Paired regions for shadow detection and removal

Ruiqi Guo, Qieyun Dai, Derek Hoiem

Research output: Contribution to journalArticlepeer-review

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.

Original languageEnglish (US)
Article number6319317
Pages (from-to)2956-2967
Number of pages12
JournalIEEE transactions on pattern analysis and machine intelligence
Volume35
Issue number12
DOIs
StatePublished - Nov 20 2013

Keywords

  • Shadow detection
  • enhancement
  • region classification
  • shadow removal

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics

Fingerprint Dive into the research topics of 'Paired regions for shadow detection and removal'. Together they form a unique fingerprint.

Cite this