Next Article in Journal
Ice Production in Ross Ice Shelf Polynyas during 2017–2018 from Sentinel–1 SAR Images
Previous Article in Journal
Combining Genetic Analysis and Multivariate Modeling to Evaluate Spectral Reflectance Indices as Indirect Selection Tools in Wheat Breeding under Water Deficit Stress Conditions
Previous Article in Special Issue
Fusing China GF-5 Hyperspectral Data with GF-1, GF-2 and Sentinel-2A Multispectral Data: Which Methods Should Be Used?
Article

HTD-Net: A Deep Convolutional Neural Network for Target Detection in Hyperspectral Imagery

1
College of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China
2
School of Information and Electronics, Beijing Institute of Technology, Beijing 100081, China
3
Department of Electrical and Computer Engineering, Mississippi State University, Starkville, MS 39762, USA
*
Author to whom correspondence should be addressed.
Received: 26 March 2020 / Revised: 2 May 2020 / Accepted: 3 May 2020 / Published: 7 May 2020
(This article belongs to the Special Issue Advanced Techniques for Spaceborne Hyperspectral Remote Sensing)
In recent years, deep learning has dramatically improved the cognitive ability of the network by extracting depth features, and has been successfully applied in the field of feature extraction and classification of hyperspectral images. However, it is facing great difficulties for target detection due to extremely limited available labeled samples that are insufficient to train deep networks. In this paper, a novel target detection framework for deep learning is proposed, denoted as HTD-Net. To overcome the few-training-sample issue, the proposed framework utilizes an improved autoencoder (AE) to generate target signatures, and then finds background samples which differ significantly from target samples based on a linear prediction (LP) strategy. Then, the obtained target and background samples are used to enlarge the training set by generating pixel-pairs, which is viewed as the input of a pre-designed network architecture to learn discriminative similarity. During testing, pixel-pairs of a pixel to be labeled are constructed with both available target samples and background samples. Spectral difference between these pixel-pairs is classified by the well-trained network with results of similarity measurement. The outputs from a two-branch averaged similarity scores are combined to generate the final detection. Experimental results with several real hyperspectral data demonstrate the superiority of the proposed algorithm compared to some traditional target detectors. View Full-Text
Keywords: hyperspectral imagery; deep learning; convolutional neural network; target detection hyperspectral imagery; deep learning; convolutional neural network; target detection
Show Figures

Graphical abstract

MDPI and ACS Style

Zhang, G.; Zhao, S.; Li, W.; Du, Q.; Ran, Q.; Tao, R. HTD-Net: A Deep Convolutional Neural Network for Target Detection in Hyperspectral Imagery. Remote Sens. 2020, 12, 1489. https://0-doi-org.brum.beds.ac.uk/10.3390/rs12091489

AMA Style

Zhang G, Zhao S, Li W, Du Q, Ran Q, Tao R. HTD-Net: A Deep Convolutional Neural Network for Target Detection in Hyperspectral Imagery. Remote Sensing. 2020; 12(9):1489. https://0-doi-org.brum.beds.ac.uk/10.3390/rs12091489

Chicago/Turabian Style

Zhang, Gaigai, Shizhi Zhao, Wei Li, Qian Du, Qiong Ran, and Ran Tao. 2020. "HTD-Net: A Deep Convolutional Neural Network for Target Detection in Hyperspectral Imagery" Remote Sensing 12, no. 9: 1489. https://0-doi-org.brum.beds.ac.uk/10.3390/rs12091489

Find Other Styles
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