Moving shadow detection via binocular vision and colour clustering

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 advanta...

Full description

Saved in:
Bibliographic Details
Published in:IET computer vision 2020-12, Vol.14 (8), p.665-673
Main Authors: Lu, Lei, Xu, Ming, Smith, Jeremy S, Yan, Yuyao
Format: Article
Language:English
Subjects:
binocular method
binocular vision
cast shadows
colour clustering
computer vision
existing binocular algorithms
fused data
image colour analysis
image motion analysis
image segmentation
image sequences
multiview
object detection
pedestrian segmentation algorithm
pedestrians
phantom detection
Research Article
shadow detection
video signal processing
Citations: Items that this one cites
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1751-9632
1751-9640
1751-9640
DOI:10.1049/iet-cvi.2019.0175