A coarse-to-fine approach for fast deformable object detection
- 1 June 2011
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1353-1360
- https://doi.org/10.1109/cvpr.2011.5995668
Abstract
We present a method that can dramatically accelerate object detection with part based models. The method is based on the observation that the cost of detection is likely to be dominated by the cost of matching each part to the image, and not by the cost of computing the optimal configuration of the parts as commonly assumed. Therefore accelerating detection requires minimizing the number of part-to-image comparisons. To this end we propose a multiple-resolutions hierarchical part based model and a corresponding coarse-to-fine inference procedure that recursively eliminates from the search space unpromising part placements. The method yields a ten-fold speedup over the standard dynamic programming approach and is complementary to the cascade-of-parts approach of. Compared to the latter, our method does not have parameters to be determined empirically, which simplifies its use during the training of the model. Most importantly, the two techniques can be combined to obtain a very significant speedup, of two orders of magnitude in some cases. We evaluate our method extensively on the PASCAL VOC and INRIA datasets, demonstrating a very high increase in the detection speed with little degradation of the accuracy.Keywords
This publication has 19 references indexed in Scilit:
- Multiple kernels for object detectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Human detection using partial least squares analysisPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- A discriminatively trained, multiscale, deformable part modelPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Classification using intersection kernel support vector machines is efficientPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Rapid object detection using a boosted cascade of simple featuresPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- WaldBoost — Learning for Time Constrained Sequential DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Pictorial Structures for Object RecognitionInternational Journal of Computer Vision, 2005
- Video Google: a text retrieval approach to object matching in videosPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Coarse-to-Fine Face DetectionInternational Journal of Computer Vision, 2001
- The Representation and Matching of Pictorial StructuresIEEE Transactions on Computers, 1973