectory area number and the target entry flag, play the video data with a first playback configuration and display the corresponding target attributes;

[0026] When detecting the trajectory area number and the target exit flag, or when the trajectory area number is not detected, play the video data with a second playback configuration;

[0027] The first playback configuration includes: playing the video data at a first preset speed; the second playback configuration includes: playing the video data at a second preset speed, or skipping the video data; the first preset speed is less than the second preset speed.

[0028] Second aspect, in this embodiment, a device for intelligent event video retrieval data storage and display is provided, including:

[0029] A storage module, configured to obtain video recording data of each video source, insert a track area number of the track area where the target appears into the video frames where the target is identified; obtain track data based on the target identifier, time information of the target, and the track area number, and store the track data;

[0030] A retrieval module, configured to retrieve the target identifier corresponding to the target from the track data based on the retrieval conditions of the track area number and time information; and integrate the corresponding target video recording data based on the target identifier;

[0031] A display module, configured to play the target video recording data corresponding to the target identifier in a display window and display corresponding target attributes.

[0032] Third aspect, in this embodiment, a computer device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the method for intelligent event video retrieval data storage and display described in the first aspect above is implemented.

[0033] Fourth aspect, in this embodiment, a storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the method for intelligent event video retrieval data storage and display described in the first aspect above is implemented.

[0034] Compared with the related art, in a method for intelligent event video retrieval data storage and display provided in this embodiment, by obtaining video recording data of each video source, inserting a track area number of the track area where the target appears into the video frames where the target is identified; obtaining track data based on the target identifier, time information of the target, and the track area number, and storing the track data; retrieving the target identifier corresponding to the target from the track data based on the retrieval conditions of the track area number and time information; integrating the corresponding target video recording data based on the target identifier; playing the target video recording data corresponding to the target identifier in a display window and displaying corresponding target attributes. Through this embodiment, it is possible to insert the track area number of the target into the video frames where the target exists, and form track data for storage. When retrieving, it is possible to quickly obtain the target video recording data of the required target based on the track area number and time information and play it, solving the problem of low video retrieval efficiency.

[0035] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more comprehensible. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings described herein are used to provide a further understanding of the present application and form a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation to the present application. In the drawings:

[0037] Figure 1 is a hardware structure block diagram of a terminal for a method of storing and displaying intelligent event video retrieval data in an embodiment;

[0038] Figure 2 is a flowchart of a method of storing and displaying intelligent event video retrieval data in an embodiment;

[0039] Figure 3 is a flowchart of a method of storing and displaying intelligent event video retrieval data in another embodiment;

[0040] Figure 4 is a flowchart of storing trajectory data and corresponding video data in an embodiment;

[0041] Figure 5 is a flowchart of video playback in an embodiment;

[0042] Figure 6 is a structure block diagram of a device for storing and displaying intelligent event video retrieval data in an embodiment.

[0043] In the figure: 102, a processor; 104, a memory; 106, a transmission device; 108, an input / output device; 10, a storage module; 20, a retrieval module; 30, a display module. Detailed implementation manners

[0044] To understand the purpose, technical solution, and advantages of the present application more clearly, the present application is described and illustrated below with reference to the accompanying drawings and embodiments.

[0045] Unless otherwise defined, technical or scientific terms used in this application shall have the ordinary meanings understood by those of ordinary skill in the technical field to which this application belongs. In this application, words such as "a", "an", "one kind", "the", "these", etc. do not indicate a limitation in quantity and can be singular or plural. The terms "comprising", "including", "having" and any variations thereof used in this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent in these processes, methods, products or devices. The terms "connected", "coupled" and similar words used in this application do not limit to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The term "plurality" used in this application means two or more. "And / or" describes the association relationship of associated objects and indicates that three relationships may exist. For example, "A and / or B" may represent: A exists alone, A and B exist simultaneously, and B exists alone. Usually, the character " / " represents an "or" relationship between the associated objects before and after. The terms "first", "second", "third", etc. used in this application only distinguish similar objects and do not represent a specific order for the objects.

[0046] The method embodiments provided in this embodiment may be executed on a terminal, a computer or a similar computing device. For example, running on a terminal, Figure 1 is a hardware structure block diagram of the terminal for the method of intelligent event video retrieval data storage and display in this embodiment. As Figure 1 shown, the terminal may include one or more ( Figure 1 only one is shown in the figure) processors 102 and a memory 104 for storing data. Among them, the processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA. The above terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those of ordinary skill in the art can understand that Figure 1 the structure shown is only schematic and does not limit the structure of the above terminal. For example, the terminal may further include more or fewer components than Figure 1 shown in the figure, or have a different configuration from Figure 1 shown.

