Video tagging method, apparatus, and device

Abstract

The present disclosure provides a video marking method, device and equipment, relates to the technical field of video transmission, in particular to the technical field of error frame recovery, and can be applied to the automatic driving scene. A specific embodiment of the method comprises: in response to receiving a starting signal of a target frame of a video, continuing to receive data of the target frame, and writing the data of the target frame from a starting address of the target frame; and in response to determining that the data transmission of the target frame is completed, marking the target frame by type. The embodiment can distinguish between good frames and error frames, after the occurrence of error frames, the subsequent frame transmission mechanism can quickly recover to normal, new error frames are no longer continuously generated, and subsequent frame mismatch is avoided.

Description

Technical Field

[0001] This disclosure relates to the field of video transmission technology, specifically to the field of error frame recovery technology, and can be applied to autonomous driving scenarios. Background Technology

[0002] Video transmission is the process of transmitting video image signals from one place to another, or from one device to another, using wired or wireless transmission media, directly or through means such as modems.

[0003] For video transmission, due to bandwidth limitations, camera malfunctions, or signal interference, the received video frames may be incomplete, resulting in video frame mismatch, which will continue to affect all subsequent video frames. Summary of the Invention

[0004] This disclosure provides a video tagging method, apparatus, device, storage medium, and program product.

[0005] In a first aspect, embodiments of this disclosure propose a video tagging method, comprising: in response to receiving a start signal of a target frame of a video, continuing to receive data of the target frame, and writing data of the target frame from the start address of the target frame; and in response to determining that the data transmission of the target frame has ended, tagging the target frame with a type.

[0006] Secondly, embodiments of this disclosure provide a video tagging device, comprising: a writing module configured to, in response to a start signal of a received target frame of video, continue to receive data of the target frame and write data of the target frame from the start address of the target frame; and a tagging module configured to, in response to determining the end of data transmission of the target frame, tag the target frame with a type.

[0007] Thirdly, embodiments of this disclosure provide an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform a method as described in any implementation of the first aspect.

[0008] Fourthly, embodiments of this disclosure provide a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform a method as described in any implementation of the first aspect.

[0009] Fifthly, embodiments of this disclosure provide a computer program product, including a computer program that, when executed by a processor, implements the method as described in any of the implementations of the first aspect.

[0010] The video tagging method provided in this disclosure writes the target frame upon receiving its start signal and tags its type upon completion of data transmission, thus distinguishing between good frames and error frames. After an error frame occurs, the subsequent frame transmission mechanism can quickly return to normal, preventing the generation of new error frames and avoiding subsequent frame mismatches.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0012] Other features, objects, and advantages of this disclosure will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings. The drawings are provided for a better understanding of the invention and are not intended to limit the scope of this disclosure. Wherein:

[0013] Figure 1 This is a flowchart of an embodiment of the video tagging method according to the present disclosure;

[0014] Figure 2 This is a flowchart of yet another embodiment of the video tagging method according to the present disclosure;

[0015] Figure 3 This is a scene diagram illustrating how the video tagging method of this disclosure embodiment can be implemented;

[0016] Figure 4 This is a schematic diagram of a structure of an embodiment of the video marking device according to the present disclosure;

[0017] Figure 5 This is a block diagram of an electronic device used to implement the video tagging method of the embodiments of this disclosure. Detailed Implementation

[0018] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0019] It should be noted that, unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other. This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0020] Figure 1A flow 100 of an embodiment of a video tagging method according to the present disclosure is shown. The video tagging method includes the following steps:

[0021] Step 101: In response to receiving the start signal of the target frame of the video, continue to receive the data of the target frame and write the data of the target frame from the start address of the target frame.

[0022] In this embodiment, the video stored on the first device can be transmitted to the second device. Typically, for a target frame in the video, the first device can start transmitting from the start signal of the target frame and gradually transmit the data until the end signal is received, at which point the target frame transmission is complete. When the second device receives the start signal of the target frame, it can determine that subsequently received data belongs to the target frame. At this point, the second device can start writing the received data from the start address of the target frame. Since target frames in the same video have the same length, the start and end addresses of the target frames can be predefined.

