On detection of multiple object instances using hough transforms
- 1 June 2010
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2233-2240
- https://doi.org/10.1109/cvpr.2010.5539905
Abstract
To detect multiple objects of interest, the methods based on Hough transform use non-maxima supression or mode seeking in order to locate and to distinguish peaks in Hough images. Such postprocessing requires tuning of extra parameters and is often fragile, especially when objects of interest tend to be closely located. In the paper, we develop a new probabilistic framework that is in many ways related to Hough transform, sharing its simplicity and wide applicability. At the same time, the framework bypasses the problem of multiple peaks identification in Hough images, and permits detection of multiple objects without invoking nonmaximum suppression heuristics. As a result, the experiments demonstrate a significant improvement in detection accuracy both for the classical task of straight line detection and for a more modern category-level (pedestrian) detection problem.Keywords
This publication has 13 references indexed in Scilit:
- On detection of multiple object instances using hough transformsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Poselets: Body part detectors trained using 3D human pose annotationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Discriminative models for multi-class object layoutPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- FLoSS: Facility location for subspace segmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- People-tracking-by-detection and people-detection-by-trackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Robust Object Detection with Interleaved Categorization and SegmentationInternational Journal of Computer Vision, 2007
- 3D LayoutCRF for Multi-View Object Class Recognition and SegmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Clustering by Passing Messages Between Data PointsScience, 2007
- Generalizing the Hough transform to detect arbitrary shapesPattern Recognition, 1981
- Best Algorithms for Approximating the Maximum of a Submodular Set FunctionMathematics of Operations Research, 1978