DocumentCode :
3033554
Title :
Fast implementation of a robust pedestrian recognition system
Author :
Schlosshauer, J. ; Giesecke, N. ; Fardi, B. ; Wanielik, Gerd
Author_Institution :
FusionSystems GmbH, Chemnitz
fYear :
2008
fDate :
22-24 Sept. 2008
Firstpage :
69
Lastpage :
74
Abstract :
In this contribution a real time capable pedestrian recognition system is presented. The AdaBoost based cascade approach is applied and enhanced. A special implementation of the feature extraction algorithms yields to a remarkable increasing of the computation efficiency. Furthermore the AdaBoost classifier uses decision trees as basic classifiers (weak learner). Therefore, the computational costs are reduced in addition without penalizing the classification performance. The details of the implementation, the computational costs as well as the classification results of real scenarios are presented. The presented work is part of the WATCH-OVER project.
Keywords :
decision trees; feature extraction; image classification; image enhancement; image recognition; AdaBoost based cascade approach; AdaBoost classifier; WATCH-OVER project; computation efficiency; decision trees; feature extraction algorithms; robust pedestrian recognition system; Cameras; Classification tree analysis; Computational efficiency; Feature extraction; Filters; Object detection; Road accidents; Robustness; Shape; Support vector machines; pedestrian recognition; vulnerable road user protection;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Vehicular Electronics and Safety, 2008. ICVES 2008. IEEE International Conference on
Conference_Location :
Columbus, OH
Print_ISBN :
978-1-4244-2359-0
Electronic_ISBN :
978-1-4244-2360-6
Type :
conf
DOI :
10.1109/ICVES.2008.4640873
Filename :
4640873
Link To Document :
بازگشت