Next Article in Journal
Railway Ballast Monitoring by GPR: A Test-Site Investigation
Previous Article in Journal
A Filter for SAR Image Despeckling Using Pre-Trained Convolutional Neural Network Model
Previous Article in Special Issue
WorldView-2 Data for Hierarchical Object-Based Urban Land Cover Classification in Kigali: Integrating Rule-Based Approach with Urban Density and Greenness Indices
Open AccessArticle

DE-Net: Deep Encoding Network for Building Extraction from High-Resolution Remote Sensing Imagery

by Hao Liu 1,2, Jiancheng Luo 1,2,*, Bo Huang 3, Xiaodong Hu 1, Yingwei Sun 1,2, Yingpin Yang 1,2, Nan Xu 1,2 and Nan Zhou 1,2
1
Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100101, China
2
University of Chinese Academy of Sciences, Beijing 100049, China
3
Department of Geography and Resource Management, The Chinese University of Hong Kong, Hong Kong 999077, China
*
Author to whom correspondence should be addressed.
Remote Sens. 2019, 11(20), 2380; https://doi.org/10.3390/rs11202380
Received: 30 August 2019 / Revised: 7 October 2019 / Accepted: 11 October 2019 / Published: 14 October 2019
Deep convolutional neural networks have promoted significant progress in building extraction from high-resolution remote sensing imagery. Although most of such work focuses on modifying existing image segmentation networks in computer vision, we propose a new network in this paper, Deep Encoding Network (DE-Net), that is designed for the very problem based on many lately introduced techniques in image segmentation. Four modules are used to construct DE-Net: the inception-style downsampling modules combining a striding convolution layer and a max-pooling layer, the encoding modules comprising six linear residual blocks with a scaled exponential linear unit (SELU) activation function, the compressing modules reducing the feature channels, and a densely upsampling module that enables the network to encode spatial information inside feature maps. Thus, DE-Net achieves state-of-the-art performance on the WHU Building Dataset in recall, F1-Score, and intersection over union (IoU) metrics without pre-training. It also outperformed several segmentation networks in our self-built Suzhou Satellite Building Dataset. The experimental results validate the effectiveness of DE-Net on building extraction from aerial imagery and satellite imagery. It also suggests that given enough training data, designing and training a network from scratch may excel fine-tuning models pre-trained on datasets unrelated to building extraction. View Full-Text
Keywords: building extraction; deep learning; fully convolutional network; high-resolution remote sensing imagery building extraction; deep learning; fully convolutional network; high-resolution remote sensing imagery
Show Figures

Graphical abstract

MDPI and ACS Style

Liu, H.; Luo, J.; Huang, B.; Hu, X.; Sun, Y.; Yang, Y.; Xu, N.; Zhou, N. DE-Net: Deep Encoding Network for Building Extraction from High-Resolution Remote Sensing Imagery. Remote Sens. 2019, 11, 2380.

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 by Country/Region

1
Back to TopTop