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

Method of realizing video target tracking by adopting two-layer cascading Boosting classification algorithm

A classification algorithm and target tracking technology, applied in the field of image processing, can solve the problems of single Haar-like feature construction template, loss of image color and texture details, etc.

Active Publication Date: 2016-06-29
EAST CHINA NORMAL UNIVERSITY
View PDF3 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Compared with the traditional method, the present invention uses multiple filters to extract features from the image block, expresses the features of the image block more finely, and solves the problem of using a Haar-like feature to construct a single template and losing image color and texture details; in addition , the proposed tracking method uses a two-layer cascaded structure to select the filter type and image block position separately, and make the selected features suitable for the tracking task as much as possible

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
  • Method of realizing video target tracking by adopting two-layer cascading Boosting classification algorithm
  • Method of realizing video target tracking by adopting two-layer cascading Boosting classification algorithm
  • Method of realizing video target tracking by adopting two-layer cascading Boosting classification algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] The technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings and specific embodiments.

[0054] refer to figure 1 , the implementation process of the present invention includes the following steps: one is the preprocessing process of the image to obtain the target sample and the image block in the target area; the other is to extract features through filters to obtain the feature pool of positive and negative samples; the third is to include online features The two-layer Boosting cascade algorithm for selection and weight training; the fourth is target tracking through classifier detection. Specific process:

[0055] 1. Preprocessing of video tracking

[0056] In the first frame of the image sequence, the target area for tracking is first marked. A number of image blocks with sizes and relative positions are randomly generated in the target area. Use the convolution kernel group of the ...

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 method of realizing video target tracking by adopting a two-layer cascading Boosting classification algorithm. The method is characterized in that image pretreatment is used to acquire target samples and image blocks in target areas; characteristic values of positive samples and negative samples can be acquired by adopting characteristic extraction of filters; the two-layer Boosting cascading algorithm comprising the on-line characteristic selection and the weight training is provided; and a classifier is used to detect the target tracking. A plurality of filters are used for the characteristic extraction of the image blocks, and the characteristics of the image blocks can be expressed in a refined manner, and then the problems such as single template formed by adopting Haar-like characteristics, loss of image colors and texture details can be solved; and in addition, by adopting the two-layer cascading structure, the filter types and the image block positions can be selected respectively, and then the selected characteristics are more suitable for the tracking task.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to a method for realizing video target tracking by using a two-layer cascaded Boosting classification algorithm. Background technique [0002] Video-based object tracking technology is a classic problem that many scholars in the field of computer vision and image processing pay attention to. With the rapid development of technologies such as computer storage, network communication, and image processing, video tracking technology has also made great progress. [0003] It is very challenging to design a stable and efficient target tracking algorithm. The difficulty mainly comes from the influence of factors such as complex background, target occlusion, and target deformation and rotation in the application. The current popular algorithms are mainly divided into two categories: generative and discriminative. The generation method uses the tracking target as a feature to constr...

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): G06T7/00G06K9/62
CPCG06T2207/10024G06T2207/10016G06F18/241
Inventor 瞿恺孙力徐姗姗
Owner EAST CHINA NORMAL 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