A Survey on Shadow Detection Techniques in a Single Image

Abstract

Shadows are inescapable elements in a scene formed due to the presence of an object between the light source and the surface on which it is cast. Appearance of shadows often cause severe issues in computer vision applications like object extraction, surveillance etc. Researchers have made effort to device techniques to locate and remove shadows from images and videos. This paper attempts to survey the various shadow detection algorithms for a single image. For the purpose of survey, the notable research work in the literature is classified under five major categories: invariant-based detection, feature-based detection, region-based detection, color model based detection and interactive shadow detection. The survey also includes a qualitative and quantitative evaluation of the methods discussed. As outcomes of the survey, it is observed that, (i) though the works discussed under each of these categories are capable of detecting shadows in different scenarios, the accuracy and time taken need further improvements to make the shadow detection process acceptable for practical applications; (ii) detection of self shadows and heavily scattered shadows are challenging;(iii) the risk of misclassifying dark objects as shadows should be addressed; (iv) soft shadows that span multiple surfaces pose challenge in accurate detection of shadows.

DOI: http://dx.doi.org/10.5755/j01.itc.47.1.15012