Paper Info
Title
Paired regions for shadow detection and removal.
Abstract
In this paper, we address the problem of shadow detection and removal from single images of natural scenes. Differently from traditional methods that explore pixel or edge information, we employ a region-based approach. In addition to considering individual regions separately, we predict relative illumination conditions between segmented regions from their appearances and perform pairwise classification based on such information. Classification results are used to build a graph of segments, and graph-cut is used to solve the labeling of shadow and nonshadow regions. Detection results are later refined by image matting, and the shadow-free image is recovered by relighting each pixel based on our lighting model. We evaluate our method on the shadow detection dataset in Zhu et al. In addition, we created a new dataset with shadow-free ground truth images, which provides a quantitative basis for evaluating shadow removal. We study the effectiveness of features for both unary and pairwise classification.
Year
DOI
Venue
2013
10.1109/TPAMI.2012.214
IEEE Trans. Pattern Anal. Mach. Intell.
Keywords
Field
DocType
paired regions,pairwise classification,shadow-free ground truth image,classification result,new dataset,image matting,shadow detection,shadow removal,shadow detection dataset,edge information,detection result,graph cut,image classification,lighting,histograms,graph theory,unary classification
Cut,Histogram,Shadow,Computer vision,Object detection,One-class classification,Pattern recognition,Computer science,Ground truth,Artificial intelligence,Pixel,Contextual image classification
Journal
Volume
Issue
ISSN
35
12
1939-3539
Citations 
PageRank 
References 
52
1.39
20
Authors
3
Name
Order
Citations
PageRank
Ruiqi Guo156422.10
Qieyun Dai221719.85
Derek Hoiem34998302.66