[0023] Here, the video is composed of video frames, and two synchronization signals are added to each frame: a start signal and an end signal. The start signal marks the beginning of the video frame, and the end signal marks the end of the video frame. The target frame is a video frame of type "good frame." That is, the first device only transmits target frames of type "good frame" to the second device. For erroneous frames in the video, the first device discards them directly.

[0024] In some embodiments, an attribute field can be added at a preset position of the video frame to record the type of the video frame. The video frame type may include, but is not limited to, good frames, short error frames, and long error frames. For example, a specific field can be added to the end of the video frame to mark its attributes, thereby helping the first device to delete error frames. This special field can be added to the end of the video frame, with a fixed address and format, generally including the frame sequence number, timestamp, and frame attributes. For example, the special field may be 32 bytes, with the last 32 bytes representing the frame attribute: 0 for a good frame, 1 for a short error frame, and 2 for a long error frame. Before reading a video frame, the first device first reads the frame attribute at the address of the special field. Only good frames with a frame attribute of 0 are read and transmitted as target frames; error frames with frame attributes of 1 or 2 are discarded. This helps the first device avoid reading and using error frames, improving transmission efficiency while avoiding the transmission of error frames.

[0025] Step 102: In response to determining that the data transmission of the target frame has ended, the target frame is type-marked.

[0026] In this embodiment, after determining that the data transmission of the target frame has ended, the second device can analyze the received data of the target frame, determine the type of the target frame, and then mark the target frame by type. For example, if there is an end signal in the data of the target frame written at the end address of the target frame, it indicates that the target frame has been transmitted completely and is marked as a good frame; if there is no end signal in the data of the target frame written at the end address of the target frame, it indicates that the target frame has not been transmitted completely and is marked as an error frame.

[0027] In some embodiments, the data of erroneous frames may be discarded without further recovery. In other embodiments, since erroneous frames are associated with several preceding and following good frames, they can be recovered based on these good frames. For example, the average image of the preceding and following good frames can be calculated to replace the erroneous frame.

[0028] The video tagging method provided in this disclosure writes the target frame upon receiving its start signal and tags its type upon completion of data transmission, thus distinguishing between good frames and error frames. After an error frame occurs, the subsequent frame transmission mechanism can quickly return to normal, preventing the generation of new error frames and avoiding subsequent frame mismatches.

[0029] Continue to refer to Figure 2 This illustrates a flow 200 of yet another embodiment of the video tagging method according to the present disclosure. The video tagging method includes the following steps:

[0030] Step 201: In response to receiving the start signal of the target frame of the video, continue to receive the data of the target frame and write the data of the target frame from the start address of the target frame.

[0031] In this embodiment, the specific operation of step 201 has been described. Figure 1 The steps in the illustrated embodiment are described in detail in step 101, and will not be repeated here.

[0032] During the transmission of the target frame, different steps are executed based on different situations. Upon receiving the start signal of the next target frame of the video, and before the data of the target frame has been written to the end address of the target frame, step 202-1 is executed; upon receiving the end signal of the target frame, and before the write pointer reaches the end address of the target frame or the write length is less than the length of the target frame, step 202-2 is executed; upon receiving the end signal of the target frame, and before the write pointer points to the end address of the target frame or the write length is equal to the length of the target frame, step 202-3 is executed; upon the write pointer pointing to the end address of the target frame or the write length being equal to the length of the target frame, step 202-4 is executed.

[0033] Step 202-1: In response to receiving the start signal of the next target frame of the video, and before the data of the target frame has been written to the end address of the target frame, the target frame is marked as a short error frame.

[0034] In this embodiment, if the start signal of the next target frame of the video is received before the data of the current target frame has been written to the end address of the current target frame, it indicates that the transmission of the current target frame is incomplete, and some of its subsequent data is lost. Furthermore, the data in the current target frame is less than the data in a good frame. In this case, the second device can consider the target frame transmission to be complete and mark the target frame as a short error frame.

[0035] Furthermore, data received after receiving the start signal of the next target frame of the video belongs to that next target frame. At this point, the second device can write the received data starting from the start address of the next target frame, thereby protecting the next target frame from corruption.

[0036] Step 202-2: In response to receiving the end signal of the target frame, and the write pointer has not reached the end address of the target frame or the write length is less than the length of the target frame, mark the target frame as a short error frame.

