Search

With the rapid development of the energy industry and the growth of the global energy demand in recent years, the development of the photovoltaic industry has become increasingly significant. However, the development of the PV industry is constrained by high land costs, and land in central cities and industrial areas is often very expensive and unsuitable for the installation of PV equipment in large areas. With this background knowledge, the key to evaluating the PV potential is by counting the rooftop information of buildings, and an ideal solution for extracting building rooftop information is from remote sensing satellite images using the deep learning method; however, the deep learning method often requires large-scale labeled samples, and the labeling of remote sensing images is often time-consuming and expensive. To reduce the burden of data labeling, models trained on large datasets can be used as pre-trained models (e.g., ImageNet) to provide prior knowledge for training. However, most of the existing pre-trained model parameters are not suitable for direct transfer to remote sensing tasks. In this paper, we design a pseudo-label-guided self-supervised learning (PGSSL) semantic segmentation network structure based on high-resolution remote sensing images to extract building information. The pseudo-label-guided learning method allows the feature results extracted by the pretext task to be more applicable to the target task and ultimately improves segmentation accuracy. Our proposed method achieves better results than current contrastive learning methods in most experiments and uses only about 20–50% of the labeled data to achieve comparable performance with random initialization. In addition, a more accurate statistical method for building density distribution is designed based on the semantic segmentation results. This method addresses the last step of the extraction results oriented to the PV potential assessment, and this paper is validated in Beijing, China, to demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Advanced techniques of multi-temporal InSAR (MT-InSAR) represent a valuable tool in ground subsidence studies allowing remote investigation of the behavior of mass movements in long time intervals by using large datasets of SAR images covering the same area and acquired at different epochs. The settlement in Beijing is very serious, producing adverse environmental impacts. Excessive groundwater withdrawal is the most direct cause of land subsidence.In this paper, a spatial-temporal analysis of the land subsidence in Beijing was performed using one of the MT-InSAR techniques, referred to as Small Baseline Subset (SBAS). This technique allows monitoring the temporal evolution of a deformation phenomenon, via the generation of mean deformation velocity maps and displacement time series from a data set of acquired SAR images. 52 C-band ENVISAT ASAR images acquired from June 2003 to August 2010 were used to produce a linear deformation rate map and to derive time series of ground deformation. The results show that there are three large subsidence funnels within this study area, which separately located in Balizhuang-Dajiaoting in Chaoyang district, Wangjing-Laiguangying Chaoyang district, Gaoliying Shunyi district. The maximum settlement center is Wangsiying-Tongzhou along the Beijing express; the subsidence velocity exceeds 110 mm/y in the LOS direction. In particular, we compared the achieved results with leveling measurements that are assumed as reference. The estimated long-term subsidence results obtained by SBAS approach agree well with the development of the over-exploitation of ground water, indicating that SBAS techniques is adequate for the retrieval of land subsidence in Beijing from multi-temporal SAR data. [ABSTRACT FROM AUTHOR]

The segmentation of high-resolution (HR) remote sensing images is very important in modern society, especially in the fields of industry, agriculture and urban modelling. Through the neural network, the machine can effectively and accurately extract the surface feature information. However, using the traditional deep learning methods requires plentiful efforts in order to find a robust architecture. In this paper, we introduce a neural network architecture search (NAS) method, called NAS-HRIS, which can automatically search neural network architecture on the dataset. The proposed method embeds a directed acyclic graph (DAG) into the search space and designs the differentiable searching process, which enables it to learn an end-to-end searching rule by using gradient descent optimization. It uses the Gumbel-Max trick to provide an efficient way when drawing samples from a non-continuous probability distribution, and it improves the efficiency of searching and reduces the memory consumption. Compared with other NAS, NAS-HRIS consumes less GPU memory without reducing the accuracy, which corresponds to a large amount of HR remote sensing imagery data. We have carried out experiments on the WHUBuilding dataset and achieved 90.44% MIoU. In order to fully demonstrate the feasibility of the method, we made a new urban Beijing Building dataset, and conducted experiments on satellite images and non-single source images, achieving better results than SegNet, U-Net and Deeplab v3+ models, while the computational complexity of our network architecture is much smaller. [ABSTRACT FROM AUTHOR]