Catalog Home Page

Automatic feature learning for robust shadow detection

Khan, S.H., Bennamoun, M., Sohel, F. and Togneri, R. (2014) Automatic feature learning for robust shadow detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2014, 23 - 28 June 2014, Columbus, OH pp. 1939-1946.

Link to Published Version:
*Subscription may be required


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.

Publication Type: Conference Paper
Item Control Page Item Control Page