Search

CN-121985173-A - Image transmission method of non-compressed packaged video and related equipment

CN121985173ACN 121985173 ACN121985173 ACN 121985173ACN-121985173-A

Abstract

The invention discloses an image transmission method of an uncompressed packaged video and related equipment, and relates to the technical field of data transmission, wherein the method comprises the steps of obtaining an uncompressed packaged original video file, wherein video data in the original video file is in a non-4K alignment state; the method comprises the steps of obtaining a storage address of each frame of image data in an original video file, calculating the number of filling bytes to be inserted before the corresponding frame of image data based on the storage address of each frame of image data, inserting the calculated corresponding number of filling bytes to generate a target video file, repackaging the video data in the target video file into a non-compressed packaged video file, storing the non-compressed packaged video file, and then performing non-cache reading. The invention can efficiently read the video data in the uncompressed packaged video file to the memory in a buffer-free reading mode and output the video data to the display equipment.

Inventors

  • WANG LIFANG
  • MAO KE
  • LI SIYUAN
  • LV YONG

Assignees

  • 北京数字电视国家工程实验室有限公司

Dates

Publication Date
20260505
Application Date
20251229

Claims (10)

  1. 1. An image transmission method of a non-compressed packaged video, comprising: Acquiring an original video file without compression encapsulation, wherein video data in the original video file is in a non-4K alignment state; acquiring a storage address of each frame of image data in the original video file; calculating the number of padding bytes to be inserted before the corresponding frame image data based on the storage address of each frame image data; before each frame of image data of the original video file, inserting the calculated corresponding number of stuffing bytes to generate a target video file, wherein the video data in the target video file is in a 4K alignment state; repackaging the target video file into an uncompressed packaged video file and storing the uncompressed packaged video file; Reading video data in the uncompressed packaged video file from the stored uncompressed packaged video file to a memory without cache; and outputting the video data read to the memory to the display device.
  2. 2. The image transmission method of a non-compressed packaged video according to claim 1, wherein calculating the number of padding bytes to be inserted before the corresponding frame image data based on the storage address of each frame image data, comprises: Setting the accumulated number of stuff bytes And initialized to 0; for each frame of image data in the original video file, performing the steps of: obtaining the memory address of the current frame ; According to the formula Calculating the number of padding bytes to be inserted before the current frame image data , wherein, Representing modulo operation, obtaining the number of padding bytes of the current frame by calculation Then, the accumulated stuffing byte number Updated to And (3) with A kind of electronic device.
  3. 3. The method for transmitting an image of an uncompressed packaged video according to claim 1, wherein reading video data in the uncompressed packaged video file from the stored uncompressed packaged video file to a memory without buffering comprises: And directly reading the video data blocks in the uncompressed packaged video file to the memory in a direct memory access mode by utilizing the characteristic that the video data in the uncompressed packaged video file is in a 4K alignment state.
  4. 4. A method of image transmission of a non-compressed packaged video according to any one of claims 1 to 3, wherein obtaining a storage address of each frame of image data in the original video file comprises: and analyzing the encapsulation structure of the original video file, and acquiring the storage address of each frame of image data in the original video file.
  5. 5. The image transmission system of the non-compressed packaged video is characterized by comprising an original video file acquisition module, a storage address acquisition module, a filling byte number calculation module, a filling byte insertion module, a packaged storage module, a non-cache reading module and an output module; The original video file acquisition module is used for acquiring an original video file without compression encapsulation, wherein video data in the original video file is in a non-4K alignment state; The storage address acquisition module is used for acquiring a storage address of each frame of image data in the original video file; The filling byte number calculation module is used for calculating the number of filling bytes to be inserted before the corresponding frame image data based on the storage address of each frame image data; The stuffing byte inserting module is used for inserting the calculated stuffing bytes with corresponding quantity before each frame of image data of the original video file to generate a target video file, wherein the video data in the target video file is in a 4K alignment state; The encapsulation storage module is used for re-encapsulating the target video file into an uncompressed encapsulation video file and storing the uncompressed encapsulation video file; The cache-free reading module is used for reading video data in the non-compressed packaged video file from the stored non-compressed packaged video file to a memory in a cache-free manner; the output module is used for outputting the video data read to the memory to the display device.
  6. 6. The image transmission system of claim 5, wherein the padding byte count calculation module is specifically configured to: Setting the accumulated number of stuff bytes And initialized to 0; for each frame of image data in the original video file, performing the steps of: obtaining the memory address of the current frame ; According to the formula Calculating the number of padding bytes to be inserted before the current frame image data , wherein, Representing modulo operation, obtaining the number of padding bytes of the current frame by calculation Then, the accumulated stuffing byte number Updated to And (3) with A kind of electronic device.
  7. 7. The image transmission system of claim 5, wherein the non-buffer reading module is specifically configured to: And directly reading the video data blocks in the uncompressed packaged video file to the memory in a direct memory access mode by utilizing the characteristic that the video data in the uncompressed packaged video file is in a 4K alignment state.
  8. 8. The system for image transmission of uncompressed packaged video according to any one of claims 5 to 7, wherein the storage address obtaining module is configured to parse the package structure of the original video file and obtain the storage address of each frame of image data in the original video file.
  9. 9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing a method of image transmission of a non-compressed packaged video according to any one of claims 1 to 4 when the computer program is executed by the processor.
  10. 10. A computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, the computer program when executed by a processor implementing a method for image transmission of a non-compressed packaged video according to any one of claims 1 to 4.

