DocumentCode :
599113
Title :
Tracking across nonoverlapping cameras based on the unsupervised learning of camera link models
Author :
Chun-Te Chu ; Jenq-Neng Hwang ; Jen-Yu Yu ; Kual-Zheng Lee
Author_Institution :
Dept. of Electr. Eng., Univ. of Washington, Seattle, WA, USA
fYear :
2012
fDate :
Oct. 30 2012-Nov. 2 2012
Firstpage :
1
Lastpage :
6
Abstract :
A multiple-camera tracking system that tracks the human across cameras with nonoverlapping views is proposed. The system is divided into two phases. In the training stage, the camera link model, including transition time distribution, brightness transfer function, region mapping matrix, region matching weight, and feature fusion weight, is estimated by an unsupervised learning scheme which tolerates well the presence of outliers in the training data. In the testing stage, besides the temporal and holistic color features, region color and region texture features are considered. The systematically integration of multiple cues enables us to perform the effective re-identification. The camera link model keeps being updated during the tracking in order to adapt the change of the environment. The complete system has been tested in a real-world camera network scenarios.
Keywords :
cameras; computerised instrumentation; image colour analysis; image texture; unsupervised learning; brightness transfer function; camera link model; feature fusion weight; holistic color feature; multiple-camera tracking system; nonoverlapping camera tracking; real-world camera network scenario; region color feature; region mapping matrix; region matching weight; region texture feature; temporal color feature; training data outlier; transition time distribution; unsupervised learning scheme; Brightness; Cameras; Color; Estimation; Histograms; Humans; Image color analysis; camera link model; multiple-camera tracking; nonoverlapping view, unsupervised learning, camera networks;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Distributed Smart Cameras (ICDSC), 2012 Sixth International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4503-1772-6
Type :
conf
Filename :
6470146
Link To Document :
بازگشت