Intelligent terminal security cross-network transmission method and device for separating data and video

Abstract

The application discloses a kind of data and video separation's intelligent terminal security cross-network transmission method, applied to monitoring terminal, comprising: based on the preset event type reads original video stream data;According to the preset event type, the original video stream data is structured to extract structured information and form a metadata file;When the information corresponding to the preset event type is not included in the structured information, video abstract is sent to monitoring server according to preset period, wherein the video abstract is generated by original video stream data;Or, when the information corresponding to the preset event type is included in the structured information, original video stream data is sent to monitoring server.The method of the application improves the data transmission and screening efficiency, generates corresponding structured data for different scene requirements, so that it is more targeted.

Description

Technical Field

[0001] This invention belongs to the field of security, specifically relating to a method and apparatus for secure cross-network transmission of data and video on intelligent terminals. Background Technology

[0002] With the evolution of high-definition video surveillance and the rapid development of safe city construction, surveillance cameras are ubiquitous. According to incomplete statistics, a medium-sized city may have tens of thousands, even hundreds of thousands, of cameras covering the area. This is a massive system containing a vast amount of information, generating video data equivalent to 100 billion photos daily. While this massive amount of video records a small portion of valuable information, it provides visual evidence for most events, greatly facilitating subsequent investigations to uncover the truth, maintain social order, protect lives and property, and promote the normal functioning of daily work and life.

[0003] Currently, video surveillance typically transmits real-time video to a monitoring center for storage and analysis. Even without considering the information interrelationships between different monitoring systems, simply browsing this video requires significant manpower and resources. Monitoring centers face dual pressures in terms of storage and bandwidth; a large amount of useless information is transmitted to the monitoring center, hindering event retrieval and monitoring management.

[0004] In summary, existing video surveillance systems have the following shortcomings: 1. They lack semantic and structured descriptions of the monitored scenes, making it impossible to classify and query scenes by event type, resulting in low video retrieval efficiency; 2. Video analysis is concentrated in the monitoring center, which places high demands on the computing power of the processing platform and results in long response latency. Since the monitoring center handles multiple data accesses, it has extremely high requirements for data and storage; 3. For some high-security scenarios, data transmission requires cross-security domain video transmission. The large amount of real-time video data consumes a significant amount of bandwidth from security gateways or firewalls, leading to slower overall processing efficiency. Summary of the Invention

[0005] To address the aforementioned problems in the existing technology, this invention provides a method and apparatus for secure cross-network transmission of data and video via smart terminals. The technical problem to be solved by this invention is achieved through the following technical solution:

[0006] A secure cross-network transmission method for smart terminals that separates data and video, applied to monitoring terminals, includes:

[0007] Read raw video stream data based on preset event types;

[0008] The raw video stream data is structured according to the preset event type to extract structured information and form a metadata file;

[0009] When it is determined that the structured information does not include information corresponding to the preset event type, a video summary is sent to the monitoring server according to a preset period, wherein the video summary is generated from the original video stream data;

[0010] Alternatively, if it is determined that the structured information includes information corresponding to the preset event type, the original video stream data is sent to the monitoring server.

[0011] In one specific implementation, the video summary includes a scene image at the start time of the current period, a scene video for a preset time period of the current period, and structured information for the current period.

[0012] In one specific implementation, the video summary is encapsulated using the MYRTY protocol and transmitted to the monitoring server via the UDP protocol.

[0013] In one specific implementation, when it is determined that the original video stream data includes a moving target, the structured information includes the category, location, trajectory, and direction of movement of the moving target.

[0014] In one specific implementation, when the category of the moving target is a vehicle, the structured information further includes license plate number, license plate color, vehicle color, vehicle type, vehicle brand, model year, and local features.

[0015] In one specific implementation, when determining that the structured information includes information corresponding to the preset event type, the method further includes:

[0016] In response to a query request of the preset event type, if the query request is a target query, the target outline of the corresponding frame in the corresponding original video stream data is marked; if the query request is a trajectory query, the motion trajectory in the metadata file is superimposed on the corresponding frame in the original video stream data.

[0017] This invention also discloses a secure cross-network transmission device for smart terminals that separates data and video, comprising:

[0018] The video data acquisition module is used to read raw video stream data based on preset event types;

[0019] The structured information generation module is used to perform a structured description of the original video stream data according to the preset event type to extract structured information and form a metadata file;

[0020] The information processing module is used to send a video summary to the monitoring server at a preset period when it is determined that the structured information does not include information corresponding to the preset event type, wherein the video summary is generated from the original video stream data; or, when it is determined that the structured information includes information corresponding to the preset event type, the original video stream data is sent to the monitoring server.

