A Two-Stage Density-Aware Single Image Deraining Method.

Although advanced single image deraining methods have been proposed, one main challenge remains: the available methods usually perform well on specific rain patterns but can hardly deal with scenarios with dramatically different rain densities, especially when the impacts of rain streaks and the veiling effect caused by rain accumulation are heavily coupled. To tackle this challenge, we propose a two-stage density-aware single image deraining method with gated multi-scale feature fusion. In the first stage, a realistic physics model closer to real rain scenes is leveraged for initial deraining, and a network branch is also trained for rain density estimation to guide the subsequent refinement. The second stage of model-independent refinement is realized using conditional Generative Adversarial Network (cGAN), aiming to eliminate artifacts and improve the restoration quality. In particular, dilated convolutions are applied to extract rain features at multiple scales and gated feature fusion is exploited to better aggregate multi-level contextual information in both stages. Extensive experiments have been conducted on representative synthetic rain datasets and real rain scenes. Quantitative and qualitative results demonstrate the superiority of our method in terms of effectiveness and generalization ability, which outperforms the state-of-the-art.

Context guided belief propagation for remote sensing image classification.

We propose a context guided belief propagation (BP) algorithm to perform high spatial resolution multispectral imagery (HSRMI) classification efficiently utilizing superpixel representation. One important characteristic of HSRMI is that different land cover objects possess a similar spectral property. This property is exploited to speed up the standard BP (SBP) in the classification process. Specifically, we leverage this property of HSRMI as context information to guide messages passing in SBP. Furthermore, the spectral and structural features extracted at the superpixel level are fed into a Markov random field framework to address the challenge of low interclass variation in HSRMI classification by minimizing the discrete energy through context guided BP (CBP). Experiments show that the proposed CBP is significantly faster than the SBP while retaining similar performance as compared with SBP. Compared to the baseline methods, higher classification accuracy is achieved by the proposed CBP when the context information is used with both spectral and structural features.

[Fast segmentation algorithm of high resolution remote sensing image based on multiscale mean shift].

Mean Shift algorithm is a robust approach toward feature space analysis and it has been used wildly for natural scene image and medical image segmentation. However, high computational complexity of the algorithm has constrained its application in remote sensing images with massive information. A fast image segmentation algorithm is presented by extending traditional mean shift method to wavelet domain. In order to evaluate the effectiveness of the proposed algorithm, multispectral remote sensing image and synthetic image are utilized. The results show that the proposed algorithm can improve the speed 5-7 times compared to the traditional MS method in the premise of segmentation quality assurance.