[0047] The memory 104 can be used to store computer programs, such as software programs and modules of application software, such as the computer program corresponding to the method for intelligent event video retrieval data storage and display in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, implements the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memories. In some instances, the memory 104 may further include a memory remotely disposed relative to the processor 102, and these remote memories can be connected to the terminal through a network. Examples of the above network include but are not limited to the Internet, intranet, local area network, mobile communication network, and combinations thereof.

[0048] The transmission device 106 is used to receive or send data via a network. The above network includes a wireless network provided by a communication provider of the terminal. In one instance, the transmission device 106 includes a network adapter (Network Interface Controller, abbreviated as NIC), which can be connected to other network devices through a base station and thus communicate with the Internet. In one instance, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0049] In this embodiment, a method for intelligent event video retrieval data storage and display is provided. Figure 2 is a flowchart of the method for intelligent event video retrieval data storage and display in this embodiment, as Figure 2 shown, the method includes the following steps:

[0050] Step S201, obtain the video data of each video source, and insert the trajectory area number of the trajectory area where the target appears in the video frame where the target is recognized.

[0051] Specifically, access the video data of video sources such as IPC (IP Camera), and perform intelligent analysis on the video data frame by frame. Among them, target detection models such as YOLO and CNN (Convolutional Neural Networks) can be used to analyze whether there is a target in the video frame, identify the target identifier of the target and its position in the picture, and output the target box coordinates.

[0052] Exemplarily, for the scenario of perimeter protection, the target can be a vehicle, a pedestrian, an animal, etc.; for the scenario of monitoring the leaving of key items, the target can be an item, etc.

[0053] For a video frame in which a target is recognized, if the target is located in a pre-divided trajectory area in the picture, the trajectory area number of the trajectory area is inserted into the video frame. Among them, the trajectory area is obtained by pre-dividing different trajectory areas for the picture of the video data in advance, and a unique trajectory area number is set for each trajectory area, and the size and shape of the trajectory area are not specifically limited.

[0054] Step S202, obtain trajectory data according to the target identifier, time information, and trajectory area number of the target, and store it.

[0055] Specifically, through the intelligent analysis of the video data of each video source, the video frame in which the target exists, the target identifier of the target, and the trajectory area number are obtained, and the time point when the target appears can be obtained from the video frame as the time information.

[0056] Store the target identifier, time information, and trajectory area number in a specific data structure to obtain trajectory data, and the trajectory data can form an independent linked list structure. In addition, store the trajectory data and the relevant video data in which the target exists in the hard disk respectively.

[0057] Step S203, based on the retrieval conditions of the trajectory area number and time information, retrieve the target identifier corresponding to the target from the trajectory data; and integrate the corresponding target video data based on the target identifier.

[0058] Specifically, when performing trajectory area video retrieval, by setting the retrieval conditions of the trajectory area number and time information, retrieve the target and target identifier that meet the retrieval conditions in the trajectory data, indicating that the target appears in the specified trajectory area at the specified time. Integrate the corresponding target video data based on the target identifier, that is, all the video data in which the target appears in the specified trajectory area at the specified time. Among them, the trajectory areas set in the retrieval conditions can be one or a combination of multiple; when combining multiple trajectory areas, it can be a combination of different trajectory areas in the same picture, or a combination of trajectory areas of different video source pictures.

[0059] In some of the embodiments, the video data of the target passing through the preset trajectory area can also be automatically saved, reducing the storage of invalid videos, saving hard disk space, and increasing the number of days of hard disk video storage.

[0060] Furthermore, the trajectory area number in the above retrieval conditions can be directly set by the user, or the user can draw a regular box in the picture, compare the regular box with the pre-divided trajectory area, and determine the trajectory area number corresponding to the regular box.

[0061] Step S204, play the target video data corresponding to the target identifier in the display window, and display the corresponding target attributes.

[0062] Specifically, when playing the target video data in the display window, corresponding target identification, time information, and trajectory data such as trajectory area numbers can also be displayed, and the target attributes can be displayed beside the target box of the target (e.g., in the upper right corner), enabling users to intuitively obtain relevant information about the target. If the target is a person, its target attributes can be information such as age, expression, and clothing.

