Shadow Detection and Removal Using Tri-Class Based Thresholding and Shadow Matting Technique. (2016)

• Record Type: Journal Article
• Authors: Anoopa, S.; Dhanya, V.; Kizhakkethottam, Jubilant J.
• Is Part Of: Procedia technology. Volume 24(2016)
• Page Start: 1358
• Page End: 1365
• Publication Date: 2016
• Subjects: Shadow detection -- urban -- tri-class thresholdind -- soft matting -- shadow removal; Technology -- Congresses; Technology -- Periodicals; Engineering -- Congresses; Engineering -- Periodicals; Engineering; Technology; Conference proceedings; Periodicals; 605
• DOI: 10.1016/j.protcy.2016.05.148
• Languages: English
• ISSNs: 2212-0173

Abstract

Abstract: Shadow detection and removal in real scene images are always a significant problem. This work aims to address the problem of shadow detection and removal from urban high resolution remote sensing images. To detect shadow from images a pre processing step is performed. Triclass Thresholding technique is used for segmentation and it is based on Otsu's method. Using this iterative method the images are separated into three classes that are foreground region, background region and to-be-determined region. Then Otsu's method is applied only to to-be-determined region iteratively. After segmentation shadow in the images are detected using bimodal histogram splitting method. Then the false shadow including water bodies, vegetation and some dark objects are eliminated by considering spectral and geometric features. Also an additional method called pair wise region based detection is used to accurately detect the shadow. So image is clustered by using K-mean Algorithm and to detect shadow by comparing colour and the ratio of intensities in the adjacent pair. Finally shadow matting called soft matting technique is used to obtain shadow free image. Results show that the new method accurately detects shadow and can efficiently restore shadow with 90.57% accuracy.