An efficient divide-and-conquer cascade for nonlinear object detection

C. Lampert, in:, IEEE, 2010, pp. 1022–1029.

Download
No fulltext has been uploaded. References only!

Conference Paper | Published
Abstract
We introduce a method to accelerate the evaluation of object detection cascades with the help of a divide-and-conquer procedure in the space of candidate regions. Compared to the exhaustive procedure that thus far is the state-of-the-art for cascade evaluation, the proposed method requires fewer evaluations of the classifier functions, thereby speeding up the search. Furthermore, we show how the recently developed efficient subwindow search (ESS) procedure [11] can be integrated into the last stage of our method. This allows us to use our method to act not only as a faster procedure for cascade evaluation, but also as a tool to perform efficient branch-and-bound object detection with nonlinear quality functions, in particular kernelized support vector machines. Experiments on the PASCAL VOC 2006 dataset show an acceleration of more than 50% by our method compared to standard cascade evaluation.
Publishing Year
Date Published
2010-06-18
Acknowledgement
Conference Information URL: http://cvl.umiacs.umd.edu/conferences/cvpr2010/
Page
1022 - 1029
Conference
CVPR: Computer Vision and Pattern Recognition
IST-REx-ID

Cite this

Lampert C. An efficient divide-and-conquer cascade for nonlinear object detection. In: IEEE; 2010:1022-1029. doi:10.1109/CVPR.2010.5540107
Lampert, C. (2010). An efficient divide-and-conquer cascade for nonlinear object detection (pp. 1022–1029). Presented at the CVPR: Computer Vision and Pattern Recognition, IEEE. https://doi.org/10.1109/CVPR.2010.5540107
Lampert, Christoph. “An Efficient Divide-and-Conquer Cascade for Nonlinear Object Detection,” 1022–29. IEEE, 2010. https://doi.org/10.1109/CVPR.2010.5540107.
C. Lampert, “An efficient divide-and-conquer cascade for nonlinear object detection,” presented at the CVPR: Computer Vision and Pattern Recognition, 2010, pp. 1022–1029.
Lampert C. 2010. An efficient divide-and-conquer cascade for nonlinear object detection. CVPR: Computer Vision and Pattern Recognition 1022–1029.
Lampert, Christoph. An Efficient Divide-and-Conquer Cascade for Nonlinear Object Detection. IEEE, 2010, pp. 1022–29, doi:10.1109/CVPR.2010.5540107.

Export

Marked Publications

Open Data IST Research Explorer

Search this title in

Google Scholar