Adaptive method for removing feature points of video frame

A feature point, self-adaptive technology, applied in the fields of instruments, character and pattern recognition, computer parts, etc., can solve the problem of low matching speed of video feature points, reduce matching complexity, reliable design principle, and highlight substantial features Effect

Inactive Publication Date: 2017-04-26
南京中孚信息技术有限公司
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide and design an adaptive video frame feature point thinning method to solve the above-mentioned technical problems in view of the technical defect of low video feature point matching speed in the above-mentioned prior art

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
  • Adaptive method for removing feature points of video frame
  • Adaptive method for removing feature points of video frame
  • Adaptive method for removing feature points of video frame

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. The following embodiments are explanations of the present invention, but the present invention is not limited to the following embodiments.

[0025] Such as figure 1 As shown, a kind of adaptive video frame feature point thinning method provided by the present invention comprises the following steps:

[0026] Step 1): extract the key frame of the video to be detected, and extract the feature point set of the video frame through the feature point detection algorithm, which is recorded as P; at the same time, carry out invisible grid division on the key frame, and divide it into grid units of the same size, The set of feature points of each grid cell is denoted as P ij , P ij The sum of is P, P ij The relationship with P is as follows:

[0027] P={P (i,j)} Formula 1)

[0028] Step 2): Determine the adaptive clustering algorithm parameters: ca...

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 relates to an adaptive method for removing feature points of a video frame. The method includes the following steps: step 1. Extracting the key frame of a to-be-detected video, extracting a feature point set of the video frames by the feature point detection algorithm, marking as P; at the same time conducting hidden grid division on key frame and dividing the the key frame into grid units having same sizes, the set of feature points of each grid unit being marked as Pij; step 2. determining adaptive clustering algorithm parameters, computing information entropy of the grid units from step 1, determining the parameter information of the clustering algorithm based on the information entropy; step 3. clustering the set of feature point sets of the grid units Pij by using the clustering algorithm, constituting a set of feature points after point removing and marking the set of feature points as P<N><i,j>; step 4. For each grid unit, repeating step 2-3, obtaining the result from removing the feature points of the key frame and marking as PN; step 5. repeating step 1-4, implementing the removing of feature point of the to-be-detected video.

Description

technical field [0001] The invention belongs to the technical field of video monitoring data analysis, and in particular relates to an adaptive video frame feature point thinning method. Background technique [0002] In the process of video surveillance data analysis, the detection and matching of feature points is a crucial technology and a key step in sensitive video detection. However, the number of feature points extracted in the video detection process is large, which has a great impact on the matching of feature points, especially for video frames with rich textures such as trees and forests. As the video resolution becomes higher and the amount of video data increases, the matching speed of feature points becomes the key to the real-time detection of sensitive video. High-density feature points have great redundancy for the detection of sensitive videos, which seriously affects the efficiency of video detection. [0003] Since the speed of feature point matching dir...

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
IPC IPC(8): G06K9/00G06K9/46G06K9/62
CPCG06V20/47G06V10/462G06F18/23213
Inventor 孙宏跃曲志峰楼方平李军陈丹伟潘飚陈英华纪翀
Owner 南京中孚信息技术有限公司
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