[0063] Furthermore, the display window also includes a time progress bar and playback controls, which can control the start, pause, speed, forward, and backward of the video. In addition, the display window also includes configuration controls, which allow users to configure retrieval conditions, select video sources, etc. The retrieval conditions include but are not limited to target identification, time information, trajectory area numbers, etc., and support users to select and play the video data of any target, the video data of any time, and the video data of any trajectory area.

[0064] Through the above steps, the trajectory area number of the target can be inserted into the video frame where the target exists, and the trajectory data can be formed and stored. During retrieval, based on the trajectory area number and time information, the target video data of the required target can be quickly obtained and played, filtering out invalid video data, improving the video retrieval efficiency, and reducing the size of the bitstream data, thereby reducing the corresponding network bandwidth data during the transmission process.

[0065] In addition, adopting the storage method of trajectory area numbers, the trajectory data only records the corresponding trajectory area numbers, without the need to store the video data twice, which can save hard disk space, increase the number of days of hard disk video storage, and at the same time, retrieving according to the trajectory area numbers in the trajectory data can also improve the video retrieval speed.

[0066] In some of the embodiments, the above method further includes:

[0067] Pre-divide the screen of the video data into different trajectory areas and set corresponding trajectory area numbers; the trajectory areas adopt a multi-level structure.

[0068] Specifically, for the screens of the video data of each video source, users can divide the screen into different trajectory areas according to custom rules, set a unique trajectory area number for each trajectory area, and pair and save the coordinates of the trajectory area and the corresponding trajectory area number for configuration. Among them, the size and shape of the trajectory area are not limited, the size of each trajectory area can be the same or different, and the shape can be a rectangle, a polygon, etc. Among them, a hash algorithm can also be used to generate a unique trajectory area number for each trajectory area for setting.

[0069] Furthermore, the trajectory area can be divided according to a multi-level structure, including a first-level trajectory area, a second-level trajectory area, a third-level trajectory area, etc. The trajectory area numbers are multi-level numbers corresponding to the multi-level structure of the trajectory area. For example, the screen is first divided into different first-level trajectory areas (numbered 1, 2, 3, etc.), and then the first-level trajectory areas are further divided into different second-level trajectory areas (the first-level trajectory area numbered 1 is divided into 1.1, 1.2, 1.3, etc.).

[0070] In some embodiments, statistical clustering can be performed based on the movement trajectory of the target in the screen to automatically divide each level of the trajectory area. Among them, the position coordinate data of the target appearance in the historical video is collected, and the clustering algorithm (such as K-means) is used to perform clustering analysis on the high-frequency appearance areas of the target; the boundaries of the dense areas formed by clustering are automatically mapped to the trajectory areas (such as the first-level trajectory area, the second-level trajectory area, the third-level trajectory area, etc.), and hierarchical trajectory area numbers are assigned; at the same time, it also supports users to perform manual correction or merging operations on the automatically generated sub-areas. In addition, it is also conceivable to use a method of combining the user-defined way of dividing the trajectory area with the automatically divided way of statistical clustering to divide each level of the trajectory area. For example, the user first divides the screen into different first-level trajectory areas according to the user-defined rules, and then uses the method of statistical clustering to automatically divide one or more of the first-level trajectory areas into second-level trajectory areas.

[0071] By pre-dividing the trajectory area and setting numbers in this embodiment, a retrieval method based on the trajectory area number can be provided in subsequent steps, and at the same time, the space occupancy can be reduced during storage. In addition, by dividing the trajectory area according to a multi-level structure, a more refined trajectory of the target can be provided to provide a more accurate retrieval method, avoiding the influence caused by too large a trajectory area, and at the same time, the configuration of the trajectory area is assisted and optimized by the method of automatically dividing the trajectory area by statistical clustering.

[0072] In some of these embodiments, corresponding retrieval conditions can be set based on the multi-level structure of the trajectory area. In the retrieval conditions, the trajectory areas of the same level can be set, or the trajectory areas of different level combinations can be set. Thus, rough retrieval and fine retrieval can be realized according to the user's needs to more accurately locate the target and improve the retrieval efficiency. Taking the first-level trajectory areas (numbered 1, 2, 3, etc.) and the second-level trajectory areas (1.1, 1.2, 1.3, 2.1, 2.2, 2.3, 3.1, 3.2, 3.3, etc.) as an example, the trajectory areas set in the retrieval conditions can be of the same level (such as 1 and 2), or a combination of different levels (such as 1 and 3.2).