[0021] In one specific implementation, the video summary includes a scene image at the start time of the current period, a scene video for a preset time period of the current period, and structured information for the current period.

[0022] In one specific implementation, the video summary is encapsulated using the MYRTY protocol and transmitted to the monitoring server via the UDP protocol.

[0023] This invention also discloses an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0024] Memory, used to store computer programs;

[0025] The steps of the above-described method for secure cross-network transmission of data and video in a smart terminal, when the processor executes a program stored in memory.

[0026] The beneficial effects of this invention are:

[0027] The data and video separation intelligent terminal secure cross-network transmission method of the present invention performs structured processing of video streams directly on the monitoring terminal according to the needs of the monitoring server, and transmits data on demand, which improves data transmission and screening efficiency. It generates corresponding structured data for different scenario needs, making it more targeted. In addition, the transmission of video streams and structured information through different links further improves transmission efficiency and real-time transmission.

[0028] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0029] Figure 1 This is a schematic flowchart of a secure cross-network transmission method for smart terminals that separates data and video, provided by an embodiment of the present invention.

[0030] Figure 2 This is a schematic diagram of the header format in the MYRTY encapsulation provided in the embodiments of the present invention;

[0031] Figure 3 This is a schematic diagram of the SR package encapsulation format provided in an embodiment of the present invention;

[0032] Figure 4This is a schematic diagram of a secure cross-network transmission device for smart terminals that separates data and video, provided in an embodiment of the present invention.

[0033] Figure 5 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0034] The present invention will be further described in detail below with reference to specific embodiments, but the implementation of the present invention is not limited thereto.

[0035] Example 1

[0036] Please see Figure 1 , Figure 1 This is a flowchart illustrating a secure cross-network transmission method for data and video separation in a smart terminal, provided by an embodiment of the present invention. Applied to a monitoring terminal, it includes:

[0037] S1. Read raw video stream data based on preset event types. Generally, the preset event types depend on the monitoring scenario. For example, when the monitoring scenario is a road, the preset event type is vehicle analysis event; when the monitoring scenario is around a building, the preset event type is person analysis event; and so on. If it is a logistics scenario, the preset event type is object analysis event. During analysis, it is first necessary to know the preset event types so that corresponding structured information can be generated.

[0038] S2. The original video stream data is described in a structured manner according to the preset event type to extract structured information and form a metadata file;

[0039] It's important to note that changes in the preset event types directly impact the characteristics of information categories during structured description. Therefore, the preset event types must be clearly defined before performing structured description. Structured description requires frame-by-frame analysis of the video stream data. Motion target-based behavior analysis is used for each video frame, employing background modeling, foreground extraction, and target tracking to extract background images and target metadata. Information related to the preset event types is extracted from the video. For example, in vehicle analysis, information such as the color, size, and trajectory of moving objects in the video is extracted to form a metadata file. Finally, search conditions can be set, including preset event types (people, vehicles, objects), occurrence areas, movement directions, and trajectories. For instance, fuzzy matching of target colors can quickly search for target objects that meet the conditions in the video and display them in a video thumbnail list. Viewers can jump to view the target object's actual scene in the original video via images, allowing for further analysis and judgment, thus improving the efficiency of finding targets from massive amounts of video data.

[0040] S3. When it is determined that the structured information does not include information corresponding to the preset event type, a video summary is sent to the monitoring server according to a preset period, wherein the video summary is generated from the original video stream data;

[0041] Alternatively, if it is determined that the structured information includes information corresponding to the preset event type, the original video stream data is sent to the monitoring server.

[0042] Sending all video feeds to the monitoring server not only results in a large amount of useless information occupying storage space, but also significantly reduces processing efficiency when reading data from the monitoring server due to the massive data volume. Therefore, when information corresponding to a preset event type is not included, it indicates that the current video data is useless to the server. For example, in vehicle analysis events, if there is no vehicle information in the video stream, it is useless data, and uploading it would only consume a large amount of storage space. In this case, it is only necessary to periodically send video summaries to the monitoring server to inform it. Alternatively, even if a vehicle is present in the video, but the vehicle information does not match the information corresponding to the preset event type, it is also considered useless data. It should be noted that the above video summaries use cross-network transmission separate from the video, thereby saving bandwidth while keeping track of scene dynamics when a large number of video surveillance feeds are connected.

