Search BYU 
Feedback   |   Help

     Human detection has always been an important part of computer vision but many implementations lack the real-time performance that real world applications require. This work developes a real-time implementation of human detection in video using the state-of-the-art histograms of oriented gradients method. Each image in the video sequence is tested at multiple scales using a sliding window. Histograms of oriented gradients are created for each window and passed to a support vector machine to classify it as human or not. The histograms of oriented gradients method is implemented on a GPU using the NVIDIA CUDA architecture. The implementation significantly speeds up computation, achieving approximately 38 frames a second on VGA video while testing 11,160 windows per frame. Accuracy remains comparable to the CPU implementation. The flexibility and computational power the GPU affords users is discussed. These discussions should benefit those researchers who are interested in using a GPU for high-performance computing tasks.

Graduate Students:

Kirt Lillywhite and Beau Tippetts

  1. K.D. Lillywhite, D.J. Lee, and B.J. Tippetts, “Improving Evolution-COnstructed Features Using Speciation,” IEEE Workshop on Applications of Computer Vision (WACV), 6 pages, Breckenridge, Colorado, USA, January 9-11, 2012.
  2. K.D. Lillywhite, D.J. Lee, and D. Zhang, “Real-time Human Detection Using Histograms of Oriented Gradients on a GPU,” IEEE Workshop on Applications of Computer Vision (WACV), 6 pages, Snowbird, Utah, USA, December 7-8, 2009.
(Click image to view.)


Maintained by the ECEn Web Team
Copyright 1994-2013. Brigham Young University. All Rights Reserved.