Next Article in Journal
Automatic Bluefin Tuna Sizing with a Combined Acoustic and Optical Sensor
Previous Article in Journal
Ultrasonic Guided Wave Testing on Cross-Ply Composite Laminate: An Empirical Study
Previous Article in Special Issue
Computer Vision System for Welding Inspection of Liquefied Petroleum Gas Pressure Vessels Based on Combined Digital Image Processing and Deep Learning Techniques
Open AccessArticle

NAS-HRIS: Automatic Design and Architecture Search of Neural Network for Semantic Segmentation in Remote Sensing Images

1
College of Information and Computer Engineering, Northeast Forestry University, Harbin 150040, China
2
College of Computer Science and Engineering, Xi’an University of Technology, Xi’an 710048, China
3
Faculty of Applied Mathematics, Silesian University of Technology, 44-100 Gliwice, Poland
4
Department of Applied Informatics, Vytautas Magnus University, 44404 Kaunas, Lithuania
*
Author to whom correspondence should be addressed.
Sensors 2020, 20(18), 5292; https://doi.org/10.3390/s20185292
Received: 20 July 2020 / Revised: 5 September 2020 / Accepted: 14 September 2020 / Published: 16 September 2020
(This article belongs to the Special Issue Computer Vision for Remote Sensing and Infrastructure Inspection)
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. View Full-Text
Keywords: deep learning; high-resolution remote sensing; image segmentation; neural architecture search; neural network optimisation; urban monitoring deep learning; high-resolution remote sensing; image segmentation; neural architecture search; neural network optimisation; urban monitoring
Show Figures

Figure 1

MDPI and ACS Style

Zhang, M.; Jing, W.; Lin, J.; Fang, N.; Wei, W.; Woźniak, M.; Damaševičius, R. NAS-HRIS: Automatic Design and Architecture Search of Neural Network for Semantic Segmentation in Remote Sensing Images. Sensors 2020, 20, 5292.

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
Search more from Scilit
 
Search
Back to TopTop