[0037] In this embodiment, if the end signal of the target frame is received before the data of the current target frame has been written to the end address of the current target frame, it indicates that the transmission of the current target frame is incomplete, and some data in the middle is lost. Furthermore, the data in the current target frame is less than the data in a good frame. In this case, the second device can consider the target frame transmission to be complete and mark the target frame as a short error frame.

[0038] Typically, after receiving the start signal of the target frame, the second device can set the write pointer to the start address of the target frame. Subsequent data received from the target frame will begin writing from the address pointed to by the write pointer, and the write pointer will gradually move backward as more data is received. If the end signal of the target frame is received before the write pointer reaches the end address, it indicates that data in the middle of the target frame is lost, classifying it as a short error frame. Alternatively, the second device can also determine the write length of the target frame after receiving the end signal. If the write length of the target frame is less than the actual length of the target frame, it also indicates that data in the middle of the target frame is lost, classifying it as a short error frame.

[0039] Furthermore, after receiving the end signal of the target frame, the second device receives the start signal of the next target frame of the video. At this time, the second device can write the received data of the next target frame starting from the start address of the next target frame, thereby protecting the next target frame from being corrupted.

[0040] Step 202-3: In response to receiving the end signal of the target frame and the write pointer pointing to the end address of the target frame or the write length being equal to the length of the target frame, mark the target frame as a good frame.

[0041] In this embodiment, if an end signal of the target frame is received when the data of the current target frame is written to the end address of the current target frame, it indicates that the current target frame transmission is complete and no data is lost. At this time, the second device can consider the target frame transmission to be complete and mark the target frame as a good frame.

[0042] Typically, after receiving the start signal of the target frame, the second device can set the write pointer to the start address of the target frame. Subsequent received target frame data begins to be written from the address pointed to by the write pointer, and the write pointer gradually moves forward as more target frame data is received. If the end signal of the target frame is received when the write pointer points to the end address, it indicates that there is no data loss in the target frame, and it is considered a good frame. Furthermore, the second device can also determine the write length of the target frame after receiving the end signal. If the write length of the target frame equals the actual length of the target frame, it also indicates that there is no data loss in the target frame, and it is considered a good frame.

[0043] Furthermore, after receiving the end signal of the target frame, the second device will receive the start signal of the next target frame of the video. At this time, the second device can write the received data of the next target frame starting from the start address of the next target frame, thereby realizing the normal writing of the next target frame.

[0044] Step 202-4: In response to the write pointer pointing to the end address of the target frame or the write length being equal to the length of the target frame, mark the target frame as a long error frame.

[0045] In this embodiment, if the data of the current target frame is written to the end address of the current target frame, and no end signal of the target frame is received, it indicates that the transmission of both the current target frame and the next target frame is incomplete; the latter part of the data in the current target frame is lost, and the former part of the data in the next target frame is lost. At this time, the second device can consider the target frame transmission complete and mark the target frame as a good frame. Furthermore, the data written to the address of the current target frame contains part of the data from both the current target frame and the next target frame, and its length is longer than that of a good frame. At this time, the second device can consider the target frame transmission complete and mark the target frame as a long error frame. In addition, subsequently received data can be directly discarded until the start signal of a new target frame arrives. At this point, the second device can write the received data of the new target frame starting from the start address of the new target frame, thereby protecting the new target frame from corruption.

[0046] Typically, after receiving the start signal of the target frame, the second device can set the write pointer to the start address of the target frame. Subsequent data received from the target frame will begin writing from the address pointed to by the write pointer, and the write pointer will gradually move forward as more data is received. If the write pointer does not point to the end address of the target frame but no end signal of the target frame is received, it indicates that the data after the target frame is lost, and the data before the next target frame is also lost, constituting a long error frame. Alternatively, the second device can also determine whether an end signal of the target frame has been received when the written length of the target frame equals the actual length of the target frame. If no end signal of the target frame is received, it also indicates that the data after the target frame is lost, and the data before the next target frame is also lost, constituting a long error frame.

[0047] from Figure 2 It can be seen from this that, with Figure 1 Compared to the corresponding embodiments, the video tagging method in this embodiment emphasizes the tagging step in process flow 200. Therefore, the scheme described in this embodiment tags various erroneous frames that occur under various circumstances, reducing the rate of missed tagging of erroneous frames.

