Distributed photovoltaic power stations are an effective way to develop and utilize solar energy resources. Using high-resolution remote sensing images to obtain the locations, distribution, and areas of distributed photovoltaic power stations over a large region is important to energy companies, government departments, and investors. In this paper, a deep convolutional neural network was used to extract distributed photovoltaic power stations from high-resolution remote sensing images automatically, accurately, and efficiently. Based on a semantic segmentation model with an encoder-decoder structure, a gated fusion module was introduced to address the problem that small photovoltaic panels are difficult to identify. Further, to solve the problems of blurred edges in the segmentation results and that adjacent photovoltaic panels can easily be adhered, this work combines an edge detection network and a semantic segmentation network for multi-task learning to extract the boundaries of photovoltaic panels in a refined manner. Comparative experiments conducted on the Duke California Solar Array data set and a self-constructed Shanghai Distributed Photovoltaic Power Station data set show that, compared with SegNet, LinkNet, UNet, and FPN, the proposed method obtained the highest identification accuracy on both data sets, and its F1-scores reached 84.79% and 94.03%, respectively. These results indicate that effectively combining multi-layer features with a gated fusion module and introducing an edge detection network to refine the segmentation improves the accuracy of distributed photovoltaic power station identification.

Marine raft aquaculture (MFA) plays an important role in the marine economy and ecosystem. With the characteristics of covering a large area and being sparsely distributed in sea area, MFA monitoring suffers from the low efficiency of field survey and poor data of optical satellite imagery. Synthetic aperture radar (SAR) satellite imagery is currently considered to be an effective data source, while the state-of-the-art methods require manual parameter tuning under the guidance of professional experience. To preclude the limitation, this paper proposes a segmentation network combined with nonsubsampled contourlet transform (NSCT) to extract MFA areas using Sentinel-1 images. The proposed method is highlighted by several improvements based on the feature analysis of MFA. First, the NSCT was applied to enhance the contour and orientation features. Second, multiscale and asymmetric convolutions were introduced to fit the multisize and strip-like features more effectively. Third, both channel and spatial attention modules were adopted in the network architecture to overcome the problems of boundary fuzziness and area incompleteness. Experiments showed that the method can effectively extract marine raft culture areas. Although further research is needed to overcome the problem of interference caused by excessive waves, this paper provides a promising approach for periodical monitoring MFA in a large area with high efficiency and acceptable accuracy.

Large-scale and periodic remote sensing monitoring of marine raft aquaculture areas is significant for scientific planning of their layout and for promoting sustainable development of marine ecology. Synthetic aperture radar (SAR) is an important tool for stable monitoring of marine raft aquaculture areas since it is all-weather, all-day, and cloud-penetrating. However, the scattering signal of marine raft aquaculture areas is affected by speckle noise and sea state, so their features in SAR images are complex. Thus, it is challenging to extract marine raft aquaculture areas from SAR images. In this paper, we propose a method to extract marine raft aquaculture areas from Sentinel-1 images based on the analysis of the features for marine raft aquaculture areas. First, the data are preprocessed using multitemporal phase synthesis to weaken the noise interference, enhance the signal of marine raft aquaculture areas, and improve the significance of the characteristics of raft aquaculture areas. Second, the geometric features of the marine raft aquaculture area are combined to design the model structure and introduce the shape constraint module, which adds a priori knowledge to guide the model convergence direction during the training process. Experiments verify that the method outperforms the popular semantic segmentation model with an F1 of 84.52%.