The shadow regions in an image may lead to uncertainty of the image content, which is not conducive to other computer vision tasks, so shadow detection is often considered as a pre-processing process of computer vision algorithms. However, most of the existing shadow detection algorithms use a multi-level network structure, which leads to difficulties in model training, and although some algorithms adopting single-layer network structure have been proposed, they only focus on local shadows and ignore the relation between shadows. To solve this problem, a shadow detection algorithm based on hybrid attention model was proposed to improve the accuracy and robustness of shadow detection. Firstly, the pre-trained deep network ResNext101 was used as the front-end feature extraction network to extract the basic features of the image. Secondly, the bidirectional pyramid structure was used for feature fusion from shallow to deep and deep to shallow, and an information compensation mechanism was proposed to reduce the loss of deep semantic information. Thirdly, a hybrid attention model was proposed for feature fusion by combining spatial attention and channel attention, so as to capture differences between shaded and non-shaded regions. Finally, the prediction results of two directions were merged to obtain the final shadow detection result. Comparison experiments were conducted on public datasets SBU and UCF. The results show that compared with DSC (Direction-aware Spatial Context) algorithm, the Balance Error Rate (BER) of the proposed algorithm is reduced by 30% and 11% respectively, proving that the proposed method can better suppress shadow error detection and enhance shadow details.

Shadow in an image is important visual information of the projective object, but it affects computer vision tasks. Existing single image shadow removal methods cannot obtain good shadow-free results due to the lack of robust shadow features or insufficiency of and errors in training sample data. In order to generate accurately the shadow mask image for describing the illumination attenuation degree and obtain the high quality shadow-free image, a single image shadow removal method based on attenuated generative adversarial network was proposed. Firstly, an attenuator guided by the sensitive parameters was used to augment the training sample data in order to provide shadow sample images agreed with physical illumination model for a subsequent generator and discriminator. Then, with the supervision from the discriminator, the generator combined perceptual loss function to generate the final shadow mask. Compared with related works, the proposed method can effectively recover the illumination information of shadow regions and obtain the more realistic shadow-free image with natural transition of shadow boundary. Shadow removal results were evaluated using objective metric. Experimental results show that the proposed method can remove shadow effectively in various real scenes with a good visual consistency.