Fast LBP Face Detection on low-power SIMD architectures
University of Ottawa, Ottawa, ON, Canada
The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 616-622, 2014
@inproceedings{bilaniuk2014fast,
title={Fast LBP Face Detection on Low-Power SIMD Architectures},
author={Bilaniuk, Olexa and Fazl-Ersi, Ehsan and Laganiere, Robert and Xu, Christina and Laroche, Daniel and Moulder, Craig},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops},
pages={616–622},
year={2014}
}
This paper presents an embedded implementation of a face detection method based on boosted LBP features for Single Instruction Multiple Data (SIMD) architectures. The implementation exploits parallelism and data reuse in the detection algorithm and is integrated into CogniVue’s Gen-1 APEX platform, which uses a SIMD design and is extremely energy efficient. The proposed embedded face detection system runs at 5 VGA frames per second, while providing similar accuracy to the PC version of the LBP face detection algorithm included in the OpenCV library.
June 26, 2014 by hgpu
