CPNet: A Context Preserver Convolutional Neural Network for Detecting Shadows in Single RGB Images
This work addresses the challenge of automatic shadow detection for computer vision applications, representing an incremental advance with specific performance gains.
The paper tackles the problem of pixel-level shadow detection in single RGB images by proposing a deep-learning segmentation method, achieving a 22% and 14% improvement in Balanced Error Rate on the SBU and UCF datasets, respectively.
Automatic detection of shadow regions in an image is a difficult task due to the lack of prior information about the illumination source and the dynamic of the scene objects. To address this problem, in this paper, a deep-learning based segmentation method is proposed that identifies shadow regions at the pixel-level in a single RGB image. We exploit a novel Convolutional Neural Network (CNN) architecture to identify and extract shadow features in an end-to-end manner. This network preserves learned contexts during the training and observes the entire image to detect global and local shadow patterns simultaneously. The proposed method is evaluated on two publicly available datasets of SBU and UCF. We have improved the state-of-the-art Balanced Error Rate (BER) on these datasets by 22\% and 14\%, respectively.