Integer arithmetic approximation of the hog algorithm used for pedestrian detection

Autor:	Srdjan Sladojevic, Bojan Lalic, Andras Anderla, Darko Stefanovic, Dubravko Culibrk
Rok vydání:	2017
Předmět:	Integer arithmetic General Computer Science Computer science Pedestrian detection 0202 electrical engineering electronic engineering information engineering 020207 software engineering Tonelli–Shanks algorithm 02 engineering and technology Algorithm
Zdroj:	Computer Science and Information Systems. 14:329-346
ISSN:	2406-1018 1820-0214
DOI:	10.2298/csis160229011s
Popis:	This paper presents the results of a study of the effects of integer (fixed-point) arithmetic implementation on classification accuracy of a popular open-source people detection system based on Histogram of Oriented Gradients. It is investigated how the system performance deviates from the reference algorithm performance as integer arithmetic is introduced with different bit-width in several critical parts of the system. In performed experiments, the effects of different bit-width integer arithmetic implementation for four key operations were separately considered: HoG descriptor magnitude calculation, HoG descriptor angle calculation, normalization and SVM classification. It is found that a 13-bit representation of variables is more than sufficient to accurately implement this system in integer arithmetic. The experiments in the paper are conducted for pedestrian detection and the methodology and the lessons learned from this study allow generalization of conclusions to a broader class of applications.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::fe7cd05bb7fbcc9e054612a983e55d40 https://doi.org/10.2298/csis160229011s Zobrazit plný text záznamu