Multi target tracking with CPHD filter based on asynchronous sensors

Author

Lamard, Laetitia ; Chapuis, Roland ; Boyer, Jean Philippe

Author_Institution

Inst. Pascal, Clermont-Ferrand, France

fYear

2013

fDate

9-12 July 2013

Firstpage

892

Lastpage

898

Abstract

In this paper, the problem of targets road tracking based on multiple asynchronous sensors is addressed. A method based on Cardinalized Probability Hypothesis Density (CPHD) filter improved with probability of target type is presented. Using the sensor classification, the probability of target type is recursively computed by Bayesian rules. This probability is used to improve the performance of the Multi Target Tracking (MTT) filter and the understanding of the observed area. The tuning of filter parameter depending of sensor is explained and the particular case of non detection due to occlusion with camera is developed. Our system has been validated with real measurements from a smart camera and a radar in real traffic conditions with real time computation.

Keywords

Bayes methods; driver information systems; filtering theory; image classification; image sensors; radar imaging; radar tracking; road traffic; target tracking; ADAS; Bayesian rules; CPHD filter; MTT; advanced driver assistance system; cardinalized probability hypothesis density filter; filter parameter tuning; multiple asynchronous sensors; multitarget tracking filter; radar; real traffic conditions; sensor classification; smart camera; target road tracking problem; target type probability; Cameras; Equations; Radar; Sensor fusion; Target tracking; Vehicles;

fLanguage

English

Publisher

ieee

Conference_Titel

Information Fusion (FUSION), 2013 16th International Conference on

Conference_Location

Istanbul

Print_ISBN

978-605-86311-1-3

Type

conf

Filename

6641088