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

Fractional differential-based multi-feature combined sparse representation tracking method

A fractional differentiation and sparse representation technology, applied in the field of image recognition and target tracking, which can solve the problems of ignoring the influence of tracking accuracy, drift, and single feature selection.

Inactive Publication Date: 2017-03-22
NORTH CHINA ELECTRIC POWER UNIV (BAODING)
View PDF2 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] At present, in the technical field of image recognition and target tracking, the feature selection for describing the target is relatively simple, and different features have different abilities to describe the target. The sharing and complementarity between different features can improve the performance of a single feature; and local The way of building a dictionary with overlapping blocks repeatedly calculates a lot of background information, and the more times the background information is calculated, the greater the possibility of drift during the tracking process, which affects the real-time and robustness of the tracking; in the actual tracking target When , only select the target subject as the main target of tracking, ignoring the impact of the surrounding information of the same moving target subject on the tracking accuracy

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
  • Fractional differential-based multi-feature combined sparse representation tracking method
  • Fractional differential-based multi-feature combined sparse representation tracking method
  • Fractional differential-based multi-feature combined sparse representation tracking method

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment 1

[0047] Specific embodiment 1, such as figure 1 As shown, a sparse representation tracking method based on fractional differentiation and multi-feature union, the specific steps are as follows:

[0048] Step 1, local block of the template image area

[0049] In order to track the target more accurately, the area of ​​the template image is divided into 9 parts, namely sub-block 1 to sub-block 9, that is, the size of the target block is 30×30 pixels, and the size of sub-block 1 and sub-block 2 is 10×20 pixels. Sub-block 3 and sub-block 4 are 20 × 10 pixels, sub-block 5 is 10 × 10 pixels, sub-block 6, sub-block 7, sub-block 8 and sub-block 9 are 20 × 20 pixels, a total of 9 image sub-blocks are generated, and the extraction grayscale and HOG features such as figure 2 shown. The overlapping sub-blocks contain more information about the tracking target, and multiple calculations of this part of information will enhance the robustness of tracking.

[0050] Step 2, feature descri...

specific Embodiment 2

[0084] Specific embodiment 2, as another embodiment of the present invention, in step 1, the size of the target block is 30×30 pixels, and the target image area is divided into 5 blocks of equal size, that is, the size of the sub-block is 15×15 pixels , with a step size of 15 pixels, sub-block 1, sub-block 2, sub-block 3 and sub-block 4 equally divide the target block, each block has a size of 15×15 pixels, plus a sub-block with a size of 15×15 pixels in the center area , a total of 5 image sub-blocks are generated, such as Figure 5 As shown, the division method of step 2 is the same as that of step 1. The overlapping sub-blocks in the middle contain more information about the tracking target, and multiple calculations of this part of information will enhance the robustness of tracking.

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 provides a fractional differential-based multi-feature combined sparse representation tracking method. The method includes the following steps: in a frame of particle filtering, first, performing partitioning processing on a target image region, dividing the target region into 9 related and unequal subblocks according to the features of the target region, extracting the gray scale feature and HOG feature of each subblock, combining the two features to perform sparse representation on a target subblock, and also performing the same feature extraction and sparse representation on 8 adjacent regions around the target; then, adopting a nucleating accelerated neighbor gradient algorithm to jointly solve sparse coefficients of 9 candidate particles; and finally, regarding target blocks in different positions as different categories, utilizing a block of the same category as a candidate particle block and a representation coefficient in a dictionary to reconstruct the block, and building a likelihood function according to a reconstruction error to determine an optimal candidate particle, thereby realizing accurate tracking of a main target and 8 auxiliary targets.

Description

technical field [0001] The inventor relates to the technical field of image recognition and target tracking, especially a sparse representation tracking method based on fractional differentiation and multi-feature union. Background technique [0002] At present, in the technical field of image recognition and target tracking, the feature selection for describing the target is relatively simple, and different features have different abilities to describe the target. The sharing and complementarity between different features can improve the performance of a single feature; and local The way of building a dictionary with overlapping blocks repeatedly calculates a lot of background information, and the more times the background information is calculated, the greater the possibility of drift during the tracking process, which affects the real-time and robustness of the tracking; in the actual tracking target When , only the target subject is selected as the main target of trackin...

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): G06T7/246G06K9/62G06K9/46
CPCG06T2207/20021G06T2207/20081G06V10/40G06V10/513G06F18/28
Inventor 牛为华赵鹏崔克彬袁和金
Owner NORTH CHINA ELECTRIC POWER UNIV (BAODING)
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