Moving shadow detection via binocular vision and colour clustering



Lu, Lei, Xu, Ming, Smith, Jeremy S ORCID: 0000-0002-0212-2365 and Yan, Yuyao
(2020) Moving shadow detection via binocular vision and colour clustering. IET COMPUTER VISION, 14 (8). pp. 665-673.

This is the latest version of this item.

[img] Text
cvi5.pdf - Author Accepted Manuscript

Download (4MB) | Preview

Abstract

<jats:p>A pedestrian segmentation algorithm in the presence of cast shadows is presented in this study. The novelty of this algorithm lies in the fusion of multi‐view and multi‐plane homographic projections of foregrounds and the use of the fused data to guide colour clustering. This brings about an advantage over the existing binocular algorithms in that it can remove cast shadows while keeping pedestrians’ body parts, which occlude shadows. Phantom detection, which is inherent with the binocular method, is also investigated. Experimental results with real‐world videos have demonstrated the efficiency of this algorithm.</jats:p>

Item Type: Article
Depositing User: Symplectic Admin
Date Deposited: 08 Jul 2020 09:22
Last Modified: 18 Sep 2023 19:18
DOI: 10.1049/iet-cvi.2019.0175
Related URLs:
URI: https://livrepository.liverpool.ac.uk/id/eprint/3093259

Available Versions of this Item