Multiple pedestrians tracking with composite sensor of laser range finder and omni-directional camera by SMC implementation of PHD filter

Author

Ikoma, Norikazu

Author_Institution

Fac. of Eng., Kyushu Inst. of Technol., Fukuoka, Japan

fYear

2012

fDate

20-24 Nov. 2012

Firstpage

705

Lastpage

710

Abstract

Multiple pedestrians tracking with composite sensor of laser range finder and omni-directional camera having wide field of view has been proposed based on Sequential Monte Carlo (SMC) implementation of Probability Hypothesis Density (PHD) filter in Track Before Detect (TBD) approach. The composite sensor has been fixed on the flat ground with its laser measurement plane crossing body of target pedestrians. Tracking has been done for multiple pedestrians walk around the sensor with cluttered static scene. Real-time tracking system has been developed and experimental results demonstrate the performance of the proposed method.

Keywords

Monte Carlo methods; cameras; filtering theory; laser ranging; pedestrians; target tracking; PHD filter; SMC implementation; TBD approach; cluttered static scene; composite sensor; laser measurement plane crossing body; laser range finder; multiple pedestrians tracking; omnidirectional camera; probability hypothesis density filter; real-time system; sequential Monte Carlo implementation; track before detect approach;

fLanguage

English

Publisher

ieee

Conference_Titel

Soft Computing and Intelligent Systems (SCIS) and 13th International Symposium on Advanced Intelligent Systems (ISIS), 2012 Joint 6th International Conference on

Conference_Location

Kobe

Print_ISBN

978-1-4673-2742-8

Type

conf

DOI

10.1109/SCIS-ISIS.2012.6505030

Filename

6505030