Enhancement of fast pedestrian detection using HOG features

Histograms of Oriented Gradients (HOG) suffers low processing speed, due to complex and redundant computations. In this paper, a method to improve the speed of detection while maintaining the accuracy has been proposed.This is implemented without using any special purpose hardware such as GPU. The...

Full description

Bibliographic Details
Main Authors: Baghdadi, Ahmad, Abd Latif, Suhaimi
Format: Article
Language:English
Published: Institute of Research and Journals 2015
Subjects:
Online Access:http://irep.iium.edu.my/44555/
http://irep.iium.edu.my/44555/1/11-126-142960909718-22.pdf
_version_ 1848782624911261696
author Baghdadi, Ahmad
Abd Latif, Suhaimi
author_facet Baghdadi, Ahmad
Abd Latif, Suhaimi
author_sort Baghdadi, Ahmad
building IIUM Repository
collection Online Access
description Histograms of Oriented Gradients (HOG) suffers low processing speed, due to complex and redundant computations. In this paper, a method to improve the speed of detection while maintaining the accuracy has been proposed.This is implemented without using any special purpose hardware such as GPU. The speed has been substantially increased through the calculations of trilinear interpolation within each block of cells, utilizing the sub-cell method. The redundant calculation over two levels has been avoided: within each block and within the detection window by utilizing the concept of reusing the calculated features. Results showed a significant speed up by more than eleven times, with almost the same detection accuracy of the original algorithm.
first_indexed 2025-11-14T16:08:25Z
format Article
id iium-44555
institution International Islamic University Malaysia
institution_category Local University
language English
last_indexed 2025-11-14T16:08:25Z
publishDate 2015
publisher Institute of Research and Journals
recordtype eprints
repository_type Digital Repository
spelling iium-445552017-11-21T08:26:19Z http://irep.iium.edu.my/44555/ Enhancement of fast pedestrian detection using HOG features Baghdadi, Ahmad Abd Latif, Suhaimi T10.5 Communication of technical information Histograms of Oriented Gradients (HOG) suffers low processing speed, due to complex and redundant computations. In this paper, a method to improve the speed of detection while maintaining the accuracy has been proposed.This is implemented without using any special purpose hardware such as GPU. The speed has been substantially increased through the calculations of trilinear interpolation within each block of cells, utilizing the sub-cell method. The redundant calculation over two levels has been avoided: within each block and within the detection window by utilizing the concept of reusing the calculated features. Results showed a significant speed up by more than eleven times, with almost the same detection accuracy of the original algorithm. Institute of Research and Journals 2015-04 Article PeerReviewed application/pdf en http://irep.iium.edu.my/44555/1/11-126-142960909718-22.pdf Baghdadi, Ahmad and Abd Latif, Suhaimi (2015) Enhancement of fast pedestrian detection using HOG features. International Journal of Industrial Electronics and Electrical Engineering, 3 (4). pp. 18-22. ISSN 2347-6982 http://pep.ijieee.org.in/journal_pdf/11-126-142960909718-22.pdf
spellingShingle T10.5 Communication of technical information
Baghdadi, Ahmad
Abd Latif, Suhaimi
Enhancement of fast pedestrian detection using HOG features
title Enhancement of fast pedestrian detection using HOG features
title_full Enhancement of fast pedestrian detection using HOG features
title_fullStr Enhancement of fast pedestrian detection using HOG features
title_full_unstemmed Enhancement of fast pedestrian detection using HOG features
title_short Enhancement of fast pedestrian detection using HOG features
title_sort enhancement of fast pedestrian detection using hog features
topic T10.5 Communication of technical information
url http://irep.iium.edu.my/44555/
http://irep.iium.edu.my/44555/
http://irep.iium.edu.my/44555/1/11-126-142960909718-22.pdf