Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Multi-scale superpixel-fused target tracking method

A target tracking and superpixel technology, applied in image analysis, image data processing, instruments, etc., can solve the problems of ignoring edge information and size information, low consistency, etc.

Inactive Publication Date: 2014-06-25
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF2 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the algorithm has good robustness in the case of occlusion and drift of the target, since the algorithm is based on the discrimination results of superpixel blocks, the accuracy of target tracking directly depends on the selection of superpixel block scale, especially The feature vectors obtained by superpixel segmentation at different scales are different. The features of small-scale superpixel blocks are highly consistent in color and texture information, but most of the edge information and size information are ignored. Large-scale superpixel blocks The features of have low consistency in color and texture information, but they can preserve edge information and size information

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
  • Multi-scale superpixel-fused target tracking method
  • Multi-scale superpixel-fused target tracking method
  • Multi-scale superpixel-fused target tracking method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0049] figure 1 It is a flow chart of the target tracking method for fusing multi-scale superpixels of the present invention.

[0050] In this example, if figure 1 As shown, the target tracking method for fusing multi-scale superpixels of the present invention includes the following steps:

[0051] 1) Construct a discriminative appearance model based on superpixels:

[0052] 1.1), obtain superpixel blocks; in a given target tracking sample sequence I 1 , I 2 , I 3 ,…I M Among them, M is the frame number of the sample sequence, for the first frame image I 1 , with (x 1 ,y 1 ) as the center, extract a rectangular area S containing the target with a height of h and a width of w 1 , where h and w are related to the target size h 1 、w 1 The proportional relationship is: h=1.5*h 1 ,w=1.5*w 1 , through the SLIC algorithm for the area S 1 Perform superpixel segmentation of d scales, where d is the total number of layers of the scale, and each layer has N j superpixel bl...

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 multi-scale superpixel-fused target tracking method. Through the method, a more accurate target confidence map can be obtained by constructing a superpixel-based discriminant appearance model, and consequently the target tracking accuracy degree and robustness are effectively improved. Specifically, the method includes the first step of adopting superpixel classification results with different scales to vote for properties of one pixel point and then obtaining the more accurate target confidence map, and the second step of updating the appearance model by continuously updating a classifier so that the appearance model can continuously adapt to scenes such as illumination changes and complicated backgrounds. Consequently, more accurate and robust tracking can be achieved.

Description

technical field [0001] The invention belongs to the technical field of computer vision recognition, and more specifically relates to a target tracking method for fusing multi-scale superpixels. Background technique [0002] In recent years, target tracking algorithms have attracted more and more researchers' attention, mainly because video tracking technology has a very broad market application prospect. As an interdisciplinary cutting-edge technology, moving target tracking combines image processing, model Theoretical knowledge in many different fields such as recognition, artificial intelligence, and automatic control has broad application prospects in many fields such as video surveillance, intelligent transportation, video compression, visual navigation, and human-computer interaction. [0003] In recent years, there are generally two ideas on the problem of moving target tracking. One is descriptive tracking algorithm. In order to better describe the target, the 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): G06T7/20
Inventor 周雪邹见效徐红兵李文茹
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products