Title :
Automatic Feature Learning for Robust Shadow Detection
Author :
Khan, S.H. ; Bennamoun, Mohammed ; Sohel, Ferdous ; Togneri, Roberto
Author_Institution :
Univ. of Western Australia, Perth, WA, Australia
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 :
feature extraction; learning (artificial intelligence); neural nets; object detection; 7-layer network architecture; ConvNet; automatic feature learning; conditional random field model; convolution layers; invariant hand-crafted features; multiple convolutional deep neural networks; object boundaries; predicted posteriors; robust shadow detection; shadow databases; shadow variant; single photograph; smooth shadow contours; subsampling layers; Convolution; Feature extraction; Image edge detection; Kernel; Lighting; Training; Visualization;
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on
Conference_Location :
Columbus, OH
DOI :
10.1109/CVPR.2014.249