Automatic Feature Learning for Robust Shadow Detection
- 1 June 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 1939-1946
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.Keywords
This publication has 21 references indexed in Scilit:
- Learning Non-linear Reconstruction Models for Image Set Classification2014
- Efficient BackProp2012
- The Shadow Meets the Mask: Pyramid‐Based Shadow RemovalComputer Graphics Forum, 2008
- Graph Cuts and Efficient N-D Image SegmentationInternational Journal of Computer Vision, 2006
- Illumination normalization with time-dependent intrinsic images for video surveillanceIEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
- Cast shadow segmentation using invariant color featuresComputer Vision and Image Understanding, 2004
- Detecting moving shadows: algorithms and evaluationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2003
- Illumination from shadowsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2003
- Illusory motion from shadowsNature, 1996
- Receptive fields, binocular interaction and functional architecture in the cat's visual cortexThe Journal of Physiology, 1962