Occupant posture analysis with stereo and thermal infrared video: algorithms and experimental evaluation

Dynamic analysis of vehicle occupant posture is a key requirement in designing "smart airbag" systems. Vision-based technology could enable the use of precise information about the occupant's size, posture, and, in particular, position in making airbag-deployment decisions. Novel sensory systems and algorithms need to be developed for capture, analysis, and classification of dynamic video-based information for a new generation of safe airbags. This paper presents a systematic investigation in which stereo and thermal long-wavelength infrared video-based real-time vision systems are developed and systematically evaluated. It also includes the design of several test beds, including instrumented vehicles for systematic experimental studies for the evaluation of independent and comparative evaluation in automobiles. Results of extensive experimental trials suggest basic feasibility of stereo and thermal long-wavelength infrared video-based occupant position and posture-analysis system.

[1]  M. Devy,et al.  Detection and classification of passenger seat occupancy using stereovision , 2000, Proceedings of the IEEE Intelligent Vehicles Symposium 2000 (Cat. No.00TH8511).

[2]  Alexandros Eleftheriadis,et al.  Automatic face location detection for model-assisted rate control in H.261-compatible coding of video , 1995, Signal Process. Image Commun..

[3]  P. Watta,et al.  Optical flow preprocessing for pose classification and transition recognition using class-specific principle component analysis , 2003, IEEE IV2003 Intelligent Vehicles Symposium. Proceedings (Cat. No.03TH8683).

[4]  Aldo Laurentini,et al.  How Many 2D Silhouettes Does It Take to Reconstruct a 3D Object? , 1997, Comput. Vis. Image Underst..

[5]  Tim Ellis,et al.  Real-time occupant classification in high dynamic range environments , 2002, Intelligent Vehicle Symposium, 2002. IEEE.

[6]  John Krumm,et al.  Video occupant detection for airbag deployment , 1998, Proceedings Fourth IEEE Workshop on Applications of Computer Vision. WACV'98 (Cat. No.98EX201).

[7]  Mohan Trivedi,et al.  Vehicle Occupant Posture Analysis Using Voxel Data , 2002 .

[8]  Mohan M. Trivedi,et al.  Real-time stereo-based vehicle occupant posture determination for intelligent airbag deployment , 2003, IEEE IV2003 Intelligent Vehicles Symposium. Proceedings (Cat. No.03TH8683).

[9]  Bir Bhanu,et al.  Computer Vision Beyond the Visible Spectrum , 2004 .

[10]  Swarup Medasani,et al.  Vision-based fusion system for smart airbag applications , 2002, Intelligent Vehicle Symposium, 2002. IEEE.

[11]  Mohan M. Trivedi,et al.  Articulated body posture estimation from multi-camera voxel data , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[12]  F. Lerasle,et al.  Car cockpit 3D reconstruction by a structured light sensor , 2000, Proceedings of the IEEE Intelligent Vehicles Symposium 2000 (Cat. No.00TH8511).

[13]  S.Y. Cheng,et al.  Human posture estimation using voxel data for "smart" airbag systems: issues and framework , 2004, IEEE Intelligent Vehicles Symposium, 2004.

[14]  Anil K. Jain,et al.  Occupant classification system for automotive airbag suppression , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[15]  A. Giralt,et al.  Head detection inside vehicles with a modified SVM for safer airbags , 2001, ITSC 2001. 2001 IEEE Intelligent Transportation Systems. Proceedings (Cat. No.01TH8585).

[16]  H. Nanda,et al.  Illumination invariant head pose estimation using single camera , 2003, IEEE IV2003 Intelligent Vehicles Symposium. Proceedings (Cat. No.03TH8683).

[17]  Erik Hjelmås,et al.  Face Detection: A Survey , 2001, Comput. Vis. Image Underst..

[18]  Mohan M. Trivedi,et al.  Human Body Model Acquisition and Tracking Using Voxel Data , 2003, International Journal of Computer Vision.

[19]  Lawrence B. Wolff,et al.  Tracking human faces in infrared video , 2003, Image Vis. Comput..

[20]  Tarak Gandhi,et al.  Driver's view and vehicle surround estimation using omnidirectional video stream , 2003, IEEE IV2003 Intelligent Vehicles Symposium. Proceedings (Cat. No.03TH8683).

[21]  Alex Pentland,et al.  A sensing chair using pressure distribution sensors , 2001 .

[22]  Frédéric Lerasle,et al.  Relaxation vs. maximal cliques search for projected beam labeling in a structured light sensor , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[23]  S.J. Krotosky,et al.  Occupant posture analysis using reflectance and stereo image for "smart" airbag deployment , 2004, IEEE Intelligent Vehicles Symposium, 2004.

[24]  Lawrence B. Wolff,et al.  Illumination invariant face recognition using thermal infrared imagery , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[25]  Stephen J. Kiselewich,et al.  Triangulation based technique for efficient stereo computation in infrared images , 2003, IEEE IV2003 Intelligent Vehicles Symposium. Proceedings (Cat. No.03TH8683).

[26]  Takeo Kanade,et al.  A real time system for robust 3D voxel reconstruction of human motions , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[27]  Petko Faber.  Seat occupation detection inside vehicles , 2000, 4th IEEE Southwest Symposium on Image Analysis and Interpretation.