Stochastic shadow detection using a hypergraph partitioning approach. (March 2017)

• Record Type: Journal Article
• Authors: Gomes, Vitor; Barcellos, Pablo; Scharcanski, Jacob
• Is Part Of: Pattern recognition. Volume 63(2017:Mar.)
• Page Start: 30
• Page End: 44
• Publication Date: 2017-03
• Subjects: Shadow detection -- Chromaticity -- Gradient correlation -- Hypergraph segmentation; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2016.09.008
• Languages: English
• ISSNs: 0031-3203

Abstract

Abstract: Discriminating shadows from the objects casting them often is challenging in practice, since the moving targets and their shadows tend to present similar motion patterns, and foreground detection methods often confuse cast shadows with foreground objects. To overcome these shadow detection difficulties, we propose a new stochastic shadow detection approach. In the proposed method, chromatic and gradient information are integrated with image hypergraph segmentation using a cascade of shadow/non-shadow classifiers, and a stochastic majority voting scheme is used to detect the shadow regions. The proposed method receives as input the segmented foreground objects and their cast shadows (mask), and outputs the shadows detected in the foreground mask. The experimental results were obtained with seven well known datasets, and suggest that the proposed shadow detection scheme can be more robust to different video acquisition conditions than other shadow detection methods, that are representative of the state-of-the-art. Abstract : Highlights: A novel shadow detection method is proposed for video sequences or still images. Color, texture and hypergraph methods are used to classify shadow/non-shadow segments. A voting scheme finds consensus among the classifiers to detect the shadow segments. The proposed method tends to perform better than comparable state-of-the-art methods.