RT Conference Proceedings
T1 Visual feature tracking based on PHD filter for vehicle detection
A1 García, Fernando
A1 Prioletti, Antonio
A1 Cerri, Pietro
A1 Broggi, Alberto
A1 Escalera Hueso, Arturo de la
A1 Armingol Moreno, José María
AB Vehicle detection is one of the classical applicationamong the Advance Driver Assistance Systems (ADAS).Applications like emergency braking or adaptive cruise control(ACC) require accurate and reliable vehicle detection. In latestyears the improvements in vision detection have lead to theintroduction of computer vision to detect vehicles by means ofthese more economical sensors, with high reliability.In the present paper, a novel algorithm for vehicle detectionand tracking based on a probability hypothesis density (PHD)filter is presented. The first detection is based on a fast machinelearning algorithm (Adaboost) and Haar-Like features. Later,the tracking is performed, by means features detected within thebounding box provided by the vehicle detection. The features, aretracked by a PHD filter. The results of the features being trackedare combined together in the last step, based on several differentmethods. Test provided show the performance of the PHD filterin public sequences using the different methods proposed.
PB IEEE
SN 978-8-4901-2355-3
YR 2014
FD 2014-10-07
LK https://hdl.handle.net/10016/23670
UL https://hdl.handle.net/10016/23670
LA eng
NO This work was supported by the Spanish Governmentthrough the Cicyt projects (GRANT TRA2010-20225-C03-01)and (GRANT TRA 2011-29454-C03-02).
DS e-Archivo
RD 18 jul. 2024