[0073] In some of these embodiments, inserting the trajectory area number of the trajectory area where the target appears into the video frame in step S201 above includes the following steps:

[0074] Identify the video frames with targets in the video data; compare the positions where the targets appear with the pre-divided trajectory areas, determine the trajectory area numbers corresponding to the targets, and insert the trajectory area numbers into the video frames.

[0075] Specifically, use the target recognition algorithm to recognize the targets existing in the video frame, as well as the target identifiers, the positions where the targets appear, etc., to determine the video frames with targets.

[0076] Compare the positions where the targets appear with the pre-divided trajectory areas. Specifically, judge whether the position coordinates of the targets (such as the center point of the position coordinates) are within the range of the trajectory areas. If the targets are located in the pre-divided trajectory areas, determine the trajectory area numbers corresponding to the targets.

[0077] Furthermore, insert a target entry flag into the video frame when it is recognized that the target enters the frame; insert a target exit flag into the video frame when it is recognized that the target leaves the frame.

[0078] Specifically, when performing intelligent analysis on the video data frame by frame, it is possible to judge whether the target enters the frame or leaves the frame according to the changes of the targets in adjacent video frames. For example, when there is no target in the previous video frame and there is a target in the current video frame, it is judged that the target enters the frame, and a target entry flag is inserted into the corresponding video frame; when there is a target in the previous video frame and there is no target in the current video frame, it is judged that the target leaves the frame, and a target exit flag is inserted into the corresponding video frame.

[0079] By inserting the target entry flag, the target exit flag, and the trajectory area number into the corresponding video frames in this embodiment, the video retrieval efficiency can be improved, which helps to quickly locate the video data that the user is interested in.

[0080] In some of these embodiments, the trajectory data includes frame description information, and the trajectory area numbers, target identifiers, target entry flags, or target exit flags of different targets in each time information.

[0081] Specifically, store the target identifiers, time information, and trajectory area numbers in a specific data structure to obtain the trajectory data, and the trajectory data can form an independent linked list structure. As shown in Table 1 for the linked list structure formed by the trajectory data, in this linked list structure, the relative offset of the next trajectory data from the current trajectory data is specified by the frame content, so as to determine the storage position of the next trajectory data.

[0082] Table 1

[0083]

[0084] The hierarchical structure of the trajectory data is shown in Table 2, which includes not only the frame header and frame tail, but also the frame description and the data at each time point. The frame description records the number of time points and the position of the next trajectory data. For example, a trajectory data records the trajectory data for 30 seconds (from 00:00:00 to 00:00:30 on May 20, 2024). The data at time point 1 records the trajectory data at 00:00:00 on May 20, 2024; the data at time point 2 records the trajectory data at 00:00:01 on May 20, 2024.

[0085] Table 2

[0086]

[0087] The data structure of the time point data is shown in Table 3, which records the trajectory data of different targets at each time point. The trajectory data includes the trajectory area number, time, target identification, target entry flag, and target departure flag.

[0088] Table 3

[0089]

[0090] Through the trajectory data and data structure provided in this embodiment, the storage method of the trajectory area number can be adopted. In this way, the trajectory data only records the corresponding trajectory area number, without secondary storage of video data, which can save hard disk space, increase the number of days of hard disk video storage, and at the same time, retrieve according to the trajectory area number in the trajectory data, which can also improve the video retrieval speed.

[0091] In some of these embodiments, the above method further includes the following steps:

[0092] When it is recognized that a target enters and / or leaves the screen, report the target event, and store the time information of the target event, the target identification, and the target attribute of the target as event data; when the target identification of the corresponding target is retrieved from the trajectory data, retrieve the target attribute from the event data based on the target identification.

[0093] Specifically, in the intelligent analysis of the above video data frame by frame, when it is recognized that a structured event occurs to a target, report the target event. For example, the target event can be that the target enters and / or leaves the screen. And store the time information of the occurrence of the target event (for example, the time point when the target enters the screen, and / or, the time point when the target leaves the screen), the target identification, and the target attribute as event data.

[0094] When retrieving the target identifier corresponding to the target from the trajectory data based on the retrieval conditions of the trajectory region number and time information, further retrieve the corresponding target attributes from the event data based on the target identifier, and display them synchronously when playing the relevant video data in the display window.

