eprintid: 8924
rev_number: 2
eprint_status: archive
userid: 1
dir: disk0/00/00/89/24
datestamp: 2023-11-09 16:20:51
lastmod: 2023-11-09 16:20:51
status_changed: 2023-11-09 16:13:52
type: conference_item
metadata_visibility: show
creators_name: Kajo, I.
creators_name: Malik, A.S.
creators_name: Kamel, N.
title: An evaluation of optical flow algorithms for crowd analytics in surveillance system
ispublished: pub
keywords: Computational efficiency; Motion analysis; Motion estimation, Crowd; Motion detection; Motion Vectors; Object velocity and direction; Optical flow estimation, Optical flows
note: cited By 11; Conference of 6th International Conference on Intelligent and Advanced Systems, ICIAS 2016 ; Conference Date: 15 August 2016 Through 17 August 2016; Conference Code:125970
abstract: Optical flow technique is one of the significant motion estimation techniques. Due to its importance, several optical flow technique have been used in order to estimate the velocity and the direction of the pedestrians in the crowded scenes. This paper presents an overview of the optical flow methods that used mainly for pedestrian and crowd motion detection. The work focuses on the conventional optical flow method such as Lucas & Kanade and Horn & Schunck methods as well as the most recent methods such as Classic+NL that combines the classic formulation with a new non-local term. The improvement in computational efficiency and increasing interest in robust and accurate motion estimation algorithms lead to increase in the use of optical flow in crowd analytic applications. The implementation of optical flow algorithms is investigated and an evaluation of those techniques is provided qualitatively as well as quantitatively. The qualitative analysis illustrates the optical flow performance in terms of large motion, occlusion, motion discontinuities, illumination and different light condition. Quantitative analysis is in terms of computational time and accuracy. © 2016 IEEE.
date: 2017
publisher: Institute of Electrical and Electronics Engineers Inc.
official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85012025589&doi=10.1109%2fICIAS.2016.7824064&partnerID=40&md5=ec8cbf48efaa5c30a68d69afbb70bf7b
id_number: 10.1109/ICIAS.2016.7824064
full_text_status: none
publication: International Conference on Intelligent and Advanced Systems, ICIAS 2016
refereed: TRUE
isbn: 9781509008452
citation:   Kajo, I. and Malik, A.S. and Kamel, N.  (2017) An evaluation of optical flow algorithms for crowd analytics in surveillance system.  In: UNSPECIFIED.