A novel object tracking algorithm based on compressed sensing and entropy of information

Ding Ma, Jinkun Yu, Zhezhou Yu, Wei Pang

Research output: Contribution to journalArticle

1 Citation (Scopus)
4 Downloads (Pure)

Abstract

Object tracking has always been a hot research topic in the field of computer vision; its purpose is to track objects with specific characteristics or representation and estimate the information of objects such as their locations, sizes, and rotation angles in the current frame. Object tracking in complex scenes will usually encounter various sorts of challenges, such as location change, dimension change, illumination change, perception change, and occlusion. This paper proposed a novel object tracking algorithm based on compressed sensing and information entropy to address these challenges. First, objects are characterized by the Haar (Haar-like) and ORB features. Second, the dimensions of computation space of the Haar and ORB features are effectively reduced through compressed sensing. Then the above-mentioned features are fused based on information entropy. Finally, in the particle filter framework, an object location was obtained by selecting candidate object locations in the current frame from the local context neighboring the optimal locations in the last frame. Our extensive experimental results demonstrated that this method was able to effectively address the challenges of perception change, illumination change, and large area occlusion, which made it achieve better performance than existing approaches such as MIL and CT.
Original languageEnglish
Article number 628101
Number of pages18
JournalMathematical Problems in Engineering
Volume2015
Early online date2 Jun 2015
DOIs
Publication statusPublished - 2015

Fingerprint

Compressed sensing
Compressed Sensing
Object Tracking
Entropy
Information Entropy
Occlusion
Illumination
Lighting
Optimal Location
Particle Filter
Computer Vision
Sort
Computer vision
Object
Angle
Experimental Results
Estimate

Cite this

A novel object tracking algorithm based on compressed sensing and entropy of information. / Ma, Ding; Yu, Jinkun; Yu, Zhezhou; Pang, Wei.

In: Mathematical Problems in Engineering, Vol. 2015, 628101, 2015.

Research output: Contribution to journalArticle

@article{d720cc512c68498982407c00770eac53,
title = "A novel object tracking algorithm based on compressed sensing and entropy of information",
abstract = "Object tracking has always been a hot research topic in the field of computer vision; its purpose is to track objects with specific characteristics or representation and estimate the information of objects such as their locations, sizes, and rotation angles in the current frame. Object tracking in complex scenes will usually encounter various sorts of challenges, such as location change, dimension change, illumination change, perception change, and occlusion. This paper proposed a novel object tracking algorithm based on compressed sensing and information entropy to address these challenges. First, objects are characterized by the Haar (Haar-like) and ORB features. Second, the dimensions of computation space of the Haar and ORB features are effectively reduced through compressed sensing. Then the above-mentioned features are fused based on information entropy. Finally, in the particle filter framework, an object location was obtained by selecting candidate object locations in the current frame from the local context neighboring the optimal locations in the last frame. Our extensive experimental results demonstrated that this method was able to effectively address the challenges of perception change, illumination change, and large area occlusion, which made it achieve better performance than existing approaches such as MIL and CT.",
author = "Ding Ma and Jinkun Yu and Zhezhou Yu and Wei Pang",
note = "Acknowledgments This research is supported by (1) the Ph.D. Programs Foundation of Ministry of Education of China under Grant no. 20120061110045, (2) the Science and Technology Development Projects of Jilin Province of China under Grant no. 20150204007G X, and (3) the Key Laboratory for Symbol Computation and Knowledge Engineering of the National Education Ministry of China.",
year = "2015",
doi = "10.1155/2015/628101",
language = "English",
volume = "2015",
journal = "Mathematical Problems in Engineering",
issn = "1024-123X",
publisher = "Hindawi Publishing Corporation",

}

TY - JOUR

T1 - A novel object tracking algorithm based on compressed sensing and entropy of information

AU - Ma, Ding

AU - Yu, Jinkun

AU - Yu, Zhezhou

AU - Pang, Wei

N1 - Acknowledgments This research is supported by (1) the Ph.D. Programs Foundation of Ministry of Education of China under Grant no. 20120061110045, (2) the Science and Technology Development Projects of Jilin Province of China under Grant no. 20150204007G X, and (3) the Key Laboratory for Symbol Computation and Knowledge Engineering of the National Education Ministry of China.

PY - 2015

Y1 - 2015

N2 - Object tracking has always been a hot research topic in the field of computer vision; its purpose is to track objects with specific characteristics or representation and estimate the information of objects such as their locations, sizes, and rotation angles in the current frame. Object tracking in complex scenes will usually encounter various sorts of challenges, such as location change, dimension change, illumination change, perception change, and occlusion. This paper proposed a novel object tracking algorithm based on compressed sensing and information entropy to address these challenges. First, objects are characterized by the Haar (Haar-like) and ORB features. Second, the dimensions of computation space of the Haar and ORB features are effectively reduced through compressed sensing. Then the above-mentioned features are fused based on information entropy. Finally, in the particle filter framework, an object location was obtained by selecting candidate object locations in the current frame from the local context neighboring the optimal locations in the last frame. Our extensive experimental results demonstrated that this method was able to effectively address the challenges of perception change, illumination change, and large area occlusion, which made it achieve better performance than existing approaches such as MIL and CT.

AB - Object tracking has always been a hot research topic in the field of computer vision; its purpose is to track objects with specific characteristics or representation and estimate the information of objects such as their locations, sizes, and rotation angles in the current frame. Object tracking in complex scenes will usually encounter various sorts of challenges, such as location change, dimension change, illumination change, perception change, and occlusion. This paper proposed a novel object tracking algorithm based on compressed sensing and information entropy to address these challenges. First, objects are characterized by the Haar (Haar-like) and ORB features. Second, the dimensions of computation space of the Haar and ORB features are effectively reduced through compressed sensing. Then the above-mentioned features are fused based on information entropy. Finally, in the particle filter framework, an object location was obtained by selecting candidate object locations in the current frame from the local context neighboring the optimal locations in the last frame. Our extensive experimental results demonstrated that this method was able to effectively address the challenges of perception change, illumination change, and large area occlusion, which made it achieve better performance than existing approaches such as MIL and CT.

U2 - 10.1155/2015/628101

DO - 10.1155/2015/628101

M3 - Article

VL - 2015

JO - Mathematical Problems in Engineering

JF - Mathematical Problems in Engineering

SN - 1024-123X

M1 - 628101

ER -