[0095] By reporting the target time and storing the event data in this embodiment, relevant information of the target can be provided when playing the video data, improving the user experience.

[0096] In some of these embodiments, in some of these embodiments, the above method further includes the following steps:

[0097] When playing the video data of each video source in the display window, detect the video region number in the video data, as well as the target entry flag or target exit flag; when detecting the trajectory region number and the target entry flag, play the video data with the first playback configuration and display the corresponding target attributes; when detecting the trajectory region number and the target exit flag, or when the trajectory region number is not detected, play the video data with the second playback configuration; the first playback configuration includes: playing the video data at the first preset speed; the second playback configuration includes: playing the video data at the second preset speed, or skipping the video data; the first preset speed is less than the second preset speed.

[0098] Specifically, since the video data of each video source includes a lot of invalid videos, for example, videos without targets. Therefore, when not performing trajectory region video retrieval, that is, when the user does not specify the trajectory region of interest, in order to improve the user experience and enable the user to locate the required picture faster, two playback configurations can be provided to adapt to different video data.

[0099] When playing the video data of each video source in the display window, synchronously detect the trajectory region number inserted in the video data according to the time period of the video data, as well as the target entry flag or target exit flag.

[0100] When detecting the trajectory region number and the target entry flag, play the video data with the first playback configuration and display the corresponding target attributes of the target in the picture; when detecting the trajectory region number and the target exit flag, or when the trajectory region number is not detected, play the video data with the second playback configuration. The first playback configuration includes: playing the video data at the first preset speed; the second playback configuration includes: playing the video data at the second preset speed, or skipping the video data; the first preset speed is less than the second preset speed.

[0101] Exemplarily, when the target appears in the screen and there is a trajectory area number, the video data is played at 1x speed, enabling the user to have sufficient time to track and observe the target; when the trajectory area number is not detected, it indicates that there is no target in the screen, or the target is not in the trajectory area divided by the user. Therefore, multiple-speed playback can be performed. For example, the video data can be played at 4x speed or 8x speed. Further, the video data of this time period can be skipped to improve the playback efficiency; when the target leaves the screen and there is a trajectory area number, it indicates that there is a target in the screen but the target is about to leave the screen. At this time, the playback can be switched from 1x speed to multiple-speed playback.

[0102] Meanwhile, the user can also perform operations such as start, pause, speed, forward, and backward when playing the video data through the controls in the display window.

[0103] By detecting the trajectory area number and the target entry flag or target exit flag in this embodiment, the playback configuration can be automatically switched, reducing the playback time of some invalid videos and improving the playback speed.

[0104] The following describes and illustrates this embodiment through preferred embodiments.

[0105] Figure 3 is a flowchart of the method for storing and displaying intelligent event video retrieval data in this embodiment, as Figure 3 shown, the method includes the following steps:

[0106] Step S301, obtain the video data of each video source; divide the screen of the video data into different trajectory areas in advance and set corresponding trajectory area numbers.

[0107] Step S302, identify the target in the video frame of the video data, compare the position where the target appears with the pre-divided trajectory area, and determine the trajectory area number corresponding to the target.

[0108] Step S303, insert the trajectory area number, and the target entry flag or target exit flag into the video frame with a target, and obtain trajectory data based on the target identifier, time information, trajectory area number, and the target entry flag or target exit flag of the target, and store it.

[0109] Step S304, when it is recognized that the target enters and / or leaves the screen, report the target event, and store the time information of the target event, the target identifier of the target, and the target attribute as event data.

[0110] Step S305, based on the retrieval condition of the trajectory area number and time information, retrieve the target identifier corresponding to the target from the trajectory data; integrate the corresponding target video data based on the target identifier, and retrieve the target attribute from the event data based on the target identifier.

[0111] Step S306: Play the target video data corresponding to the target identifier in the display window and display the corresponding target attributes.

[0112] Step S307: When playing the video data of each video source in the display window, synchronously detect the track area number in the video data, as well as the target entry flag or target exit flag; when detecting the track area number and the target entry flag, play the video data with the first playback configuration and display the corresponding target attributes.

[0113] Step S308: When detecting the track area number and the target exit flag, or when not detecting the track area number, play the video data with the second playback configuration.

