• May 23, 2018 News![CFP] 2019 the annual meeting of IJMLC Editorial Board, ACMLC 2018, will be held in Ho Chi Minh, Vietnam, December 7-9, 2018   [Click]
  • May 23, 2018 News!Good News! All papers from Volume 8, Number 1 have been indexed by Scopus!   [Click]
  • May 29, 2018 News!Vol.8, No.2 has been published with online version.   [Click]
Search
General Information
Editor-in-chief
Dr. Lin Huang
Metropolitan State University of Denver, USA
It's my honor to take on the position of editor in chief of IJMLC. We encourage authors to submit papers concerning any branch of machine learning and computing.
IJMLC 2017 Vol.7(6): 232-237 ISSN: 2010-3700
DOI: 10.18178/ijmlc.2017.7.6.652

Removing Shadows from Video

Seyed Mahdi Javadi Brunel, Yongmin Li, and Xiaohui Liu
Abstract—This paper presents a novel approach to automatic shadow identification and removal from video input. Based on the observation that the length and position of a shadow changes linearly over a relatively long period in outdoor environments, due to the relative movement of the sun, we can distinguish a shadow from other dark regions in an input video. Subsequently, we can identify the Reference Shadow as that with the highest confidence of the aforementioned linear changes. This Reference Shadow is used to fit the shadow-free invariant model, with which the shadow-free invariant images can be computed for all frames in the input video. Our method does not require camera calibration and shadows from stationary objects, as moving objects are detected automatically.

Index Terms—Invariant image, reference shadow, video surveillance, shadow-less image, shadow detection.

The authors are with the Department of computer science, Brunel University, UK (e-mail: Seyed.javadi@brunel.ac.uk, Yongmin.li@brunel.ac.uk, XiaoHui.Liu@brunel.ac.uk).

[PDF]

Cite: Seyed Mahdi Javadi Brunel, Yongmin Li, and Xiaohui Liu, "Removing Shadows from Video," International Journal of Machine Learning and Computing vol. 7, no. 6, pp. 232-237, 2017.

Copyright © 2008-2018. International Journal of Machine Learning and Computing. All rights reserved.
E-mail: ijmlc@ejournal.net