Přístupnostní navigace
E-application
Search Search Close
Publication detail
WIGLASZ, M. SEKANINA, L.
Original Title
Evolutionary Approximation of Gradient Orientation Module in HOG-based Human Detection System
Type
conference paper
Language
English
Original 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 Cartesian genetic programming (CGP) to exploit the error resilience in the HOG algorithm. We evolved new approximate implementations of the arctan function, which is typically employed to compute the gradient orientations. When the best evolved approximations are integrated into the SW implementation of the HOG algorithm, not only the execution time, but also the classification accuracy was improved in comparison with the accurate implementation and the state-of-the-art approximate implementations.
Keywords
Functional approximation, Cartesian genetic programming, Histogram of oriented gradients
Authors
WIGLASZ, M.; SEKANINA, L.
Released
14. 11. 2017
Publisher
IEEE Signal Processing Society
Location
Montreal
ISBN
978-1-5090-5989-8
Book
2017 IEEE Global Conference on Signal and Information Processing GlobalSIP 2017
Pages from
1300
Pages to
1304
Pages count
5
URL
https://www.fit.vut.cz/research/publication/11441/
BibTex
@inproceedings{BUT144438, author="Michal {Wiglasz} and Lukáš {Sekanina}", title="Evolutionary Approximation of Gradient Orientation Module in HOG-based Human Detection System", booktitle="2017 IEEE Global Conference on Signal and Information Processing GlobalSIP 2017", year="2017", pages="1300--1304", publisher="IEEE Signal Processing Society", address="Montreal", doi="10.1109/GlobalSIP.2017.8309171", isbn="978-1-5090-5989-8", url="https://www.fit.vut.cz/research/publication/11441/" }