[0043] In one specific implementation, the video summary includes a scene image at the start time of the current period, a scene video for a preset time period of the current period, and structured information for the current period.

[0044] For example, if the cycle is 1 minute, meaning a video summary is uploaded to the monitoring server once per minute, then the scene image at the start time of the current cycle is the first frame of that cycle. The scene video for the preset time period of the current cycle is a 1-second video, which can generally be the 1st second of the current cycle. The structured information for the current cycle is sent according to the specific situation. For example, in the vehicle analysis event mentioned above, if there is no vehicle information in the video stream, then the corresponding structured information cannot be extracted, and the content can be empty.

[0045] In one specific implementation, the video summary is encapsulated using the MYRTY protocol and transmitted to the monitoring server via the UDP protocol.

[0046] MYRTY is a protocol used to provide real-time transmission, and therefore can be considered a sublayer of the transport layer. MYRTY is located in the transport layer and is built on top of UDP. Like UDP, MYRTY also has a fixed encapsulation method to implement its real-time transmission functionality. MYRTY is used to provide time information and stream synchronization for end-to-end real-time transmission and to guarantee quality of service.

[0047] The header format in the MYRTY wrapper is as follows:Figure 2 As shown, where,

[0048] Version number (V): 2 bits, used to identify the MYRTY version used.

[0049] Padding bit (P): 1 bit. If this bit is set, the end of the MYRTY packet contains additional padding bytes.

[0050] Extension bit (X): 1 bit. If this bit is set, an extension header will follow the MYRTY fixed header.

[0051] CSRC counter (CC): 4 bits, containing the number of CSRCs following a fixed header.

[0052] Flag bit (M): 1 bit.

[0053] Payload Type (PT): 7 bits, identifies the type of MYRTY payload.

[0054] Sequence Number: 16 bits. The sender increments this field by 1 after sending each MYRTY packet. The receiver can use this field to detect packet loss and recover the packet sequence. The initial value of the sequence number is random.

[0055] Timestamp: 32 bits, recording the sampling time of the first byte of data in the packet. At the start of a session, the timestamp is initialized to an initial value. Even when no signal is being transmitted, the timestamp value continuously increases over time; the timestamp is essential for jitter removal and synchronization.

[0056] Synchronization Source Identifier (SSRC): 32 bits. The synchronization source refers to the origin of the MYRTY packet stream. No two SSRC values ​​can be the same within the same MYRTY session. This identifier is randomly selected using the MD5 randomization algorithm recommended in RFC1889.

[0057] Contribution Source List (CSRC List): 0-15 entries, 32 bits each, used to identify the sources of all MYRTY packets that contributed to a new packet generated by a MYRTY mixer. The mixer inserts these contributing CSRC identifiers into the table. All CSRC identifiers are listed so that the receiving end can correctly identify the parties involved in the conversation.

[0058] The MYRTY protocol receives streaming media information (such as H.263) from the upper layer and encapsulates it into MYRTY data packets; MYRTCY receives control information from the upper layer and encapsulates it into MYRTCY control packets. MYRTY sends MYRTY data packets to even-numbered ports in the UDP port pair; MYRTCY sends MYRTCY control packets to the receiving port in the UDP port pair.

[0059] MYRTY requires MYRTCY to guarantee its Quality of Service (QoS). MYRTCY's main functions are: QoS monitoring and feedback, media synchronization, and member identification within multicast groups. During a MYRTY session, each participant periodically transmits MYRTCY packets. These packets contain statistics such as the number of packets sent and lost, allowing participants to dynamically adjust transmission rates and even payload types. The combined use of MYRTY and MYRTCY optimizes transmission efficiency with effective feedback and minimal overhead, making them particularly suitable for transmitting real-time data over the internet.

[0060] MyRTCY packets are also transmitted using UDP, but they encapsulate only control information, resulting in very short packets. Therefore, multiple MyRTCY packets can be encapsulated in a single UDP packet. As shown in Table 1, MyRTCY has the following five packet types.

[0061] Table 1

[0062]

[0063] The encapsulation of the above five grouping types is largely the same; only the SR type will be explained below.

[0064] The Sender Report (SR) packet is used to enable the sender to report the transmission status to all receivers via multicast. The main contents of the SR packet include: the SSRC of the corresponding MYRTY stream, the timestamp and NTP of the most recently generated MYRTY packet in the MYRTY stream, the number of packets contained in the MYRTY stream, and the number of bytes contained in the MYRTY stream. The SR packet encapsulation is as follows: Figure 3 As shown, where,

[0065] Version (V): Same as the MYRTY header field.

