A New Hyperspectral Image Identification Method Based on LSDA and OSELM

To solve the problems of information loss and nonlinear transformation of hyperspectral image dimensionality reduction methods and the problem that recognition methods are sensitive to noise and cannot be trained online, a new hyperspectral image identification method based on locality sensitive dis...

Full description

Saved in:
Bibliographic Details
Main Authors: Chengjiang Zhou, Mingli Yang, Sasa Duan, Lu Shao, Zhilin Zhang, Yunfei Liu
Format: Article
Language:English
Published: Wiley 2024-01-01
Series:Modelling and Simulation in Engineering
Online Access:http://dx.doi.org/10.1155/2024/1296492
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849765514468917248
author Chengjiang Zhou
Mingli Yang
Sasa Duan
Lu Shao
Zhilin Zhang
Yunfei Liu
author_facet Chengjiang Zhou
Mingli Yang
Sasa Duan
Lu Shao
Zhilin Zhang
Yunfei Liu
author_sort Chengjiang Zhou
collection DOAJ
description To solve the problems of information loss and nonlinear transformation of hyperspectral image dimensionality reduction methods and the problem that recognition methods are sensitive to noise and cannot be trained online, a new hyperspectral image identification method based on locality sensitive discriminant analysis (LSDA) and online sequential extreme learning machine (OSELM) is proposed. Firstly, LSDA is used to reduce the redundant information and data noise, and the local structure and discriminant information of the hyperspectral image are extracted on the basis of reducing the data dimension. Then, a real-time recognition model based on OSELM is constructed to identify various terrain targets in hyperspectral images through online real-time updates of data. According to the experimental results of the Pavia University dataset and Salinas dataset, the proposed LSDA-OSELM not only achieved the maximum overall accuracy (OA) of 97.56 and 97.88 but also obtained the maximum kappa coefficient of 0.9726 and 0.9774. Compared with several new dimensionality reduction methods and identification methods, the proposed LSDA-OSELM has achieved a leading position in both OA and kappa indicators. The proposed method improves the generalization ability and accuracy of hyperspectral image target recognition models. In the future, its computational complexity and parameter robustness are expected to be further improved and applied in practical application scenarios.
format Article
id doaj-art-c2a1b241a3a34833bcd6d1c5ba4c90c8
institution DOAJ
issn 1687-5605
language English
publishDate 2024-01-01
publisher Wiley
record_format Article
series Modelling and Simulation in Engineering
spelling doaj-art-c2a1b241a3a34833bcd6d1c5ba4c90c82025-08-20T03:04:50ZengWileyModelling and Simulation in Engineering1687-56052024-01-01202410.1155/2024/1296492A New Hyperspectral Image Identification Method Based on LSDA and OSELMChengjiang Zhou0Mingli Yang1Sasa Duan2Lu Shao3Zhilin Zhang4Yunfei Liu5School of Information Science and TechnologyBeijing CCID Industry and Information Engineering Supervision Center Co. Ltd.School of Information Science and TechnologySchool of Information Science and TechnologySchool of Information Science and TechnologySchool of Information Science and TechnologyTo solve the problems of information loss and nonlinear transformation of hyperspectral image dimensionality reduction methods and the problem that recognition methods are sensitive to noise and cannot be trained online, a new hyperspectral image identification method based on locality sensitive discriminant analysis (LSDA) and online sequential extreme learning machine (OSELM) is proposed. Firstly, LSDA is used to reduce the redundant information and data noise, and the local structure and discriminant information of the hyperspectral image are extracted on the basis of reducing the data dimension. Then, a real-time recognition model based on OSELM is constructed to identify various terrain targets in hyperspectral images through online real-time updates of data. According to the experimental results of the Pavia University dataset and Salinas dataset, the proposed LSDA-OSELM not only achieved the maximum overall accuracy (OA) of 97.56 and 97.88 but also obtained the maximum kappa coefficient of 0.9726 and 0.9774. Compared with several new dimensionality reduction methods and identification methods, the proposed LSDA-OSELM has achieved a leading position in both OA and kappa indicators. The proposed method improves the generalization ability and accuracy of hyperspectral image target recognition models. In the future, its computational complexity and parameter robustness are expected to be further improved and applied in practical application scenarios.http://dx.doi.org/10.1155/2024/1296492
spellingShingle Chengjiang Zhou
Mingli Yang
Sasa Duan
Lu Shao
Zhilin Zhang
Yunfei Liu
A New Hyperspectral Image Identification Method Based on LSDA and OSELM
Modelling and Simulation in Engineering
title A New Hyperspectral Image Identification Method Based on LSDA and OSELM
title_full A New Hyperspectral Image Identification Method Based on LSDA and OSELM
title_fullStr A New Hyperspectral Image Identification Method Based on LSDA and OSELM
title_full_unstemmed A New Hyperspectral Image Identification Method Based on LSDA and OSELM
title_short A New Hyperspectral Image Identification Method Based on LSDA and OSELM
title_sort new hyperspectral image identification method based on lsda and oselm
url http://dx.doi.org/10.1155/2024/1296492
work_keys_str_mv AT chengjiangzhou anewhyperspectralimageidentificationmethodbasedonlsdaandoselm
AT mingliyang anewhyperspectralimageidentificationmethodbasedonlsdaandoselm
AT sasaduan anewhyperspectralimageidentificationmethodbasedonlsdaandoselm
AT lushao anewhyperspectralimageidentificationmethodbasedonlsdaandoselm
AT zhilinzhang anewhyperspectralimageidentificationmethodbasedonlsdaandoselm
AT yunfeiliu anewhyperspectralimageidentificationmethodbasedonlsdaandoselm
AT chengjiangzhou newhyperspectralimageidentificationmethodbasedonlsdaandoselm
AT mingliyang newhyperspectralimageidentificationmethodbasedonlsdaandoselm
AT sasaduan newhyperspectralimageidentificationmethodbasedonlsdaandoselm
AT lushao newhyperspectralimageidentificationmethodbasedonlsdaandoselm
AT zhilinzhang newhyperspectralimageidentificationmethodbasedonlsdaandoselm
AT yunfeiliu newhyperspectralimageidentificationmethodbasedonlsdaandoselm