Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Fast video key frame extraction method of principal component characteristic curve analysis

A technology of video key frames and characteristic curves, applied in image analysis, image data processing, instruments, etc., can solve the problems of inability to accurately extract key frames and good algorithm effects

Inactive Publication Date: 2014-07-23
HANGZHOU XISONG TECH
View PDF2 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The number of key frames extracted by this method is determined. The disadvantage is that only when there are obvious clustering characteristics between the video frames and the number of clusters is consistent with the real data cluster distribution, the algorithm better effect
Otherwise, due to the limitations of the clustering algorithm itself, key frames cannot be accurately extracted

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
  • Fast video key frame extraction method of principal component characteristic curve analysis
  • Fast video key frame extraction method of principal component characteristic curve analysis
  • Fast video key frame extraction method of principal component characteristic curve analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0033] For a natural landscape video sequence containing 11096 frames, follow the method described above:

[0034]1) Extract four image visual features of SIFT, HOG, GIST and PHOI from the video frame image, a total of 500+576+512+2040=3628-dimensional feature expression, splicing the above four types of image visual features in sequence to get The characteristic matrix X=[x that this video sequence image frame characteristic constitutes 1 ,x 2 ,...,x n ]∈R d×n , where d is 3628 dimensions, n=11096;

[0035] 2) Perform PCA dimension reduction processing on the feature matrix X to obtain a 500-dimensional image low-dimensional feature expression Y=W T X=[y 1 ,y 2 ,...,y n ]∈R m×n , where y i is the low-dimensional feature expression corresponding to the i-th frame of the video sequence;

[0036] 3) The low-dimensional feature expression Y of the image is regarded as m principal component characteristic curves that change with time series, and each principal component ...

Embodiment 2

[0039] For a Tai Chi motion video sequence that includes 12444 frames, follow the method described above:

[0040] 4) Extract four image visual features of SIFT, HOG, GIST and PHOI from the video frame image, totaling 500+576+512+2040=3628 dimensional feature expression, splicing the above four types of image visual features in sequence to get The characteristic matrix X=[x that this video sequence image frame characteristic constitutes 1 ,x 2 ,...,x n ]∈R d×n , where d is 3628 dimensions, n=12444;

[0041] 5) Perform PCA dimension reduction processing on the feature matrix X to obtain a 500-dimensional image low-dimensional feature expression Y=W T X=[y 1 ,y 2 ,...,y n ]∈R m×n , where y i is the low-dimensional feature expression corresponding to the i-th frame of the video sequence;

[0042] 6) The low-dimensional feature expression Y of the image is regarded as m principal component characteristic curves that change with time series, and each principal component c...

Embodiment 3

[0045] For a BBC news video sequence containing 2340 frames, follow the method described above:

[0046] 7) Extract four image visual features of SIFT, HOG, GIST and PHOI from the video frame image, a total of 500+576+512+2040=3628-dimensional feature expression, splicing the above four types of image visual features in sequence to get The characteristic matrix X=[x that this video sequence image frame characteristic constitutes 1 ,x 2 ,...,x n ]∈R d×n , where d is 3628 dimensions, n=2340;

[0047] 8) Perform PCA dimension reduction processing on the feature matrix X to obtain a 500-dimensional image low-dimensional feature expression Y=W T X=[y 1 ,y 2 ,...,y n ]∈R m×n , where y i is the low-dimensional feature expression corresponding to the i-th frame of the video sequence;

[0048] 9) The low-dimensional feature expression Y of the image is regarded as m principal component characteristic curves that change with time series, and each principal component characteri...

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 fast video key frame extraction method of the principle characteristic curve analysis. The method includes the steps that firstly, a visual characteristic expression is extracted from video image frames; secondly, PCA dimension reduction processing is performed on a characteristic matrix X composed of all video image frame characteristics, and an image low-dimension characteristic expression Y is obtained; thirdly, each characteristic curve in the Y is searched for a curve local extreme point, and the image low-dimension characteristic expression of the frames wherein the curve local extreme points exist is added into a candidate key frame low-dimension characteristic set T; finally, K mean value clustering is performed on the candidate key frame low-dimension characteristic set, the original video sequence image frame corresponding to the candidate key frame low-dimension characteristic and is closest to the clustering center is used as a final video key frame to be sent back, and therefore extraction of the video key frame is obtained. The fast video key frame extraction method of the principle characteristic curve analysis has the advantages of being small in calculation amount, simple and easy to achieved, and influences of variations of object movement, colors, illumination and the like existing in a video image sequence can be effectively resisted.

Description

technical field [0001] The invention relates to a video key frame extraction technology, a data dimension reduction technology and a clustering technology, in particular to a method for advancing video key frames by using the clustering technology. Background technique [0002] With the rapid development of network and multimedia technology, video data is showing explosive growth. Effective management and indexing of these video data requires efficient video shot detection algorithms and video key frame extraction algorithms. What the present invention relates to is the video key frame extraction technology, so the relevant video key frame extraction technology is briefly reviewed below. [0003] A key frame refers to the most important and representative image frame in a video shot, which contains most of the semantic information that the shot wants to express. Extracting key frames from the video, on the one hand, can facilitate users to quickly browse the video, on the ...

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 Applications(China)
IPC IPC(8): G06T7/00G06T7/20
Inventor 陈晋音黄坚
Owner HANGZHOU XISONG TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products