[0066] Padding (P): Same as the MYRTY header field.

[0067] Receive Report Counter (RC): 5 bits, the number of receive report blocks in this SR packet, which can be zero.

[0068] Packet type (PT): 8 bits, SR packets are 200.

[0069] Length field: 16 bits, which stores the total length of the SR packet in 32-bit units minus one.

[0070] Synchronization Source (SSRC): The synchronization source identifier of the sender of the SR packet. It is the same as the SSRC in the corresponding MYRTY packet.

[0071] The NTP Timestamp (Network Time Protocol) is the absolute time value at the time the SR packet is sent. NTP's function is to synchronize different MyRTY media streams.

[0072] MYRTY Timestamp: Corresponds to the NTP timestamp, and has the same unit and random initial value as the MYRTY timestamp in the MYRTY data packet.

[0073] Sender's packet count: The total number of MYRTY packets sent by the sender from the start of packet transmission to the generation of this SR packet. This field is cleared when the SSRC changes.

[0074] Sender's octet count: The total number of payload data bytes (excluding header and padding) sent by the sender from the start of packet transmission to the generation of this SR packet. This field is cleared when the sender changes its SSRC.

[0075] SSRC identifier of synchronization source n: This report block contains statistics on packets received from this source.

[0076] Friction Lost: Indicates the rate of loss of MYRTY packets from synchronization source n (SSRC_n) since the last SR or RR packet was sent.

[0077] Cumulative packet loss count: The total number of MYRTY data packets lost from SSRC_n from the start of receiving packets from SSRC_n to the sending of SR.

[0078] Received Extended Maximum Sequence Number: The largest sequence number in the MYRTY packets received from SSRC_n.

[0079] Interarrival jitter: Statistical variance estimation of MYRTY packet reception time

[0080] Last SR timestamp (Last SR, LSR): Take the middle 32 bits of the NTP timestamp from the most recent SR packet received from SSRC_n. If no SR packet has been received yet, this field is cleared.

[0081] Delay since last SR (DLSR): The delay from the last receipt of an SR packet from SSRC_n to the sending of this report.

[0082] When a MYRTY session is established, the application determines a pair of destination transport addresses. The destination transport address consists of a network address and a pair of ports: one for MYRTY packets and one for MYRTCY packets, ensuring correct transmission of MYRTY / MYRTCY data. MYRTY data is sent to the even-numbered UDP port, while the corresponding control signal MYRTCY data is sent to the adjacent odd-numbered UDP port (even-numbered UDP port + 1), thus forming a UDP port pair. The MYRTY sending process is as follows, and the receiving process is the reverse.

[0083] In one specific implementation, when it is determined that the original video stream data includes a moving target, the structured information includes the moving target's category, location, trajectory, and direction of movement. Examples of moving target categories include vehicles, people, animals, and objects.

[0084] In one specific implementation, when the category of the moving target is a vehicle, the structured information further includes license plate number, license plate color, vehicle color, vehicle type, vehicle brand, model year, and local features.

[0085] In one specific implementation, when determining that the structured information includes information corresponding to the preset event type, the method further includes:

[0086] In response to a query request of the preset event type, if the query request is a target query, the target outline of the corresponding frame in the corresponding original video stream data is marked; if the query request is a trajectory query, the motion trajectory in the metadata file is superimposed on the corresponding frame in the original video stream data.

[0087] Please see Figure 4 This invention also discloses a secure cross-network transmission device for smart terminals that separates data and video, comprising:

[0088] Video data acquisition module 41 is used to read raw video stream data based on preset event types;

[0089] The structured information generation module 42 is used to perform a structured description of the original video stream data according to the preset event type to extract structured information and form a metadata file;

[0090] The information processing module 43 is used to send a video summary to the monitoring server according to a preset period when it is determined that the structured information does not include information corresponding to the preset event type, wherein the video summary is generated from the original video stream data; or, when it is determined that the structured information includes information corresponding to the preset event type, it sends the original video stream data to the monitoring server.

[0091] In one specific implementation, the video summary includes a scene image at the start time of the current period, a scene video for a preset time period of the current period, and structured information for the current period.

[0092] In one specific implementation, the video summary is encapsulated using the MYRTY protocol and transmitted to the monitoring server via the UDP protocol.

[0093] Please see Figure 5 The present invention also discloses an electronic device, including a processor 51, a communication interface 52, a memory 53 and a communication bus 54, wherein the processor 51, the communication interface 52 and the memory 53 communicate with each other through the communication bus 54.