[0114] Figure 4 This is the flowchart for storing track data and corresponding video data in this embodiment. As Figure 4 shown, after accessing the video data of the video source, the picture is segmented into different track areas according to rules. The intelligent server uses its own intelligent capabilities to perform frame-by-frame intelligent analysis on the video data of the video source to determine whether there is a target or a target event in the video frame.

[0115] When a target is recognized, compare the position where the target appears with the pre-set track areas. When the target is within the track area, if the target enters the picture, while inserting the corresponding track area number between video frames, mark the target entry flag; if the target is in the picture, insert the corresponding track area number between video frames; if the target leaves the picture, insert the corresponding track area number between video frames and mark the target exit flag. Finally, save the track data such as the track area number and the corresponding video data in the hard disk respectively.

[0116] When a target event occurs, store the information about the occurrence of the target event (such as time information, target identifier, target attributes, etc.) in the event database.

[0117] Figure 5 This is the flowchart for video playback in this embodiment. As Figure 5 shown, according to the retrieval conditions input by the user, etc., determine whether to perform track area video retrieval. When performing track area video retrieval, find the corresponding track data according to the retrieval conditions set by the user, and integrate the corresponding video according to the time recorded in the track data. In addition, retrieve the corresponding target attributes in the event data according to the information (such as target identifier) recorded in the track data. Finally, play the integrated video data in the display window of the client and display the corresponding target attributes at the same time.

[0118] When no trajectory area video retrieval is performed, analyze whether there is a trajectory area number in the codec stream frame. When a target appears in the picture and there is a trajectory area number, play the video data at 1x speed; when the target leaves the picture and there is a trajectory area number, or when no trajectory area number is detected, play at multiple speeds.

[0119] It should be noted that the steps shown in the above process or the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. And although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here. For example, step S306 and step S307 are the playback methods for performing trajectory data retrieval and not performing trajectory data retrieval, respectively.

[0120] In this embodiment, a device for intelligent event video retrieval data storage and display is also provided. This device is used to implement the above embodiments and preferred implementation manners, and those that have been described will not be repeated here. The following terms such as "module", "unit", "sub-unit", etc. can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0121] Figure 6 is the structural block diagram of the device for intelligent event video retrieval data storage and display in this embodiment, as Figure 6 shown, the device includes:

[0122] A storage module 10, which is used to obtain the video data of each video source, insert the trajectory area number of the trajectory area where the target appears in the video frame where the target is recognized; obtain the trajectory data according to the target identifier, time information, and trajectory area number of the target and store it;

[0123] A retrieval module 20, which is used to retrieve the target identifier of the corresponding target from the trajectory data based on the retrieval conditions of the trajectory area number and time information; and integrate the corresponding target video data based on the target identifier;

[0124] A display module 30, which is used to play the target video data corresponding to the target identifier in the display window and display the corresponding target attributes.

[0125] Through the device provided in this embodiment, the trajectory area number of the target can be inserted into the video frame where the target exists, and the trajectory data can be formed and stored. During retrieval, based on the trajectory area number and time information, the target video data required can be quickly obtained and played, filtering out invalid video data, improving the video retrieval efficiency, and being able to reduce the size of the codec stream data, and thus reduce the corresponding network bandwidth data during the transmission process.

[0126] In addition, a storage method using trajectory area numbers is adopted. In this way, the trajectory data only records the corresponding trajectory area numbers, without the need to store video data twice, which can save hard disk space, increase the number of days for hard disk video storage, and at the same time, retrieve according to the trajectory area numbers in the trajectory data, which can also improve the video retrieval speed.

[0127] It should be noted that each of the above modules can be a functional module or a program module, and can be implemented either by software or by hardware. For the modules implemented by hardware, each of the above modules can be located in the same processor; or each of the above modules can also be located in different processors in any combination form.

[0128] In this embodiment, a computer device is also provided, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0129] Optionally, the above computer device may further include a transmission device and an input / output device, wherein the transmission device is connected to the above processor, and the input / output device is connected to the above processor.

[0130] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation manners, and will not be repeated in this embodiment.

[0131] In addition, in combination with the method for intelligent event video retrieval data storage and display provided in the above embodiments, a storage medium can also be provided to implement in this embodiment. A computer program is stored on the storage medium; when the computer program is executed by the processor, it implements any one of the methods for intelligent event video retrieval data storage and display in the above embodiments.

