Efficient image gradient-based object localisation and recognition
- 1 January 1996
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 397-402
- https://doi.org/10.1109/cvpr.1996.517103
Abstract
This paper reports novel algorithms for the efficient localisation and recognition of vehicles in traffic scenes, which eliminate the need for explicit symbolic feature extraction and matching. The algorithms make use of two a priori sources of knowledge about the scene and the objects: (i) the ground-plane constraint, and (ii) the fact that road vehicles are strongly rectilineal: The algorithms are demonstrated and tested using routine outdoor traffic images. Success with a variety of vehicles demonstrates the efficiency and robustness of context-based computer vision in road traffic scenes. The limitations of the algorithms are also addressed in the paper.Keywords
This publication has 10 references indexed in Scilit:
- Three-dimensional object recognition from single two-dimensional imagesPublished by Elsevier ,2003
- Fast algorithms for object orientation determinationPublished by SPIE-Intl Soc Optical Eng ,1995
- 3D pose estimation by fitting image gradients directly to polyhedral modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1995
- Recognizing objects on the ground-planeImage and Vision Computing, 1994
- Fast Vehicle Localisation and Recognition Without Line Extraction and MatchingPublished by British Machine Vision Association and Society for Pattern Recognition ,1994
- Model-based object tracking in monocular image sequences of road traffic scenesInternational Journal of Computer Vision, 1993
- On Computing The Perspective Transformation Matrix and Camera ParametersPublished by British Machine Vision Association and Society for Pattern Recognition ,1993
- Advances in Model-Based Traffic VisionPublished by British Machine Vision Association and Society for Pattern Recognition ,1993
- Linear Algorithms for Object Pose EstimationPublished by Springer Nature ,1992
- Generalizing the Hough transform to detect arbitrary shapesPattern Recognition, 1981