Designed system and algorithms for detecting pedestrians at a high detection rate and low false-positive rate by combining contextual cues from buildings, vehicles and other non-pedestrian classes as part of this project from the Federal Highway Administration (FHWA) Exploratory Advanced Research (EAR) Program (FHWA-HRT-11-056). The research results are included in the FHWA EAR summary.
Layered Object Recognition System for Pedestrian Collision Sensing
Publications
J. Eledath, B. Matei, M. Bansal, S. Jung, H. Sawhney.
Layered Object Recognition System for Pedestrian Sensing.
U.S. Department of Transportation, Federal Highway Administration (FHWA-HRT-11-056),
2012.
M. Bansal, S. Jung, B. Matei, J. Eledath, H. Sawhney.
A Real-time Pedestrian Detection System based on Structure and Appearance Classification.
IEEE International Conference on Robotics and Automation (ICRA),
2010.
M. Bansal, S. Jung, B. Matei, J. Eledath, H. Sawhney.
Combining Structure and Appearance Cues for Real-time Pedestrian Detection.
Unmanned Systems Technology XII, Proc. SPIE,
2010.
M. Bansal, B. Matei, H. Sawhney, S. Jung, J. Eledath.
Pedestrian Detection with Depth-guided Structure Labeling.
IEEE Workshop on Search in 3D and Video (ICCV Workshop),
2009.