Logo image
Automatic feature learning for robust shadow detection
Conference paper

Automatic feature learning for robust shadow detection

S.H. Khan, M. Bennamoun, F. Sohel and R. Togneri
2014 IEEE Conference on Computer Vision and Pattern Recognition, pp.1939-1946
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2014 (Columbus, OH, 23/06/2014–28/06/2014)
2014
url
Link to Published Version *Subscription may be requiredView

Abstract

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.

Details

Metrics

78 Record Views
Logo image