[0094] Memory 53 is used to store computer programs;

[0095] When the processor 51 executes the program stored in the memory 53, it implements the steps of the above-mentioned secure cross-network transmission method for smart terminals that separates data and video.

[0096] The communication bus mentioned in the above electronic devices can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0097] The communication interface is used for communication between the aforementioned electronic devices and other devices.

[0098] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0099] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0100] The method provided in this invention can be applied to electronic devices. Specifically, the electronic device can be a desktop computer, a portable computer, a smart mobile terminal, a server, etc. No limitation is made herein; any electronic device that can implement this invention falls within the protection scope of this invention.

[0101] For the embodiments of the device / electronic device / storage medium, since they are basically similar to the method embodiments, the description is relatively simple, and relevant parts can be referred to in the description of the method embodiments.

[0102] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. In addition, those skilled in the art can combine and integrate the different embodiments or examples described in this specification.

[0103] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, disclosure, and appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude a plurality. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce good results.

[0104] Those skilled in the art will understand that embodiments of this application can be provided as methods, apparatus (devices), or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects, all of which are collectively referred to herein as "modules" or "systems." Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The computer program may be stored / distributed in a suitable medium, provided with or as part of other hardware, or may take other distribution forms, such as via the Internet or other wired or wireless telecommunications systems.

[0105] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (devices), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0106] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0107] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes

[0108] The above description, in conjunction with specific preferred embodiments, provides a further detailed explanation of the present invention. It should not be construed that the specific implementation of the present invention is limited to these descriptions. For those skilled in the art, various simple deductions or substitutions can be made without departing from the concept of the present invention, and all such modifications and substitutions should be considered within the scope of protection of the present invention.

Claims

1. A secure cross-network transmission method for intelligent terminals that separates data and video, applied to monitoring terminals, characterized in that, include: The raw video stream data is read based on a preset event type, which is determined according to the monitoring scenario; The original video stream data is structured according to the preset event type to extract structured information and form a metadata file. The change of the preset event type directly affects the information category characteristics during the structured description. Specifically, this includes: clarifying the preset event type, analyzing the original video stream data frame by frame during the structured description, and using motion target-based behavior analysis processing on the video frames to extract the background image and target metadata information of the image, and extracting information related to the preset event type in the video to form a metadata file. If it is determined that the structured information does not include information corresponding to the preset event type, a video summary is sent to the monitoring server according to a preset period. The video summary is generated from the original video stream data and includes the scene image at the start time of the current period, the scene video for a preset time period of the current period, and the structured information for the current period. The video summary is encapsulated using the MYRTY protocol and transmitted to the monitoring server via the UDP protocol. If it is determined that the structured information includes information corresponding to the preset event type, the original video stream data is sent to the monitoring server. The video summary is transmitted across networks separately from the video.

2. The secure cross-network transmission method for smart terminals with data and video separation according to claim 1, characterized in that, When it is determined that the original video stream data includes a moving target, the structured information includes the moving target's category, location, trajectory, and direction of movement.

3. The secure cross-network transmission method for smart terminals with data and video separation according to claim 2, characterized in that, When the category of the moving target is a vehicle, the structured information also includes license plate number, license plate color, vehicle color, vehicle type, vehicle brand, model year, and local features.

4. The secure cross-network transmission method for smart terminals with data and video separation according to claim 2, characterized in that, When determining that the structured information includes information corresponding to the preset event type, the method further includes: In response to a query request of the preset event type, if the query request is a target query, the target outline of the corresponding frame in the corresponding original video stream data is marked; if the query request is a trajectory query, the motion trajectory in the metadata file is superimposed on the corresponding frame in the original video stream data.

5. A secure cross-network transmission device for intelligent terminals that separates data and video, characterized in that, The apparatus for performing the secure cross-network transmission method for data and video separation of a smart terminal as described in claim 1, the apparatus comprising: The video data acquisition module is used to read raw video stream data based on preset event types; The structured information generation module is used to perform a structured description of the original video stream data according to the preset event type to extract structured information and form a metadata file; The information processing module is used to send a video summary to the monitoring server according to a preset period when it is determined that the structured information does not include information corresponding to the preset event type. The video summary is generated from the original video stream data. When it is determined that the structured information includes information corresponding to the preset event type, the original video stream data is sent to the monitoring server.

6. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the steps of the method described in any one of claims 1-4.

Images