Proceedings ArticleDOI
Detection of moving cast shadows using image orthogonal transform
Wei Zhang,Xiangzhong Fang,Yi Xu +2 more
- Vol. 1, pp 626-629
TLDR
A novel method to detect the moving cast shadows in the scene using normalized coefficients of orthogonal transform of image block are proved to be illumination invariant and are used to classify moving shadows and foreground objects.Abstract:
In many image and computer vision applications, shadows interfere with fundamental tasks such as moving objects segmentation and tracking. In this paper, a novel method is proposed to detect the moving cast shadows in the scene. The normalized coefficients of orthogonal transform of image block are proved to be illumination invariant and are used to classify moving shadows and foreground objects. Five kinds of orthogonal transform: DCT, DFT, Haar Transform, SVD and Hadamard Transform, are utilized in our work to detect moving cast shadows. Experimental results show that the proposed method succeeds in detecting moving cast shadows within indoor and outdoor environments.read more
Citations
More filters
Journal ArticleDOI
Shadow detection: A survey and comparative evaluation of recent methods
TL;DR: A survey and a comparative evaluation of recent techniques for moving cast shadow detection indicate that all shadow detection approaches make different contributions and all have individual strength and weaknesses.
Journal ArticleDOI
Human detection in surveillance videos and its applications - a review
TL;DR: A comprehensive review with comparisons on available techniques for detecting human beings in surveillance videos is presented and the characteristics of few benchmark datasets as well as the future research directions on human detection have also been discussed.
Journal ArticleDOI
Moving Cast Shadows Detection Using Ratio Edge
TL;DR: This paper proves that the ratio edge is illumination invariant and presents a novel method for moving cast shadows detection that significantly outperforms state-of-the-art methods.
Journal ArticleDOI
SVD Face: Illumination-Invariant Face Representation
TL;DR: Experimental results demonstrate that the SVD face is effective for face recognition and verification compared to previous approaches proposed in literature and greatly preserves textures of the original image based on the relaxation of SVD coefficients.
Journal ArticleDOI
An evaluation of moving shadow detection techniques
Mosin Russell,Ju Jia Zou,Gu Fang +2 more
TL;DR: This paper addresses the main problematic situations associated with shadows and provides a comprehensive performance comparison on up-todate methods that have been proposed to tackle these problems.
References
More filters
Journal ArticleDOI
Learning patterns of activity using real-time tracking
Chris Stauffer,W.E.L. Grimson +1 more
TL;DR: This paper focuses on motion tracking and shows how one can use observed motion to learn patterns of activity in a site and create a hierarchical binary-tree classification of the representations within a sequence.
Journal ArticleDOI
Detecting moving shadows: algorithms and evaluation
TL;DR: This paper organizes contributions reported in the literature in four classes two of them are statistical and two are deterministic, and presents a comparative empirical evaluation of representative algorithms selected from these four classes.
Proceedings ArticleDOI
Improving shadow suppression in moving object detection with HSV color information
TL;DR: This work aims to present a technique for shadow detection and suppression used in a system for moving visual object detection and tracking, carried out in the HSV color space to improve the accuracy in detecting shadows.
Journal ArticleDOI
Efficient moving object segmentation algorithm using background registration technique
TL;DR: An efficient moving object segmentation algorithm suitable for real-time content-based multimedia communication systems is proposed and a processing speed of 25 QCIF fps can be achieved on a personal computer with a 450-MHz Pentium III processor.
Journal ArticleDOI
Cast shadow segmentation using invariant color features
TL;DR: A new cast shadow segmentation algorithm is proposed that exploits spectral and geometrical properties of shadows in a scene to perform this task and is robust and efficient in detecting shadows for a large class of scenes.