To detect wind turbines precisely and quickly in very high resolution remote sensing images (VHRRSI) we propose target mask U-Net. This convolution neural network (CNN), which is carefully designed to be a wide-field detector, models the pixel class assignment to wind turbines and their context information. The shadow, which is the context information of the target in this study, has been regarded as part of a wind turbine instance. We have trained the target mask U-Net on training dataset, which is composed of down sampled image blocks and instance mask blocks. Some post-processes have been integrated to eliminate wrong spots and produce bounding boxes of wind turbine instances. The evaluation metrics prove the reliability and effectiveness of our method for the average F1-score of our detection method is up to 0.97. The comparison of detection accuracy and time consuming with the weakly supervised targets detection method based on CNN illustrates the superiority of our method.

This paper presents a regionalized segmentation method for synthetic aperture radar (SAR) intensity images based on tessellation with irregular polygons. In the proposed method, the image domain is partitioned into a collection of irregular polygons, which are constructed using sets of nodes and are used to fit homogeneous regions with arbitrary shapes. Each partitioned polygon is taken as the basic processing unit. Assuming the intensities of the pixels in the polygon follow an independent and identical gamma distribution, the likelihood of the image intensities is modeled. After defining the prior distributions of the tessellation and the parameters for the likelihood model, a posterior probability model can be built based on the Bayes theorem as a segmentation model. To obtain optimal segmentation, a reversible-jump Markov chain Monte Carlo (RJMCMC) algorithm is designed to simulate from the segmentation model, where the move operations include updating the gamma distribution parameter, updating labels, moving nodes, merging polygons, splitting polygons, adding nodes, and deleting nodes. Experiments were carried out on synthetic and real SAR intensity images using the proposed method while the regular and Voronoi tessellation-based methods were also preformed for comparison. Our results show the proposed method overcomes some intrinsic limitations of current segmentation methods and is able to generate good results for homogeneous regions with different shapes.