Efficient Stixel-based object recognition
- 1 June 2012
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 12 (19310587), 1066-1071
- https://doi.org/10.1109/ivs.2012.6232137
Abstract
This paper presents a novel attention mechanism to improve stereo-vision based object recognition systems in terms of recognition performance and computational efficiency at the same time. We utilize the Stixel World, a compact medium-level 3D representation of the local environment, as an early focus-of-attention stage for subsequent system modules. In particular, the search space of computationally expensive pattern classifiers is significantly narrowed down. We explicitly couple the 3D Stixel representation with prior knowledge about the object class of interest, i.e. 3D geometry and symmetry, to precisely focus processing on well-defined local regions that are consistent with the environment model. Experiments are conducted on large real-world datasets captured from a moving vehicle in urban traffic. In case of vehicle recognition as an experimental testbed, we demonstrate that the proposed Stixel-based attention mechanism significantly reduces false positive rates at constant sensitivity levels by up to a factor of 8 over state-of-the-art. At the same time, computational costs are reduced by more than an order of magnitude.Keywords
This publication has 29 references indexed in Scilit:
- 2D–3D-based on-board pedestrian detection systemComputer Vision and Image Understanding, 2010
- Survey of Pedestrian Detection for Advanced Driver Assistance SystemsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- Coupled Object Detection and Tracking from Static Cameras and Moving VehiclesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
- Multi-cue Pedestrian Detection and Tracking from a Moving VehicleInternational Journal of Computer Vision, 2006
- Accurate and Efficient Stereo Processing by Semi-Global Matching and Mutual InformationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Real-time estimation and tracking of optical flow vectors for obstacle detectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Robust vehicle detection at large distance using low resolution camerasPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Statistical pattern recognition: a reviewIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000
- Intensity and Edge-Based Symmetry Detection with an Application to Car-FollowingComputer Vision and Image Understanding, 1993
- Symmetry-based recognition of vehicle rearsPattern Recognition Letters, 1991