Fast Object Hypotheses Generation Using 3D Position and 3D Motion
- 5 January 2006
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 56
- https://doi.org/10.1109/cvpr.2005.459
Abstract
This contribution proposes a method to generate object hypotheses from stereo obstacle detection and image motion. Our algorithm is a general approach since it does not require any a priori information about the shape of the observed objects but relies on the basic assumption that the objects are rigid. The algorithm has two processing stages: First, obstacles are detected using stereo vision. Second, each obstacle is segmented into clusters of consistent motion in 3D space. The clustering process explicitly accounts for measurement uncertainties of stereo disparity and 2d motion. Our system may serve as a general feature for higher-level object detection and classification.Keywords
This publication has 10 references indexed in Scilit:
- Vehicle detection fusing 2D visual featuresPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Dynamic ego-pose estimation for driver assistance in urban environmentsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Real-time detection of moving objects in a dynamic scene from moving robotic vehiclesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Fusing optical flow and stereo disparity for object trackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Qualitative detection of 3D motion discontinuitiesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Real-time stereo vision for urban traffic scene understandingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Fast obstacle detection for urban traffic situationsIEEE Transactions on Intelligent Transportation Systems, 2002
- Die Radontransformation in der digitalen Bildverarbeitung (The Radon Transform in Digital Image Processing)at – Automatisierungstechnik, 2002
- Real-Time Correlation-Based Stereo Vision with Reduced Border ErrorsInternational Journal of Computer Vision, 2002
- The interpretation of a moving retinal imageProceedings of the Royal Society of London. B. Biological Sciences, 1980