Publication Details

Cooperative Coevolutionary Approximation in HOG-based Human Detection Embedded System

WIGLASZ Michal and SEKANINA Lukáš. Cooperative Coevolutionary Approximation in HOG-based Human Detection Embedded System. In: 2018 IEEE Symposium Series on Computational Intelligence (SSCI 2018). Bengaluru: Institute of Electrical and Electronics Engineers, 2018, pp. 1313-1320. ISBN 978-1-5386-9276-9.
Czech title
Kooperativní koevoluční aproximace v systému detekce osob založeném na HOG
Type
conference paper
Language
english
Authors
Keywords
Approximate computing, Cartesian genetic programming, Cooperative coevolution, Histogram of oriented gradients
Abstract
The histogram of oriented gradients (HOG) feature extraction is a computer vision method widely used in embedded systems for detection of objects such as pedestrians. We used cooperative coevolutionary Cartesian genetic programming (CGP) to exploit the error resilience in the HOG algorithm. We evolved new approximate implementations of the arctan and square root functions, which are typically employed to compute the gradient orientations and magnitudes. When the best evolved approximations are integrated into the software implementation of the HOG algorithm, not only the execution time, but also the classification accuracy was improved in comparison with approximations evolved separately using CGP and also compared to the state-of-the art approximate implementations. As the evolved code does not contain any loops and branches, it is suitable for the follow-up low-power hardware implementation.
Published
2018
Pages
1313-1320
Proceedings
2018 IEEE Symposium Series on Computational Intelligence (SSCI 2018)
Conference
IEEE Symposium Series on Computational Intelligence 2018, Bengaluru, IN
ISBN
978-1-5386-9276-9
Publisher
Institute of Electrical and Electronics Engineers
Place
Bengaluru, IN
DOI
BibTeX
@INPROCEEDINGS{FITPUB11695,
   author = "Michal Wiglasz and Luk\'{a}\v{s} Sekanina",
   title = "Cooperative Coevolutionary Approximation in HOG-based Human Detection Embedded System",
   pages = "1313--1320",
   booktitle = "2018 IEEE Symposium Series on Computational Intelligence (SSCI 2018)",
   year = 2018,
   location = "Bengaluru, IN",
   publisher = "Institute of Electrical and Electronics Engineers",
   ISBN = "978-1-5386-9276-9",
   doi = "10.1109/SSCI.2018.8628910",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/11695"
}
Files
Back to top