Evolutionary Approximation of Gradient Orientation Module in HOG-based Human Detection System

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F17%3APU126415" target="_blank" >RIV/00216305:26230/17:PU126415 - isvavai.cz</a>

Result on the web

<a href="https://www.fit.vut.cz/research/publication/11441/" target="_blank" >https://www.fit.vut.cz/research/publication/11441/</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/GlobalSIP.2017.8309171" target="_blank" >10.1109/GlobalSIP.2017.8309171</a>

Result language

angličtina

Original language name

Evolutionary Approximation of Gradient Orientation Module in HOG-based Human Detection System

Original language description

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.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

<a href="/en/project/LQ1602" target="_blank" >LQ1602: IT4Innovations excellence in science</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Publication year

2017

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

2017 IEEE Global Conference on Signal and Information Processing GlobalSIP 2017

ISBN

978-1-5090-5989-8

ISSN

—

e-ISSN

—

Number of pages

5

Pages from-to

1300-1304

Publisher name

IEEE Signal Processing Society

Place of publication

Montreal

Event location

Montreal, Kanada

Event date

Nov 14, 2017

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

000450053100257