Publication Details

High Performance Architecture for Object Detection in Streamed Videos

ZEMČÍK Pavel, JURÁNEK Roman, MUSIL Martin, MUSIL Petr and HRADIŠ Michal. High Performance Architecture for Object Detection in Streamed Videos. In: Proceedings of FPL 2013. Porto: IEEE Circuits and Systems Society, 2013, pp. 1-4. ISBN 978-1-4799-0004-6. Available from: http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=&arnumber=6645559
Czech title
Architektura pro detekci objektů ve streamovaném videu
Type
conference paper
Language
english
Authors
URL
Keywords

Object Detection, FPGA, LRD, LBP, Streamed Video

Abstract
In this paper, we introduce a novel architecture of an engine for high performance multi-scale detection of objects in videos based on WaldBoost training algorithm.
The key properties of the architecture include processing of streamed data and low resource consumption. We implemented the engine in FPGA and we show that it can process 640x480 pixel video streams at over 160 fps without the need of external memory. We evaluate the design on the face detection task, compare it to state of the art designs, and discuss its features and limitations.
Published
2013
Pages
1-4
Proceedings
Proceedings of FPL 2013
Conference
23th International Conference on Field Programmable Logic and Applications, Porto, PT
ISBN
978-1-4799-0004-6
Publisher
IEEE Circuits and Systems Society
Place
Porto, PT
DOI
BibTeX
@INPROCEEDINGS{FITPUB10390,
   author = "Pavel Zem\v{c}\'{i}k and Roman Jur\'{a}nek and Martin Musil and Petr Musil and Michal Hradi\v{s}",
   title = "High Performance Architecture for Object Detection in Streamed Videos",
   pages = "1--4",
   booktitle = "Proceedings of FPL 2013",
   year = 2013,
   location = "Porto, PT",
   publisher = "IEEE Circuits and Systems Society",
   ISBN = "978-1-4799-0004-6",
   doi = "10.1109/FPL.2013.6645559",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/10390"
}
Back to top