Double Deep Q-Network for Hyperspectral Image Band Selection in Land Cover Classification Applications
-
Published:2023-01-23
Issue:3
Volume:15
Page:682
-
ISSN:2072-4292
-
Container-title:Remote Sensing
-
language:en
-
Short-container-title:Remote Sensing
Author:
Yang Hua1, Chen Ming1ORCID, Wu Guowen2, Wang Jiali1ORCID, Wang Yingxi1, Hong Zhonghua1ORCID
Affiliation:
1. College of Information, Shanghai Ocean University, 999 Hucheng Huanlu, Shanghai 201308, China 2. School of Computer Science and Technology, Donghua University, 2999 North Renmin Road, Shanghai 201620, China
Abstract
Hyperspectral data usually consists of hundreds of narrow spectral bands and provides more detailed spectral characteristics compared to commonly used multispectral data in remote sensing applications. However, highly correlated spectral bands in hyperspectral data lead to computational complexity, which limits many applications or traditional methods when applied to hyperspectral data. The dimensionality reduction of hyperspectral data becomes one of the most important pre-processing steps in hyperspectral data analysis. Recently, deep reinforcement learning (DRL) has been introduced to hyperspectral data band selection (BS); however, the current DRL methods for hyperspectral data BS simply remove redundant bands, lack the significance analysis for the selected bands, and the reward mechanisms used in DRL only take basic forms in general. In this paper, a new reward mechanism strategy has been proposed, and Double Deep Q-Network (DDQN) is introduced during BS using DRL to improve the network stabilities and avoid local optimum. To verify the effect of the proposed BS method, land cover classification experiments were designed and carried out to analyze and compare the proposed method with other BS methods. In the land cover classification experiments, the overall accuracy (OA) of the proposed method can reach 98.37%, the average accuracy (AA) is 95.63%, the kappa coefficient (Kappa) is 97.87%. Overall, the proposed method is superior to other BS methods. Experiments have also shown that the proposed method works not only for airborne hyperspectral data (AVIRIS and HYDICE), but also for hyperspectral satellite data, such as PRISMA data. When hyperspectral data is applied to similar applications, the proposed BS method could be a candidate for the BS preprocessing options.
Funder
Shanghai Science and Technology Innovation Action Planning
Subject
General Earth and Planetary Sciences
Reference55 articles.
1. Mechanical Structure Design for Hyperspectral Imager of HJ-1A Satellite;Yan;Spacecr. Eng.,2009 2. The First Two Satellites OVS-1A/1B of Zhuhai-1 Remote-sensing Micro/Nano Satellites Constellation Launched Successfully;Zhan;Space Int.,2017 3. Gaofen 5 and Gaofen 6 Satellites Put into Operation;Shanshan;Aerosp. China,2019 4. Kerr, G., Avbelj, J., Carmona, E., Eckardt, A., Gerasch, B., Graham, L., Günther, B., Heiden, U., Krutz, D., and Krawczyk, H. (2016, January 10–15). The hyperspectral sensor DESIS on MUSES: Processing and applications. Proceedings of the 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Beijing, China. 5. Pignatti, S., Palombo, A., Pascucci, S., Romano, F., Santini, F., Simoniello, T., Umberto, A., Vincenzo, C., Acito, N., and Diani, M. (2013, January 21–26). The PRISMA hyperspectral mission: Science activities and opportunities for agriculture and land monitoring. Proceedings of the 2013 IEEE International Geoscience and Remote Sensing Symposium-IGARSS, Melbourne, VIC, Australia.
Cited by
7 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|