Visual recognition of driver hand-held cell phone use based on hidden CRF

In this paper, we propose an automatic system that recognizes driver's abnormal behavior, i.e. cell phone use. Driver's actions are captured using a camera mounted above the dash board. Then the observed features are input into a Hidden Conditional Random Fields (HCRF) model. To incorporate long range dependencies, features are collected within a local window from neighbor sites. We evaluate the presented algorithm on the real video segments, and the results show that the system can successfully recognize the behavior.

[1]  Tomohiro Yamamura,et al.  A Driver Behavior Recognition Method Based on a Driver Model Framework , 2000 .

[2]  Euiyoung Cha,et al.  Face Detection in Color Image , 2003 .

[3]  Nanning Zheng,et al.  Interactive Road Situation Analysis for Driver Assistance and Safety Warning Systems: Framework and Algorithms , 2007, IEEE Transactions on Intelligent Transportation Systems.

[4]  Trevor Darrell,et al.  Conditional Random Fields for Object Recognition , 2004, NIPS.

[5]  Trevor Darrell,et al.  Hidden Conditional Random Fields for Gesture Recognition , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[6]  R. Naguib,et al.  Hand motion segmentation against skin colour background in breast awareness applications , 2004, The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[7]  Alex Pentland,et al.  Graphical models for driver behavior recognition in a SmartCar , 2000, Proceedings of the IEEE Intelligent Vehicles Symposium 2000 (Cat. No.00TH8511).

[9]  Kenichi Takahashi,et al.  Method of detecting concentration on cellular phone call from facial expression change by image processing , 2005, 2005 IEEE International Conference on Systems, Man and Cybernetics.

[10]  Anil K. Jain,et al.  Face Detection in Color Images , 2002, IEEE Trans. Pattern Anal. Mach. Intell..