[0048] For ease of understanding, Figure 3A scenario diagram illustrating a video marking method that can be implemented according to embodiments of the present disclosure is shown. As shown in FIG301, in an idle state, a first device can transmit video to a second device. As shown in FIG302, frame transmission begins when the first start signal sof arrives. As shown in FIG303, the write pointer wr_pt points to the start address frame_start of the current frame, and the first frame data will be transmitted to the start address of the current frame, which will gradually increase as data is transmitted. As shown in FIG304, after frame transmission begins, as shown in FIG305-1, if a new sof arrives before the end address, the current frame will be marked as a short frame. Data synchronized with this new sof will be sent to the start address of the next frame, which will protect the next frame from being corrupted. As shown in FIG305-2, after frame transmission begins, the end signal eof arrives. If the write pointer does not point to the end of the frame wr_pt != frame_end, this frame will be marked as a short frame. As shown in 305-3, if the write pointer points to the end of the frame (wr_pt = frame_end), the frame will be marked as a good frame. As shown in 305-4, after frame transmission begins, when the write pointer points to the end of the frame (wr_pt = frame_end), if the EOF is lost, the frame will be marked as a long error frame, and the remaining data in that frame will be discarded until a new EOF arrives. Then, data synchronized with this new EOF will be sent to the start address of the next frame. As shown in 306, frame transmission stops after all frames have been transmitted.

[0049] Further reference Figure 4 As an implementation of the methods shown in the above figures, this disclosure provides an embodiment of a video tagging device, which is similar to... Figure 1 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0050] like Figure 4 As shown, the video tagging device 400 of this embodiment may include a writing module 401 and a tagging module 402. The writing module 401 is configured to continue receiving data of the target frame and writing data of the target frame from the starting address of the target frame in response to a start signal indicating that the target frame has been received. The tagging module 402 is configured to tag the target frame with a type in response to determining that the data transmission of the target frame has ended.

[0051] In this embodiment, the specific processing of the writing module 401 and the marking module 402 in the video marking device 400 and the resulting technical effects can be referred to respectively. Figure 1 The relevant descriptions of steps 101-102 in the corresponding embodiments will not be repeated here.

[0052] In some optional implementations of this embodiment, the marking module 402 includes: a first marking submodule, configured to mark the target frame as a short error frame in response to the start signal of the next target frame of the received video and before the data of the target frame has been written to the end address of the target frame.

[0053] In some optional implementations of this embodiment, the marking module 402 includes: a second marking submodule, configured to mark the target frame as a short error frame in response to receiving the end signal of the target frame and the write pointer not reaching the end address of the target frame or the write length being less than the length of the target frame.

[0054] In some optional implementations of this embodiment, the marking module 402 includes: a third marking submodule, configured to mark the target frame as a good frame in response to receiving an end signal of the target frame and the write pointer pointing to the end address of the target frame or the write length being equal to the length of the target frame.

[0055] In some optional implementations of this embodiment, the marking module 402 includes: a fourth marking submodule, configured to mark the target frame as a long error frame in response to the write pointer pointing to the end address of the target frame or the write length being equal to the length of the target frame, and no end signal of the target frame being received.

[0056] In some optional implementations of this embodiment, the start position of the video frame is marked with a start signal, the end position of the video frame is marked with an end signal, and an attribute field is added at a preset position of the video frame to record the type of the video frame. The video frame with the type "good frame" is the target frame.

[0057] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0058] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0059] Figure 5A schematic block diagram of an example electronic device 500 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0060] like Figure 5 As shown, device 500 includes a computing unit 501, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 502 or a computer program loaded from storage unit 508 into random access memory (RAM) 503. RAM 503 may also store various programs and data required for the operation of device 500. The computing unit 501, ROM 502, and RAM 503 are interconnected via bus 504. Input / output (I / O) interface 505 is also connected to bus 504.

[0061] Multiple components in device 500 are connected to I / O interface 505, including: input unit 506, such as keyboard, mouse, etc.; output unit 507, such as various types of monitors, speakers, etc.; storage unit 508, such as disk, optical disk, etc.; and communication unit 509, such as network card, modem, wireless transceiver, etc. Communication unit 509 allows device 500 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0062] The computing unit 501 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 501 performs the various methods and processes described above, such as video tagging methods. For example, in some embodiments, the video tagging method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on device 500 via ROM 502 and / or communication unit 509. When the computer program is loaded into RAM 503 and executed by the computing unit 501, one or more steps of the video tagging method described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform the video tagging method by any other suitable means (e.g., by means of firmware).

