Multi-Feature Walking Pedestrian Detection Using Dense Stereo and Motion

This paper deals with a pedestrian pre-crash sensor based on dense stereovision and motion analysis. We aim to provide means to deploy safety measures before a crash occurs. Depending on the concrete selected actuator, it could be interesting to know the type of object (e. g. vehicle, pedestrian, bicyclist, etc.) involved in the collision. Some actuators need the information about the collision partner type, because they have to be triggered only in specific situations, or in a situation dependent manner. We present a pedestrian detection system based on dense stereo and motion, acting as pre–crash sensor. In order to detect pedestrians, we use simple features such as object size, speed, and also more complex, motion based features. All these features are combined into a flexible, Bayesian framework.

[1]  Bernt Schiele,et al.  Pedestrian detection in crowded scenes , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[2]  D.M. Gavrila,et al.  Vision-based pedestrian detection: the PROTECTOR system , 2004, IEEE Intelligent Vehicles Symposium, 2004.

[3]  M. Mahlisch,et al.  A multiple detector approach to low-resolution FIR pedestrian recognition , 2005, IEEE Proceedings. Intelligent Vehicles Symposium, 2005..

[4]  Marc-Michael Meinecke,et al.  Side-Pre-Crash Sensing System for Automatic Vehicle Height Level Adaptation , 2006 .

[5]  A. Shashua,et al.  Pedestrian detection for driving assistance systems: single-frame classification and system level performance , 2004, IEEE Intelligent Vehicles Symposium, 2004.

[6]  P. Welch.  The use of fast Fourier transform for the estimation of power spectra: A method based on time averaging over short, modified periodograms , 1967 .

[7]  Martial Hebert,et al.  Parts-based 3D object classification , 2004, CVPR 2004.

[8]  Bernard Chazelle,et al.  Matching 3D models with shape distributions , 2001, Proceedings International Conference on Shape Modeling and Applications.

[9]  Alan F. Smeaton,et al.  Pedestrian Detection Using Stereo and Biometric Information , 2006, ICIAR.

[10]  Dariu Gavrila,et al.  Pedestrian Detection from a Moving Vehicle , 2000, ECCV.

[11]  S. Nedevschi,et al.  Real-Time 3D Environment Reconstruction Using High Precision Trinocular Stereovision , 2006, 2006 IEEE International Conference on Automation, Quality and Testing, Robotics.

[12]  Hermann Rohling,et al.  Signal Processing Strategies for a Multi Sensor Pre-Crash Application , 2006 .

[13]  J.-Y. Bouguet,et al.  Pyramidal implementation of the lucas kanade feature tracker , 1999 .

[14]  Paul A. Viola,et al.  Detecting Pedestrians Using Patterns of Motion and Appearance , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[15]  László Havasi,et al.  Pedestrian Detection using derived Third-Order Symmetry of Legs , 2004 .

[16]  Massimo Bertozzi,et al.  Stereo Vision-based approaches for Pedestrian Detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops.

[17]  Dariu Gavrila,et al.  The Visual Analysis of Human Movement: A Survey , 1999, Comput. Vis. Image Underst..

[18]  John Iselin Woodfill,et al.  Tyzx DeepSea High Speed Stereo Vision System , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.