Description

Image transmission method of non-compressed packaged video and related equipment Technical Field The present invention relates to the field of data transmission technologies, and in particular, to an image transmission method for a non-compressed packaged video and related devices. Background With the gradual maturity of the 8K ultra-high definition television industry chain, all links of content production, coding/decoding, transmission and display to storage are covered, and the transmission of 8K ultra-high definition video becomes an important technical link. During the fabrication and packaging phase, common tools such as ffmpeg and da vinci can package video data into common packaging formats such as AVI and MOV. However, in the uncompressed format video thus directly packaged, its video data is typically in a non-4K aligned state. When attempting to read and transmit such unprocessed video, it is difficult for the conventional reading method to satisfy the extremely high data throughput required for a high frame rate (for example, 60 frames/second) at 8K resolution, and the reading speed cannot reach an index of about 6GB/s, thereby forming a transmission bottleneck. Currently, there are conventional software reading methods for reading and transmitting uncompressed packaged video. Such methods typically rely on a common file input/output interface to read video data from a storage device to a system buffer frame by frame or in blocks, then schedule copies to a target memory area via a central processor, and finally submit to a display device for rendering. This approach is universally applicable to video files in a variety of package formats, but its data path is not optimized for extreme throughput. The above-described conventional reading method has significant drawbacks. Because the internal video data of the unprocessed uncompressed packaged video is in a non-4K alignment state, the initial address of the data block on the storage medium is random, so that the system cannot utilize high-efficiency data transmission mechanisms such as direct memory access of the underlying hardware. Read operations often involve multiple non-aligned memory accesses, additional data copies, and higher central processor overhead, which severely limit the data transfer rate. Therefore, for 8K non-compressed packaged video with extremely large data volume, the traditional method cannot realize stable and real-time rapid reading and outputting, and is difficult to meet the requirement of the ultra-high definition industry on efficient transmission. In order to solve the speed bottleneck existing in the conventional method for reading non-4K aligned non-compressed packaged video, an innovative processing and transmission scheme is needed to be proposed. The scheme needs to be capable of preprocessing the original video file to enable the original video file to meet the hardware requirement of efficient transmission, so that a key path for high-speed transmission of 8K ultra-high definition video is opened. Disclosure of Invention The invention aims to solve the technical problems of the prior art, and particularly provides an image transmission method and related equipment for a non-compressed packaged video, wherein the method comprises the following steps of: 1) In a first aspect, the present invention provides an image transmission method for a non-compressed packaged video, which has the following specific technical scheme: Acquiring an original video file without compression encapsulation, wherein video data in the original video file is in a non-4K alignment state; Acquiring a storage address of each frame of image data in an original video file; calculating the number of padding bytes to be inserted before the corresponding frame image data based on the storage address of each frame image data; Before each frame of image data of an original video file, inserting the calculated corresponding number of stuffing bytes to generate a target video file, wherein the video data in the target video file are in a 4K alignment state; Repackaging the target video file into an uncompressed packaged video file and storing the uncompressed packaged video file; Reading video data in the uncompressed packaged video file from the stored uncompressed packaged video file to a memory without cache; and outputting the video data read to the memory to the display device. The image transmission method of the non-compressed packaged video has the following beneficial effects: Firstly, an original video file in a non-4K aligned state and without compression encapsulation is obtained, and a storage address of each frame of image data is obtained through analysis. Based on these addresses, accurate stuff bytes are calculated and inserted, generating a target video file with video data in a 4K aligned state. The key step enables the non-compressed packaged video file after being repackaged and stored to be read at high speed by fully utiliz