Automatic Feature Learning for Robust Shadow Detection

Salman Hameed Khan, Mohammed Bennamoun, Ferdous Sohel, Roberto Togneri; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014, pp. 1931-1938


We present a practical framework to automatically detect shadows in real world scenes from a single photograph. Previous works on shadow detection put a lot of effort in designing shadow variant and invariant hand-crafted features. In contrast, our framework automatically learns the most relevant features in a supervised manner using multiple convolutional deep neural networks (ConvNets). The 7-layer network architecture of each ConvNet consists of alternating convolution and sub-sampling layers. The proposed framework learns features at the super-pixel level and along the object boundaries. In both cases, features are extracted using a context aware window centered at interest points. The predicted posteriors based on the learned features are fed to a conditional random field model to generate smooth shadow contours. Our proposed framework consistently performed better than the state-of-the-art on all major shadow databases collected under a variety of conditions.

Related Material

author = {Hameed Khan, Salman and Bennamoun, Mohammed and Sohel, Ferdous and Togneri, Roberto},
title = {Automatic Feature Learning for Robust Shadow Detection},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2014}