[0063] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0064] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0065] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0066] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0067] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0068] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, distributed system servers, or servers incorporating blockchain technology.

[0069] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution provided in this disclosure can be achieved, and this is not limited herein.

[0070] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A video tagging method for video stream transmission in autonomous driving, comprising: In response to receiving a start signal for a target frame of video for autonomous driving, the system continues to receive data of the target frame and write data of the target frame from the start address of the target frame. In response to determining that the data transmission of the target frame has ended, the target frame is marked as a good frame or an error frame, including: in response to the write pointer pointing to the end address of the target frame or the write length being equal to the length of the target frame, and no end signal of the target frame being received, the target frame is marked as a long error frame; In response to the target frame being a long erroneous frame, the target frame and the data received before the arrival of the next start signal are discarded, or the target frame is replaced with the average image of the several good frames before and after the target frame based on the correlation between the target frame and the several good frames before and after the target frame.

2. The method according to claim 1, wherein, The step of responding to receiving a start signal for a target frame of video used for autonomous driving, and continuing to receive data of the target frame, and writing data of the target frame from the start address of the target frame, includes: In response to receiving the start signal of the next target frame of the video, and before the data of the target frame has been written to the end address of the target frame, the target frame is marked as a short error frame.

3. The method according to claim 1, wherein, The step of responding to receiving a start signal for a target frame of video used for autonomous driving, and continuing to receive data of the target frame, and writing data of the target frame from the start address of the target frame, includes: In response to receiving the end signal of the target frame, and the write pointer has not reached the end address of the target frame or the write length is less than the length of the target frame, the target frame is marked as a short error frame.

4. The method according to claim 1, wherein, The step of responding to receiving a start signal for a target frame of video used for autonomous driving, and continuing to receive data of the target frame, and writing data of the target frame from the start address of the target frame, includes: In response to receiving the end signal of the target frame, and the write pointer pointing to the end address of the target frame or the write length being equal to the length of the target frame, the target frame is marked as a good frame.

5. The method according to any one of claims 1-4, wherein, The video frames are marked with a start signal at the start position and an end signal at the end position. An attribute field is added to a preset position of the video frames to record the type of the video frames. Video frames with the type "good frame" are the target frames.

6. A video tagging device for video stream transmission in autonomous driving, comprising: The writing module is configured to, in response to receiving a start signal of a target frame for video used in autonomous driving, continue to receive data of the target frame and write data of the target frame from the start address of the target frame; A marking module is configured to mark the target frame as a good frame or an error frame in response to determining that the data transmission of the target frame has ended, including: a fourth marking submodule, configured to mark the target frame as a long error frame in response to the write pointer pointing to the end address of the target frame or the write length being equal to the length of the target frame, and no end signal of the target frame being received; In response to the target frame being a long erroneous frame, the target frame and the data received before the arrival of the next start signal are discarded, or the target frame is replaced with the average image of the average images ...

7. The apparatus according to claim 6, wherein, The marking module includes: The first marking submodule is configured to mark the target frame as a short error frame in response to receiving the start signal of the next target frame of the video and before the data of the target frame has been written to the end address of the target frame.

8. The apparatus according to claim 6, wherein, The marking module includes: The second marking submodule is configured to mark the target frame as a short error frame in response to receiving the end signal of the target frame and the write pointer not reaching the end address of the target frame or the write length being less than the length of the target frame.

9. The apparatus according to claim 6, wherein, The marking module includes: The third marking submodule is configured to mark the target frame as a good frame in response to receiving the end signal of the target frame and the write pointer pointing to the end address of the target frame or the write length being equal to the length of the target frame.

10. The apparatus according to any one of claims 6-9, wherein, The video frames are marked with a start signal at the start position and an end signal at the end position. An attribute field is added to a preset position of the video frames to record the type of the video frames. Video frames with the type "good frame" are the target frames.

11. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-4.

12. A non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-4.

13. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-4.

Images