Urban building segmentation is a prevalent research domain for very high resolution (VHR) remote sensing; however, various appearances and complicated background of VHR remote sensing imagery make accurate semantic segmentation of urban buildings a challenge in relevant applications. Following the basic architecture of U-Net, an end-to-end deep convolutional neural network (denoted as DeepResUnet) was proposed, which can effectively perform urban building segmentation at pixel scale from VHR imagery and generate accurate segmentation results. The method contains two sub-networks: One is a cascade down-sampling network for extracting feature maps of buildings from the VHR image, and the other is an up-sampling network for reconstructing those extracted feature maps back to the same size of the input VHR image. The deep residual learning approach was adopted to facilitate training in order to alleviate the degradation problem that often occurred in the model training process. The proposed DeepResUnet was tested with aerial images with a spatial resolution of 0.075 m and was compared in performance under the exact same conditions with six other state-of-the-art networks—FCN-8s, SegNet, DeconvNet, U-Net, ResUNet and DeepUNet. Results of extensive experiments indicated that the proposed DeepResUnet outperformed the other six existing networks in semantic segmentation of urban buildings in terms of visual and quantitative evaluation, especially in labeling irregular-shape and small-size buildings with higher accuracy and entirety. Compared with the U-Net, the F1 score, Kappa coefficient and overall accuracy of DeepResUnet were improved by 3.52%, 4.67% and 1.72%, respectively. Moreover, the proposed DeepResUnet required much fewer parameters than the U-Net, highlighting its significant improvement among U-Net applications. Nevertheless, the inference time of DeepResUnet is slightly longer than that of the U-Net, which is subject to further improvement.

Geospatial data sharing is a concern in geospatial science because of the heterogeneity of existing geographical information systems. This study aims to examine the use of Geospatial Semantic Web technologies such as ontology web services and the service‐oriented architecture for enabling disparate heterogeneous legacy GIS to share and integrate information in a cost effective way to reduce spatial data duplication. A framework based on the Geospatial Semantic Web technologies is proposed in this study. Experimental results from an implemented prototype show that the proposed framework allows searching and accessing geospatial data and services at the semantic level based on their content instead of keywords in the metadata.

While OGC’s WFS facilitates disseminating heterogeneous spatial data over the Web and allows feature-level geospatial information sharing and synchronization, performance issues challenge the efficient and effective utilization of WFS for disaster response. Literature shows that obtaining spatial information becomes very slow when querying WFS systems from large geospatial databases over the Internet. Solutions on how to improve the WFS system performance so that spatial data can be delivered to disaster responders within a reasonable amount of time are needed. This paper proposes a parallel approach based on Voronoi diagram indexing and data/task parallelism for improving the query performance of WFS systems for disaster applications. Experimental results show that the parallel approach can significantly improve the response time needed to process the spatial queries from a massive volume of spatial data for disaster response.