Efficient scan-window based object detection using GPGPU
Authors:
- 1 June 2008
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21607508,p. 1-7
Abstract
We describe an efficient design for scan-window based object detectors using a general purpose graphics hardware computing (GPGPU) framework. While the design is particularly applied to built a pedestrian detector that uses histogram of oriented gradient (HOG) features and the support vector machine (SVM) classifiers, the methodology we use is generic and can be applied to other objects, using different features and classifiers. The GPGPU paradigm is utilized for feature extraction and classification, so that the scan windows can be processed in parallel. We further propose to precompute and cache all the histograms in advance, instead of using integral images, which greatly lowers the computation cost. A multi-scale reduce strategy is employed to save expensive CPU-GPU data transfers. Experimental results show that our implementation achieves a more-than-ten-times speed up with no loss on detection rates.Keywords
This publication has 6 references indexed in Scilit:
- MinGPU: a minimum GPU library for computer visionJournal of Real-Time Image Processing, 2008
- Human Detection via Classification on Riemannian Manifolds2007
- Detecting Pedestrians by Learning Shapelet Features2007
- Detection and Tracking of Multiple, Partially Occluded Humans by Bayesian Combination of Edgelet based Part DetectorsInternational Journal of Computer Vision, 2007
- Fast Human Detection Using a Cascade of Histograms of Oriented Gradients2006
- OpenVIDIA2005