Enhancement of fast pedestrian detection using HOG features

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

PDF - Published Version Restricted to Repository staff only Download (168kB) | Request a copy

Abstract

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.

Item Type:	Article (Journal)
Additional Information:	3064/44555
Uncontrolled Keywords:	Pedestrian Detection, HOG, Fast Method
Subjects:	T Technology > T Technology (General) > T10.5 Communication of technical information
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button):	Kulliyyah of Engineering > Department of Electrical and Computer Engineering
Depositing User:	Dr Suhaimi Abd Latif
Date Deposited:	03 Sep 2015 14:08
Last Modified:	21 Nov 2017 16:26
URI:	http://irep.iium.edu.my/id/eprint/44555

Actions (login required)

View Item