Next Article in Journal
Geodetic Constraints on the Crustal Deformation along the Kunlun Fault and Its Tectonic Implications
Next Article in Special Issue
Web-Net: A Novel Nest Networks with Ultra-Hierarchical Sampling for Building Extraction from Aerial Imageries
Previous Article in Journal
Dust Storm Remote Sensing Monitoring Supported by MODIS Land Surface Reflectance Database
Previous Article in Special Issue
A Building Extraction Approach Based on the Fusion of LiDAR Point Cloud and Elevation Map Texture Features
Open AccessArticle

Semantic Segmentation of Urban Buildings from VHR Remote Sensing Imagery Using a Deep Convolutional Neural Network

1
Key Laboratory of Digital Earth Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, China
2
University of Chinese Academy of Sciences, Beijing 100049, China
3
Department of Geography, University of Connecticut, Storrs, CT 06269, USA
4
Department of Computer Science, University of Wisconsin, Milwaukee, WI 53211, USA
*
Author to whom correspondence should be addressed.
The first two authors are contributed equally to the work presented and are considered as equal first authors of this manuscript.
Remote Sens. 2019, 11(15), 1774; https://doi.org/10.3390/rs11151774
Received: 22 June 2019 / Revised: 22 July 2019 / Accepted: 26 July 2019 / Published: 28 July 2019
(This article belongs to the Special Issue Remote Sensing based Building Extraction)
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. View Full-Text
Keywords: semantic segmentation; urban building extraction; deep convolutional neural network; VHR remote sensing imagery; U-Net semantic segmentation; urban building extraction; deep convolutional neural network; VHR remote sensing imagery; U-Net
Show Figures

Figure 1

MDPI and ACS Style

Yi, Y.; Zhang, Z.; Zhang, W.; Zhang, C.; Li, W.; Zhao, T. Semantic Segmentation of Urban Buildings from VHR Remote Sensing Imagery Using a Deep Convolutional Neural Network. Remote Sens. 2019, 11, 1774.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map

1
Back to TopTop