Next Article in Journal
Simultaneous Floating-Base Estimation of Human Kinematics and Joint Torques
Previous Article in Journal
Receiver-Side TCP Countermeasure in Cellular Networks
Open AccessArticle

Land Use Classification of the Deep Convolutional Neural Network Method Reducing the Loss of Spatial Features

by Xuedong Yao 1, Hui Yang 2,*, Yanlan Wu 1,3,*, Penghai Wu 1,3,4, Biao Wang 1,3, Xinxin Zhou 1 and Shuai Wang 5
1
School of Resources and Environmental Engineering, Anhui University, Hefei 230601, China
2
Institute of Physical Science and Information Technology, Anhui University, Hefei 230601, China
3
Anhui Engineering Research Center for Geographical Information Intelligent Technology, Hefei 230601, China
4
Key Laboratory of Ecological Protection and Restoration of Wetland in Anhui Province, Anhui University, Hefei 230601, China
5
School of Resource and Environmental Science, Wuhan University, Wuhan 430079, China
*
Authors to whom correspondence should be addressed.
Sensors 2019, 19(12), 2792; https://doi.org/10.3390/s19122792
Received: 7 May 2019 / Revised: 3 June 2019 / Accepted: 19 June 2019 / Published: 21 June 2019
(This article belongs to the Section Remote Sensors, Control, and Telemetry)
Land use classification is a fundamental task of information extraction from remote sensing imagery. Semantic segmentation based on deep convolutional neural networks (DCNNs) has shown outstanding performance in this task. However, these methods are still affected by the loss of spatial features. In this study, we proposed a new network, called the dense-coordconv network (DCCN), to reduce the loss of spatial features and strengthen object boundaries. In this network, the coordconv module is introduced into the improved DenseNet architecture to improve spatial information by putting coordinate information into feature maps. The proposed DCCN achieved an obvious performance in terms of the public ISPRS (International Society for Photogrammetry and Remote Sensing) 2D semantic labeling benchmark dataset. Compared with the results of other deep convolutional neural networks (U-net, SegNet, Deeplab-V3), the results of the DCCN method improved a lot and the OA (overall accuracy) and mean F1 score reached 89.48% and 86.89%, respectively. This indicates that the DCCN method can effectively reduce the loss of spatial features and improve the accuracy of semantic segmentation in high resolution remote sensing imagery. View Full-Text
Keywords: remote sensing; semantic segmentation; DCNNs; coordconv; ISPRS; high resolution remote sensing; semantic segmentation; DCNNs; coordconv; ISPRS; high resolution
Show Figures

Figure 1

MDPI and ACS Style

Yao, X.; Yang, H.; Wu, Y.; Wu, P.; Wang, B.; Zhou, X.; Wang, S. Land Use Classification of the Deep Convolutional Neural Network Method Reducing the Loss of Spatial Features. Sensors 2019, 19, 2792.

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