LAUSR

Haze in remote sensing images severely degrades image visibility, making it hard to identify different land covers. This work proposes an edge-preserving filtering-based image dehazing method for remote sensing images, mainly consisting of following several steps. First, the original image contaminated with haze is decomposed by a multiscale guided filtering into base layers that contain haze components and detail layers that reflect the spatial details of input. Then, an optimized atmospheric scattering model is performed on the base layers to eliminate haze. Next, adaptive nonlinear mapping is exploited to enhance image details. Finally, the resulting image is reconstructed by combining the dehazed base layers and the refined detail layers. Experiments on several images demonstrate that the proposed method has an outstanding haze removal capability and yields better dehazing performance compared to other dehazing approaches in terms of objective indexes and subjective results.