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

Target tracking algorithm based on scale adaptive correlation filtering and feature point matching

A scale adaptive, feature point matching technology, applied in the field of visual tracking, can solve the problem of occlusion, can not avoid the target model well, can not well eliminate the free points, difficult to achieve processing speed and other problems, to achieve long-term stable goals Tracking, processing speed is satisfied, and the effect of reducing the introduction of error information

Active Publication Date: 2017-06-09
DALIAN UNIV OF TECH
View PDF5 Cites 35 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The existing tracking algorithm based on correlation filtering has been able to obtain a very high processing speed to ensure the real-time processing requirements of target tracking, but it still cannot prevent the target model from being polluted and cannot adapt to the size change of the target for the occlusion problem.
In addition, in the tracking algorithm based on feature point matching, how to select representative feature points to represent the target will directly affect the tracking effect, and the tracking algorithm based on feature point matching is difficult to achieve real-time processing speed, and can not remove the free objects well. point

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
  • Target tracking algorithm based on scale adaptive correlation filtering and feature point matching
  • Target tracking algorithm based on scale adaptive correlation filtering and feature point matching
  • Target tracking algorithm based on scale adaptive correlation filtering and feature point matching

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] The present invention will be further described below.

[0018] The first step is to establish a scale adaptive correlation filtering tracking module CFF to process each frame of image

[0019] Given the initial information, take the target area frame of the initial frame as a positive sample, and use the image block x of W×H w,h To express, the cyclic shift around the center of the target area obtains negative samples, and the cyclic matrix of the area around the target is used to collect positive and negative samples; the initial information includes the initial frame and the corresponding target area frame;

[0020] a) Train the object detector

[0021] Use the image blocks to train a target detector with correlation filtering, that is, find the regression function f(z)=ω T z to get the minimized squared error as shown in equation (1):

[0022] min ω Σ w，h |w,h ),ω>-y(w,h)| 2 +λ||w|| 2 . (1)

[0023] Among them, φ is the mapping function that maps linear reg...

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 belongs to the visual tracking field, and provides a target tracking algorithm based on the scale adaptive correlation filtering and feature point matching which solves a long-time target tracking problem. The target tracking algorithm comprises establishing a scale adaptive correlation filtering tracking module CFF to process each frame of image; establishing a tracking module MTF based on the feature pint matching and an optical flow; and establishing a cooperative processing determination module of the CFF and the MTF. According to the present invention, a tracking problem is decomposed into the CFF and the MTF which can assist mutually, whether the algorithm is updated is decided by determining the shielded degree of a target or determining whether the target has disappeared in the view field, thereby preventing a model from being polluted by the background information to generate a drift phenomenon. When appearing in the view field again, the target can be detected again, and the corresponding modules are updated to track continuously and stably for a long time. Moreover, the processing speed of the target tracking algorithm satisfies the real-time processing requirement completely, and the target tracking algorithm has a very good effect aiming at an actual complicated scene.

Description

technical field [0001] The invention belongs to the field of visual tracking, relates to a target tracking algorithm based on scale adaptive correlation filtering and feature point matching, and solves the problem of long-term target tracking. Background technique [0002] In recent years, with the continuous development of target tracking algorithms, most tracking algorithms can well solve the slight occlusion problem of a single target in a simple environment. However, more robust long-term, real-time tracking algorithms are still needed in more complex situations such as severe occlusion or objects leaving the field of view. [0003] Existing tracking algorithms based on correlation filtering have been able to achieve very high processing speed to meet the real-time processing requirements of target tracking, but for the occlusion problem, it is still unable to avoid target model pollution and cannot adapt to target size changes. In addition, how to select representative...

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): G06T7/246G06T7/262
CPCG06T2207/10016G06T2207/20056G06T2207/20081
Inventor 王涛王凡胡小鹏
Owner DALIAN UNIV OF 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

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