Towards a Vision-based System Exploring 3D Driver Posture Dynamics for Driver Assistance: Issues and Possibilities

被引:24
作者
Cuong Tran [1 ]
Trivedi, Mohan M. [1 ]
机构
[1] Univ Calif San Diego, LISA Lab Safe & Intelligent Automobiles, La Jolla, CA 92093 USA
来源
2010 IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV) | 2010年
关键词
D O I
10.1109/IVS.2010.5547957
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Driver's body posture in 3D contains information potentially related to driver intent, driver affective state, and driver distraction. In this paper, we discuss issues and possibilities in developing a vision-based, markerless system to systematically explore the role of 3D driver posture dynamics for driver assistance. At high level, two main emphases in the proposed system are: (i) The coordination between real world driving testbed and simulation environment and (ii) The usefulness of driver posture dynamics is studied not only as an individual cue but also in relation with other contextual information (e. g. head dynamics, facial features, and vehicle dynamics). Some initial results in our experiment following these guidelines show the feasibility and promise of extracting and using 3D driver posture dynamics for driver assistance.
引用
收藏
页码:179 / 184
页数:6
相关论文
共 23 条
[1]  
[Anonymous], 2007, 2 INT C AFF COMP INT
[2]  
Baker S., 2004, 0410 CARN MELL U ROB
[3]  
Brodeur R., 1996, ERLTR95009
[4]  
Cheng S., 2010, IEEE Trans. Intelligent Transportation Systems
[5]  
Cheng SY, 2006, IEEE PERVAS COMPUT, V5, P28, DOI 10.1109/MPRV.2006.88
[6]  
Datta A., 2008, IEEE C COMP VIS PATT
[7]  
Doshi A., 2009, IEEE TRANSACTIONS ON
[8]  
Doshi A., 2009, IEEE T SYSTEMS MAN B
[9]   Progressive search space reduction for human pose estimation [J].
Ferrari, Vittorio ;
Marin-Jimenez, Manuel ;
Zisserman, Andrew .
2008 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-12, 2008,
[10]  
McCall J., 2007, IEEE TRANSACTIONS ON