SVHAE: Spectral Variability-Aware Hybrid Autoencoder for Hyperspectral Underwater Target Detection

Hyperspectral imaging (HSI) has evolved as an important tool for many applications, including remote sensing, crime investigation, target detection, disease diagnosis, and anomaly detection. Among these, hyperspectral underwater target detection (HUTD) presents unique challenges due to spectral dist...

Full description

Saved in:
Bibliographic Details
Main Authors: Suresh Aala, Sravan Kumar Sikhakolli, Sunil Chinnadurai, Anuj Deshpande, Karthikeyan Elumalai, Md. Abdul Latif Sarker, Hala Mostafa
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11075652/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849713168139419648
author Suresh Aala
Sravan Kumar Sikhakolli
Sunil Chinnadurai
Anuj Deshpande
Karthikeyan Elumalai
Md. Abdul Latif Sarker
Hala Mostafa
author_facet Suresh Aala
Sravan Kumar Sikhakolli
Sunil Chinnadurai
Anuj Deshpande
Karthikeyan Elumalai
Md. Abdul Latif Sarker
Hala Mostafa
author_sort Suresh Aala
collection DOAJ
description Hyperspectral imaging (HSI) has evolved as an important tool for many applications, including remote sensing, crime investigation, target detection, disease diagnosis, and anomaly detection. Among these, hyperspectral underwater target detection (HUTD) presents unique challenges due to spectral distortions caused by water absorption and scattering. Conventional methods often struggle with spectral variability, complicating detection accuracy. This paper introduces spectral variability-aware hybrid autoencoder (SVHAE) for HUTD, a novel autoencoder-based unmixing network incorporating parallel linear and nonlinear decoders to improve underwater target detection. Our method effectively reduces the effect of spectral distortions and addresses variability using a combined loss function integrating Kullback-Leibler divergence, mean squared error, and spectral angle distance. Experimental validation on real-world and simulated datasets demonstrates that our proposed SVHAE outperformed state-of-the-art methods by achieving superior AUC values. These advancements contribute to the progressing field of HUTD, making the way for robust solutions in marine exploration and detecting targets under the water.
format Article
id doaj-art-a92895e00cf54e1eaa29e02159018e8a
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-a92895e00cf54e1eaa29e02159018e8a2025-08-20T03:14:02ZengIEEEIEEE Access2169-35362025-01-011312916112917110.1109/ACCESS.2025.358743811075652SVHAE: Spectral Variability-Aware Hybrid Autoencoder for Hyperspectral Underwater Target DetectionSuresh Aala0https://orcid.org/0000-0002-3110-5062Sravan Kumar Sikhakolli1https://orcid.org/0000-0002-4887-997XSunil Chinnadurai2https://orcid.org/0000-0002-7464-1578Anuj Deshpande3https://orcid.org/0000-0002-7415-1691Karthikeyan Elumalai4Md. Abdul Latif Sarker5https://orcid.org/0000-0001-7911-3689Hala Mostafa6https://orcid.org/0000-0002-7388-8990Department of Electronics and Communication Engineering, School of Engineering and Sciences, SRM University-AP, Amaravati, IndiaDepartment of Electronics and Communication Engineering, School of Engineering and Sciences, SRM University-AP, Amaravati, IndiaDepartment of Electronics and Communication Engineering, School of Engineering and Sciences, SRM University-AP, Amaravati, IndiaDepartment of Electronics and Communication Engineering, School of Engineering and Sciences, SRM University-AP, Amaravati, IndiaDepartment of Electronics and Communication Engineering, School of Engineering and Sciences, SRM University-AP, Amaravati, IndiaDepartment of Electronics and Information Engineering, Jeonbuk National University, Jeonju, South KoreaDepartment of Information Technology, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh, Saudi ArabiaHyperspectral imaging (HSI) has evolved as an important tool for many applications, including remote sensing, crime investigation, target detection, disease diagnosis, and anomaly detection. Among these, hyperspectral underwater target detection (HUTD) presents unique challenges due to spectral distortions caused by water absorption and scattering. Conventional methods often struggle with spectral variability, complicating detection accuracy. This paper introduces spectral variability-aware hybrid autoencoder (SVHAE) for HUTD, a novel autoencoder-based unmixing network incorporating parallel linear and nonlinear decoders to improve underwater target detection. Our method effectively reduces the effect of spectral distortions and addresses variability using a combined loss function integrating Kullback-Leibler divergence, mean squared error, and spectral angle distance. Experimental validation on real-world and simulated datasets demonstrates that our proposed SVHAE outperformed state-of-the-art methods by achieving superior AUC values. These advancements contribute to the progressing field of HUTD, making the way for robust solutions in marine exploration and detecting targets under the water.https://ieeexplore.ieee.org/document/11075652/Hyperspectral imagingunderwater target detectionparallel spectral unmixinglinear unmixingnonlinear unmixingremote sensing
spellingShingle Suresh Aala
Sravan Kumar Sikhakolli
Sunil Chinnadurai
Anuj Deshpande
Karthikeyan Elumalai
Md. Abdul Latif Sarker
Hala Mostafa
SVHAE: Spectral Variability-Aware Hybrid Autoencoder for Hyperspectral Underwater Target Detection
IEEE Access
Hyperspectral imaging
underwater target detection
parallel spectral unmixing
linear unmixing
nonlinear unmixing
remote sensing
title SVHAE: Spectral Variability-Aware Hybrid Autoencoder for Hyperspectral Underwater Target Detection
title_full SVHAE: Spectral Variability-Aware Hybrid Autoencoder for Hyperspectral Underwater Target Detection
title_fullStr SVHAE: Spectral Variability-Aware Hybrid Autoencoder for Hyperspectral Underwater Target Detection
title_full_unstemmed SVHAE: Spectral Variability-Aware Hybrid Autoencoder for Hyperspectral Underwater Target Detection
title_short SVHAE: Spectral Variability-Aware Hybrid Autoencoder for Hyperspectral Underwater Target Detection
title_sort svhae spectral variability aware hybrid autoencoder for hyperspectral underwater target detection
topic Hyperspectral imaging
underwater target detection
parallel spectral unmixing
linear unmixing
nonlinear unmixing
remote sensing
url https://ieeexplore.ieee.org/document/11075652/
work_keys_str_mv AT sureshaala svhaespectralvariabilityawarehybridautoencoderforhyperspectralunderwatertargetdetection
AT sravankumarsikhakolli svhaespectralvariabilityawarehybridautoencoderforhyperspectralunderwatertargetdetection
AT sunilchinnadurai svhaespectralvariabilityawarehybridautoencoderforhyperspectralunderwatertargetdetection
AT anujdeshpande svhaespectralvariabilityawarehybridautoencoderforhyperspectralunderwatertargetdetection
AT karthikeyanelumalai svhaespectralvariabilityawarehybridautoencoderforhyperspectralunderwatertargetdetection
AT mdabdullatifsarker svhaespectralvariabilityawarehybridautoencoderforhyperspectralunderwatertargetdetection
AT halamostafa svhaespectralvariabilityawarehybridautoencoderforhyperspectralunderwatertargetdetection