[0132] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0133] It should be understood that the specific embodiments described here are only used to explain this application, rather than to limit it. According to the embodiments provided in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the protection scope of this application.

[0134] Obviously, the accompanying drawings are only some examples or embodiments of the present application. For those of ordinary skill in the art, the present application can also be applied to other similar situations based on these drawings without creative efforts. Additionally, it can be understood that although the work done during this development process may be complex and time-consuming, for those of ordinary skill in the art, certain design, manufacturing, or production changes based on the technical content disclosed in the present application are only conventional technical means and should not be regarded as insufficient disclosure of the present application.

[0135] The term "embodiment" in the present application means that the specific features, structures, or characteristics described in connection with the embodiments can be included in at least one embodiment of the present application. The phrase appears in various positions in the specification and does not necessarily mean the same embodiment, nor does it mean being independent or alternative to other embodiments and mutually exclusive. Those of ordinary skill in the art can clearly or implicitly understand that the embodiments described in the present application can be combined with other embodiments without conflict.

[0136] The above-described embodiments merely represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of patent protection. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A method for storing and displaying intelligent event video retrieval data, characterized in that: include: Acquire the video data of each video source, and insert the track area number of the track area where the target appears in the video frame where the target is identified; Obtaining and storing trajectory data according to the target identification, time information and the trajectory area number of the target; Retrieving a target identifier of a corresponding target from the track data based on the search conditions of the track area number and time information; and obtaining corresponding target video data based on the target identification integration; The target video data corresponding to the target identifier is played in the display window, and the corresponding target attributes are displayed.

2. The method for storing and displaying intelligent event video retrieval data according to claim 1, characterized in that: The method further comprises: The screen of the video data is pre-divided into different track areas, and corresponding track area numbers are set; the track areas adopt a multi-level structure.

3. The method for storing and displaying intelligent event video retrieval data according to claim 1, characterized in that: The step of inserting the track area number of the track area where the target appears in the video frame where the target is identified comprises: Identify a video frame containing a target in the video data; The position where the target appears is compared with the pre-divided track area, the track area number corresponding to the target is determined, and the track area number is inserted into the video frame.

4. The method for storing and displaying intelligent event video retrieval data according to claim 3, characterized in that: The method further comprises: Inserting a target entry mark into the video frame in which the target is identified to have entered the picture; Inserting a target leaving mark into the video frame where it is recognized that the target leaves the screen.

5. The method for storing and displaying intelligent event video retrieval data according to claim 1, characterized in that: The trajectory data includes frame description information and trajectory area numbers, target identifiers, target entry marks or target exit marks of different targets in each time information.

6. The method for storing and displaying intelligent event video retrieval data according to claim 1, characterized in that: The method further comprises: When the target is identified to enter the screen and / or leave the screen, a target event is reported, and time information of the target event and the target identifier and target attribute of the target are stored as event data; When the target identifier of the corresponding target is retrieved from the trajectory data, the target attribute is retrieved from the event data based on the target identifier.

7. The method for storing and displaying intelligent event video retrieval data according to claim 1, characterized in that: The method further comprises: When playing the video data of each video source in the display window, synchronously detecting the track area number and the target entry mark or the target exit mark in the video data; When the track area number and the target entry mark are detected, the video data is played in a first playback configuration and corresponding target attributes are displayed; When the track area number and the target leaving mark are detected, or when the track area number is not detected, playing the video data with a second playing configuration; The first playback configuration includes: playing the video data at a first preset speed; the second playback configuration includes: playing the video data at a second preset speed, or skipping the video data; the first preset speed is smaller than the second preset speed.

8. An intelligent event video retrieval data storage and display device, characterized in that: include: A storage module, used for acquiring the video data of each video source, and inserting the track area number of the track area where the target appears in the video frame where the target is identified; Obtaining and storing trajectory data according to the target identification, time information and the trajectory area number of the target; A retrieval module, configured to retrieve a target identifier of a corresponding target from the trajectory data based on a retrieval condition of the trajectory area number and time information; and obtaining corresponding target video data based on the target identification integration; The display module is used to play the target video data corresponding to the target identifier in the display window and display the corresponding target attributes.

9. A computer device comprising a memory and a processor, characterized in that: The memory stores a computer program, and the processor is configured to run the computer program to execute the method for storing and displaying intelligent event video retrieval data as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for storing and displaying intelligent event video retrieval data as described in any one of claims 1 to 7 are implemented.

Images