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

Method for tracking moving object

A moving target and tracking algorithm technology, applied in image data processing, instruments, character and pattern recognition, etc., can solve the problems of tracking loss, tracking failure, irreversible and so on

Inactive Publication Date: 2013-04-03
HARBIN ENG UNIV
View PDF3 Cites 40 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the Camshift tracking algorithm is greatly affected by other moving targets around, and it is easy to mistake non-target points for target points, which will change the size of the target and cause tracking failure, resulting in tracking loss. [8]
The traditional Camshift target tracking algorithm uses color information as a feature for tracking. When the target color is similar to the background or non-target, tracking loss will also occur.
Moreover, the traditional Camshift target tracking algorithm tends to fail to track fast moving targets, and cannot recover from the failure [9]

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 for tracking moving object
  • Method for tracking moving object
  • Method for tracking moving object

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] The present invention is described in more detail below in conjunction with accompanying drawing example:

[0060] 1. Selection of motion target features

[0061] Good target features are equally important as good tracking algorithms. The selection of features directly determines the accuracy of weak classifiers. Selecting high-precision features can not only reduce the number of learning samples, but also greatly reduce the number of weak classifiers. The features selected by the present invention combine local orientation histogram features (LOH) and color features (RGB) which are more suitable for pedestrian tracking in the scene. The use of local direction features has two advantages: (1) Gradient features are not sensitive to light and are very little affected by light changes; (2) The description of geometric features is superior to other features, and can indirectly express contours. In general, when objects and backgrounds are similar in color, their textures ...

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 method for tracking a moving object. The method comprises the following steps of 1, accurately detecting the moving object by a rapid moving object detection method based on a codebook model; 2, initializing a weak classifier group of an online Adaboost algorithm to obtain a strong classifier, fusing local direction histogram characteristics and color characteristic in selection of characteristics of the moving object; 3, computing a characteristic matrix of an online Adaboost tracking algorithm and the weak classifier to obtain a confidence chart, updating the weak classifier according to the obtained moving object position by a CamShift tracking algorithm on the confidence chart, and finally obtaining a tracking result of a whole segment of video sequence. The method for tracking the moving object capable of effectively tracking the moving object which largely deforms within a short period of time, generates shelter even large-area shelter, is similar to the colors of the other moving objects in background, rapidly changes and accelerates is provided by the invention.

Description

technical field [0001] The invention relates to a moving target tracking technology, in particular to a moving target tracking method based on the combination of an online Adaboost algorithm and a CamShift algorithm. Background technique [0002] The research on tracking technology based on the characteristics of moving objects is a hot topic in the field of computer vision in recent years. Although biometrics such as fingerprints, palmprints, and veins have been extensively researched and initially applied in the security field, these biometrics belong to contact recognition, which greatly limits their application range. Relatively speaking, the "non-contact" recognition technology such as gait and face recognition, which combines human motion and biological characteristics for recognition research, has now become an important field in intelligent scene video surveillance. Especially for gait recognition, it is necessary to collect the characteristics of the moving human b...

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): G06T7/20G06K9/62
Inventor 王科俊吕卓纹阎涛李宏宇唐墨
Owner HARBIN ENG UNIV
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