Video Feature Extraction Method and System Based on Cubic Spline Curve

A technology of video features and spline curves, applied in character and pattern recognition, image data processing, instruments, etc., can solve the problems of low data redundancy and incomplete analysis of changing trends, and achieve simple calculation and flexible control Effect

Active Publication Date: 2017-09-22
ELECTRIC POWER RES INST OF GUANGDONG POWER GRID
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The feature data redundancy of this method is low, and the extracted features also have good representation ability, but it usually considers the features of each frame of video as a whole, without finely analyzing the time axis of each feature component. Trend

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
  • Video Feature Extraction Method and System Based on Cubic Spline Curve
  • Video Feature Extraction Method and System Based on Cubic Spline Curve
  • Video Feature Extraction Method and System Based on Cubic Spline Curve

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The present invention will be described in further detail below in conjunction with the embodiments and accompanying drawings, but the embodiments of the present invention are not limited thereto.

[0024] Such as figure 1 Shown, is the schematic flow chart of the video feature extraction method based on cubic spline curve of the present invention, comprises the following steps:

[0025] S11. For the video to be processed, arrange the video feature sequence in time order, so that each dimension feature component forms a discrete motion track on the time axis;

[0026] S12. For each discrete motion trajectory, use a cubic spline curve to perform segment fitting to obtain the continuous motion trajectory of the feature component;

[0027] S13. On the continuous motion track, extract feature components according to a preset threshold using the principle of equal arc length, and obtain video features of the video;

[0028] The video feature extraction method based on the ...

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 present invention provides a video feature extraction method and system based on a cubic spline curve. The method includes: arranging the video feature sequence in chronological order for the video to be processed, so that each dimensional feature component forms a discrete motion on the time axis trajectory; for each discrete motion trajectory, use a cubic spline curve to perform segmented fitting to obtain the continuous motion trajectory of the feature component; on the continuous motion trajectory, use the principle of equal arc length to extract the feature component according to the preset threshold , to obtain the video features of the video. The video feature extraction process of the invention has high speed, simple calculation and can accurately express the change of feature components.

Description

technical field [0001] The invention relates to the technical field of video feature extraction, in particular to a cubic spline-based video feature extraction method and a cubic spline-based video feature extraction system. Background technique [0002] The video feature extraction technology is to select a representative feature subset in the video feature set to characterize the video sequence. These features can not only effectively represent video content, but also reduce the redundancy of video feature data, which is of great significance to video content analysis and video retrieval. [0003] With the continuous increase of video applications, video feature extraction technology is becoming more and more important. Feature extraction technology not only requires the extracted features to effectively represent the original video, but also requires the extraction algorithm to have low time complexity and space complexity. [0004] The existing feature extraction metho...

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): G06T7/20G06K9/46
CPCG06V20/40G06V20/46
Inventor 陈世和罗嘉张曦
Owner ELECTRIC POWER RES INST OF GUANGDONG POWER GRID
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