DocumentCode :
3309409
Title :
Improving driver pose estimation
Author :
Watta, Paul ; Hou, Yulin ; Lakshmanan, Sridhar ; Natarajan, Narasimhamurthi
Author_Institution :
Dept. of Electr. & Comput. Eng., Michigan Univ., Dearborn, MI, USA
Volume :
2
fYear :
2002
fDate :
17-21 June 2002
Firstpage :
310
Abstract :
In this paper, we consider the problem of estimating the pose of a driver from video data. We propose extensions to our previous eigenface and Fisherface-based methods to improve classification performance. In particular, a hybrid neural network/nearest neighbor algorithm is formulated for classification of frames. Experimental results show that the hybrid neural network outperforms the nearest neighbor classifier.
Keywords :
automated highways; driver information systems; gesture recognition; image sequences; driver behavior; driver pose; hybrid neural network; intelligent transportation systems; nearest neighbor classifier; pose estimation; vehicle safety; video sequence; Driver circuits; Image databases; Intelligent transportation systems; Mirrors; Nearest neighbor searches; Neural networks; System testing; Vehicle driving; Vehicle safety; Video sequences;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Vehicle Symposium, 2002. IEEE
Print_ISBN :
0-7803-7346-4
Type :
conf
DOI :
10.1109/IVS.2002.1187970
Filename :
1187970
Link To Document :
بازگشت