A video key frame extraction method

A technology of video key frame and extraction method, applied in image data processing, instrumentation, calculation and other directions, can solve problems such as large amount of calculation, complex algorithm, inability to maintain the timing relationship and dynamic information of video frames, etc., and achieve efficient extraction and solution calculation. Process complex effects

Active Publication Date: 2017-06-06
MINZU UNIVERSITY OF CHINA
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The frame difference method based on color or color histogram is sensitive to light changes, and cannot reflect global features or local detail changes.
The key frame extraction method based on motion analysis uses optical flow analysis to calculate the motion of the video frame, which has the problem of complex algorithm and large amount of calculation.
The key frame extraction method based on clustering can effectively obtain the visual content of the lens with significant changes, but the clustering method cannot maintain the timing relationship and dynamic information of the video frame

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 video key frame extraction method
  • A video key frame extraction method
  • A video key frame extraction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] The implementation steps of video key frame extraction method of the present invention comprise:

[0018] (1) Read the video frame frame by frame, convert the video frame image into a grayscale image, calculate the video grayscale centroid and store the grayscale centroid, and use the grayscale centroid sequence to represent the video frame sequence, detailed steps:

[0019] a. Convert the video frame image pixel RGB value to the corresponding pixel value of the grayscale image, and the conversion formula is:

[0020] Gray=R*0.11+G*0.59+B*0.30,

[0021] b. Calculate the gray centroid, the formula is as follows:

[0022] where x ij for X M×N (X M×N Represents the grayscale image whose size is M×N) The grayscale value of the pixel at the i-th row and j-column position, the corresponding image size of the video frame is M×N;

[0023] c. Save the grayscale centroid coordinates (X C ,Y C ), all video frame image gray-scale centroids form a gray-scale centroid sequen...

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

The invention discloses a method for extracting a video key frame, and belongs to the field of video data processing. The method for extracting the video key frame comprises the steps that the gray level mass centers of video frames are calculated, a video frame sequence is segmented into a plurality of frame sequences with vision similarity continuity according to the distance of the gray level mass centers of the adjacent frames and the distance between the gray level mass center of a current video frame and the average gray level mass center of presequence vision similar frame sequences, and the key frame is selected from the vision similar frame sequences. The problems that an existing key frame extraction technology is complex in computation process and large in computation quantity are solved.

Description

technical field [0001] The invention relates to a video key frame extraction method, which belongs to the technical field of video data processing. Background technique [0002] With the continuous improvement of network infrastructure, the application of new network technology and the popularization of video shooting equipment, the total amount of video resources and people's demand for video resources have increased dramatically. The demand for intelligent labeling and automatic classification of video information to realize automatic detection, filtering and video content retrieval of video content is constantly increasing. As the basic technology of video information processing, video key frame extraction directly affects the results of advanced video processing. The current video key frame extraction methods mainly include: based on color (or histogram) frame difference method, based on motion analysis method and based on video frame clustering method. The frame diffe...

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): G06T7/10
Inventor 宋伟邢高娃杨国胜杨培刘宁宁李明刘向春
Owner MINZU UNIVERSITY OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap