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

Correlation filtering tracking method based on self-adaptive regular feature combined time correlation

A correlation filtering and time-correlation technology, applied in image data processing, instrumentation, computing, etc., can solve problems such as incomplete filter targets and excessive background information

Pending Publication Date: 2021-05-18
XIAN UNIV OF TECH
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to provide a correlation filter tracking method based on adaptive regular features combined with time correlation, which solves the problem that the original windowing will cause the target learned by the filter to be incomplete or have too much background information when the scale of the target changes. question

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
  • Correlation filtering tracking method based on self-adaptive regular feature combined time correlation
  • Correlation filtering tracking method based on self-adaptive regular feature combined time correlation
  • Correlation filtering tracking method based on self-adaptive regular feature combined time correlation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0159] This algorithm uses the OTB-100 dataset for evaluation. The algorithm development environment is Matlab R2018b and the deep learning library MatConvNet-Gpu. The processor is AMD Ryzen 7 1700Eight-Core Processor, and the GPU is GTX-1060. In the experiment, the algorithm uses the same parameters for the test video, and the specific setting is: regularization parameter λ=10 -4 , the adjustment factor δ=0.43, the learning rate η=0.01, the Gaussian variance ε=0.3, the search area adjustment parameter k=2, and select the 3, 4, 5 layer features in the VGG19 network as the output features. The proposed algorithm is experimentally evaluated by comparing it with state-of-the-art tracking methods.

[0160] The algorithm in the present invention is HZXT, and the proposed algorithm is evaluated by comparing with three representative trackers, namely correlation filtering-based SRDCF, BACF, and deep learning-based HCF. First draw a comparison chart of the tracking algorithm in terms...

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 correlation filtering tracking method based on self-adaptive regular feature combined time correlation, and the method specifically comprises the following steps: 1, selecting a to-be-tracked video sequence, and initializing a first frame of the video sequence; 2, determining the central position of the target in a second frame of the tracking video sequence, and estimating the scale of the target in the second frame; and step 3, determining the position of the target in the t-th frame of the tracking video sequence, and estimating the scale of the target in the t-th frame, wherein t is greater than 2. According to the method, the problem that the original windowing causes incomplete target learned by the filter or excessive background information when the scale of the target changes is solved.

Description

technical field [0001] The invention belongs to the technical field of video image tracking in machine vision, and relates to a correlation filter tracking method based on adaptive regular features combined with time correlation. Background technique [0002] With the rapid development of computer technology, object tracking has become one of the hot topics in computer vision research. Visual target tracking, visual target tracking is to continuously mark the position of the tracked target through some algorithms in each frame of the video sequence, so as to obtain the motion parameters of the target, such as position, speed, acceleration, etc., so as to carry out further processing and analysis to realize Behavioral understanding of targets to accomplish more advanced tasks. As an important branch of the field of computer vision, it has various applications in various fields of science and technology, national defense construction, aerospace, medicine and health, and the n...

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): G06T7/262G06T7/246
CPCG06T7/262G06T7/248G06T2207/10016G06T2207/20056G06T2207/20081G06T2207/20084
Inventor 刘龙惠志轩杨尚其
Owner XIAN 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