Unlock instant, AI-driven research and patent intelligence for your innovation.

A method of extracting video key frame with video compression coding information

A technology of video key frames and coding information, which is applied in the direction of digital video signal modification, image communication, electrical components, etc., can solve the problems of slow video frame processing speed, long processing time, and impracticality, so as to shorten the processing time, The effect of fast processing speed and high accuracy

Active Publication Date: 2021-12-07
XIAN UNIV OF POSTS & TELECOMM
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The common point of the above methods is that the intra-frame prediction mode value is used as the feature, and the experiment is only for the full intra-frame mode, the processing speed of the video frame is slow, the processing time is long, and it is not practical

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A method of extracting video key frame with video compression coding information
  • A method of extracting video key frame with video compression coding information
  • A method of extracting video key frame with video compression coding information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] Taking the video sequence A New Horizon, segment 02 in the international VSUMM data set as an example, the method steps of extracting video key frames with video compression coding information in this embodiment are as follows (see figure 1 ):

[0044] (1) Extract depth and frame bit number features

[0045] Determine the rate-distortion cost J of the coding unit according to formula (1):

[0046]

[0047] where D x,y and R x,y Respectively represent the distortion and the number of coded bits of the (x, y)th pixel in the coding unit, x∈{1,2,…,H}, y∈{1,2,…,W}, W×H is the video resolution λ≥0 is the Lagrangian coefficient, W and H are finite positive integers, and W>H, the value of W in this embodiment is 352, and the value of H is 240.

[0048] Determine the depth feature vector F of the encoded frame according to formula (2) n :

[0049] f n ={f 1 , f 2 ,..., f α} (2)

[0050]

[0051] Where n represents the nth coded frame of the video, n∈{1,2,...,N},...

Embodiment 2

[0073] Taking the video sequence Oceanfloor Legacy as an example, the steps of the method for extracting video key frames using video compression coding information in this embodiment are as follows:

[0074] (1) Extract depth and frame bit number features

[0075] Determine the rate-distortion cost J of the coding unit according to formula (1):

[0076]

[0077] where D x,y and R x,y Respectively represent the distortion and the number of coded bits of the (x, y)th pixel in the coding unit, x∈{1,2,…,H}, y∈{1,2,…,W}, W×H is the video resolution λ≥0 is the Lagrangian coefficient, W and H are finite positive integers, and W>H, the value of W in this embodiment is 176, and the value of H is 144.

[0078] Determine the depth feature vector F of the encoded frame according to formula (2) n :

[0079] f n ={f 1 , f 2 ,..., f α} (2)

[0080]

[0081] Where n represents the nth coded frame of the video, n∈{1,2,...,N}, N is the total number of frames of the video, and t...

Embodiment 3

[0103] Taking the video sequence Exotic Terrane as an example, the steps of the method for extracting video key frames using video compression coding information in this embodiment are as follows:

[0104] (1) Extract depth and frame bit number features

[0105] Determine the rate-distortion cost J of the coding unit according to formula (1):

[0106]

[0107] where D x,y and R x,y Respectively represent the distortion and the number of coded bits of the (x, y)th pixel in the coding unit, x∈{1,2,…,H}, y∈{1,2,…,W}, W×H is the video resolution λ≥0 is the Lagrangian coefficient, W and H are finite positive integers, and W>H, the value of W in this embodiment is 7680, and the value of H is 4320.

[0108] Determine the depth feature vector F of the encoded frame according to formula (2) n :

[0109] f n ={f 1 , f 2 ,..., f α} (2)

[0110]

[0111] Where n represents the nth coded frame of the video, n∈{1,2,...,N}, N is the total number of frames of the video, and th...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

A method for extracting video key frames by using video compression coding information, which is composed of extracting depth and frame bit number features, lens switching detection and extracting key frames. The invention adopts the encoding unit depth information in the video code stream and the frame bit number compression domain feature to detect the shot switching, obtain the shot fragments, and extract key frames. The invention makes full use of the video in the compressed domain and can be processed without decompression, reduces the calculation process, shortens the processing time, and improves the processing speed. The present invention and existing method are through comparative test, and experimental result shows, the accuracy rate of the present invention's method has improved 12.1%, and recall rate has improved 5.3%, and F value has improved 8.4%, and the key frame extracted can express well The main content of the original video. The method of the invention has the advantages of small calculation amount, high efficiency, high accuracy rate, fast processing speed and the like, and can be used for processing video images.

Description

[0001] Technology area [0002] The invention belongs to the technical field of digital video retrieval, and in particular relates to a method for extracting video key frames by using video compression coding information. Background technique [0003] With the rapid development of multimedia technology and network technology, video data has grown rapidly, and there has been an unprecedented amount of data. How to effectively manage video and quickly obtain important information in video has become a research hotspot. In this context, extracting key frames has become an effective way to solve this problem. By extracting key frames, not only can the amount of video data be greatly reduced, but also the important information of the original video can be well expressed, saving retrieval time. , which improves the efficiency of video retrieval. [0004] At present, domestic and foreign scholars have done a lot of research work on key frame extraction methods. According to the proc...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): H04N19/147H04N19/19H04N19/172H04N19/42H04N19/85H04N19/70
CPCH04N19/147H04N19/172H04N19/19H04N19/42H04N19/70H04N19/85
Inventor 艾达梁嘉倩
Owner XIAN UNIV OF POSTS & TELECOMM