Publication Details
Real-time object detection on CUDA
Jošth Radovan, Ing. (DCGM FIT BUT)
Juránek Roman, Ing., Ph.D. (DCGM FIT BUT)
Havel Jiří, Ing., Ph.D. (DCGM FIT BUT)
Hradiš Michal, Ing., Ph.D. (DCGM FIT BUT)
Zemčík Pavel, prof. Dr. Ing. (DCGM FIT BUT)
Object detection, Pattern recognition, Acceleration, CUDA, AdaBoost
The aim of the research described in this article is to accelerate object detection in images and video sequences using graphics processors. It includes algorithmic modifications and adjustments of existing detectors, constructing variants of efficient implementations and evaluation comparing with efficient implementations on the CPUs. This article focuses on detection by statistical classifiers based on boosting. The implementation and the necessary algorithmic alterations are described, followed by experimental measurements of the created object detector and discussion of the results. The final solution outperforms the reference efficient CPU/SSE implementation, by approximately 6-89 for high-resolution videos using nVidia GeForce 9800GTX and Intel Core2 Duo E8200.
@ARTICLE{FITPUB9393,
author = "Adam Herout and Radovan Jo\v{s}th and Roman Jur\'{a}nek and Ji\v{r}\'{i} Havel and Michal Hradi\v{s} and Pavel Zem\v{c}\'{i}k",
title = "Real-time object detection on CUDA",
pages = "159--170",
journal = "Journal of Real-Time Image Processing",
volume = 2011,
number = 3,
year = 2011,
ISSN = "1861-8200",
language = "english",
url = "https://www.fit.vut.cz/research/publication/9393"
}