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

Vehicle tracking method in fusion with feature matching and optical flow method

A fusion feature and vehicle tracking technology, which is applied in the field of vehicle tracking by fusion feature matching and optical flow method, can solve the problems of tracking system instability, offset error of related information parameters, etc.

Inactive Publication Date: 2016-10-12
XI'AN PETROLEUM UNIVERSITY
View PDF3 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a vehicle tracking method that combines feature matching and optical flow method, which can effectively solve the problem of offset error in relevant information parameters caused by using feature point matching based on exhaustive search alone in the prior art and using optical flow alone technical problems that lead to instability of the tracking system

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
  • Vehicle tracking method in fusion with feature matching and optical flow method
  • Vehicle tracking method in fusion with feature matching and optical flow method
  • Vehicle tracking method in fusion with feature matching and optical flow method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0050] see Figure 1~4 , a vehicle tracking method that combines feature matching and optical flow, including the following steps:

[0051] Step 1, use a rectangular frame to mark the vehicle target to be tracked in the initial frame, and use the SURF feature extraction algorithm to extract the feature points in the rectangular frame, expressed as a feature point set R;

[0052] Step 2, extract the coordinate O of the center position of the rectangular frame in step 1, and:

[0053] Calculate the relative distance (r ij ) i≠j ;

[0054] According to the formula (1.2), calculate the relative distance h(p i ,O);

[0055] Calculate the relative angle α between any two feature points in the point set R in step 1 according to formula (1.3), where 180°>α≥0°; figure 1 As shown, the rotation angle of α is counterclockwise;

[0056] According to...

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 vehicle tracking method in fusion with feature matching and optical flow method. The method comprises the following steps: determining interrelation of target related information parameters between frame movement targets, recording the target trajectory through the matching of the neighbor frames to realize the tracking to the target; on one hand, the deviation error caused by the recursive estimation of a pyramid model thereof is avoided while single adopting the KLT tracking algorithm, on the other hand, the feature matching algorithm is used as a compensation mechanism to update and correct the target feature point set; not only the scale change and the rotation change produced in the movement process of the vehicle target are adapted, but also the stability and robustness of the tracking algorithm are improved; the problem that the feature point in the tracking process due to the adoption of the KLT in bidirectional reversibility constraint is solved.

Description

technical field [0001] The invention belongs to the technical field of video detection, and in particular relates to a vehicle tracking method combining feature matching and an optical flow method. Background technique [0002] As an important research content in the field of computer vision and image processing, video-based vehicle detection technology has attracted more and more people's attention due to its convenience and speed. Video-based moving vehicle tracking is an attempt to determine the target correlation between moving targets in each frame. Information parameters, such as the relationship between position, speed, color, texture, shape, etc., record the trajectory and other information of the target through the matching relationship between the front and rear frames, and realize the tracking of the target. How to get the corresponding points between the video frames, that is Feature point matching problem is one of the key technologies of target tracking. [00...

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): G06K9/00G06K9/20G06K9/46G06K9/62
CPCG06V20/584G06V10/225G06V10/443G06V10/751G06V2201/08G06F18/231
Inventor 卢胜男李小和张峰
Owner XI'AN PETROLEUM UNIVERSITY
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com