A cloud model-based camshift target tracking

Chang Liu; Shaolei Lu; Shuai Liu; Yaping Dai; Kaoru Hirota

A cloud model-based camshift target tracking

Chang Liu, Shaolei Lu, Shuai Liu, Yaping Dai, Kaoru Hirota^*

^*Corresponding author for this work

School of Automation

Beijing Institute of Technology

Research output: Contribution to conference › Paper › peer-review

Abstract

A cloud model-based Camshift algorithm is proposed to track the moving target with an amount of background information. It overcomes the unstable tracking problem caused by the reasonable rigid division of histogram in the traditional Camshift algorithm. The cloud model of the target block is established to extract the target and background concepts and to construct the certainty graph. The interference of the background information to the target tracking is weakened by averaging the weight of the target conceptual area with kernel function. The experimental results which are done by Matlab validate that, compared to the traditional Camshift and saliency Camshift algorithm, the accuracy of the proposed algorithm is increased by 51 and 9% for the target tracking without occlusion, and also increased by 54 and 15% with occlusion, respectively.

Original language	English
Publication status	Published - 2017
Event	5th International Workshop on Advanced Computational Intelligence and Intelligent Informatics, IWACIII 2017 - Beijing, China Duration: 2 Nov 2017 → 5 Nov 2017

Conference

Conference	5th International Workshop on Advanced Computational Intelligence and Intelligent Informatics, IWACIII 2017
Country/Territory	China
City	Beijing
Period	2/11/17 → 5/11/17

Keywords

Camshift
Cloud model
Occlusion
Target tracking

Cite this

@conference{c83c49b5f169482c852a376aa4faed06,

title = "A cloud model-based camshift target tracking",

abstract = "A cloud model-based Camshift algorithm is proposed to track the moving target with an amount of background information. It overcomes the unstable tracking problem caused by the reasonable rigid division of histogram in the traditional Camshift algorithm. The cloud model of the target block is established to extract the target and background concepts and to construct the certainty graph. The interference of the background information to the target tracking is weakened by averaging the weight of the target conceptual area with kernel function. The experimental results which are done by Matlab validate that, compared to the traditional Camshift and saliency Camshift algorithm, the accuracy of the proposed algorithm is increased by 51 and 9\% for the target tracking without occlusion, and also increased by 54 and 15\% with occlusion, respectively.",

keywords = "Camshift, Cloud model, Occlusion, Target tracking",

author = "Chang Liu and Shaolei Lu and Shuai Liu and Yaping Dai and Kaoru Hirota",

year = "2017",

language = "English",

note = "5th International Workshop on Advanced Computational Intelligence and Intelligent Informatics, IWACIII 2017 ; Conference date: 02-11-2017 Through 05-11-2017",

}

TY - CONF

T1 - A cloud model-based camshift target tracking

AU - Liu, Chang

AU - Lu, Shaolei

AU - Liu, Shuai

AU - Dai, Yaping

AU - Hirota, Kaoru

PY - 2017

Y1 - 2017

N2 - A cloud model-based Camshift algorithm is proposed to track the moving target with an amount of background information. It overcomes the unstable tracking problem caused by the reasonable rigid division of histogram in the traditional Camshift algorithm. The cloud model of the target block is established to extract the target and background concepts and to construct the certainty graph. The interference of the background information to the target tracking is weakened by averaging the weight of the target conceptual area with kernel function. The experimental results which are done by Matlab validate that, compared to the traditional Camshift and saliency Camshift algorithm, the accuracy of the proposed algorithm is increased by 51 and 9% for the target tracking without occlusion, and also increased by 54 and 15% with occlusion, respectively.

AB - A cloud model-based Camshift algorithm is proposed to track the moving target with an amount of background information. It overcomes the unstable tracking problem caused by the reasonable rigid division of histogram in the traditional Camshift algorithm. The cloud model of the target block is established to extract the target and background concepts and to construct the certainty graph. The interference of the background information to the target tracking is weakened by averaging the weight of the target conceptual area with kernel function. The experimental results which are done by Matlab validate that, compared to the traditional Camshift and saliency Camshift algorithm, the accuracy of the proposed algorithm is increased by 51 and 9% for the target tracking without occlusion, and also increased by 54 and 15% with occlusion, respectively.

KW - Camshift

KW - Cloud model

KW - Occlusion

KW - Target tracking

UR - http://www.scopus.com/inward/record.url?scp=85037548312&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85037548312

T2 - 5th International Workshop on Advanced Computational Intelligence and Intelligent Informatics, IWACIII 2017

Y2 - 2 November 2017 through 5 November 2017

ER -

A cloud model-based camshift target tracking

Abstract

Conference

Keywords

Other files and links

Fingerprint

Cite this