Target Detection Adapting to Spectral Variability in Multi-Temporal Hyperspectral Images Using Implicit Contrastive Learning
Remote Sensing · 18.02.2024 · 16 (4) · 718
DOI: 10.3390/rs16040718 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 18.02.2024. Verfasst von Xiaodian Zhang und 7 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Ministry of China, National Natural Science Foundation of China.
Abstract (Originalsprache)
Hyperspectral target detection (HTD) is a crucial aspect of remote sensing applications, aiming to identify targets in hyperspectral images (HSIs) based on their known prior spectral signatures. However, the spectral variability resulting from various imaging conditions in multi-temporal hyperspectral images poses a challenge to both classical and deep learning (DL) methods. To overcome the limitations imposed by spectral variability, an implicit contrastive learning-based target detector (ICLTD) is proposed to exploit in-scene spectra in an unsupervised way. First, only prior spectra are utilized for explicit supervision, while an implicit contrastive learning module (ICLM) is designed to normalize the feature distributions of prior and in-scene spectra. This paper theoretically demonstrates that the ICLM can transfer the gradients from prior spectral features to those of in-scene spectra based on their feature similarities and differences. Because of transferred gradient signals, the ICLTD is regularized to extract similar representations for the prior and in-scene target spectra, while augmenting feature differences between the target and background spectra. Additionally, a local spectral similarity constraint (LSSC) is proposed to enhance the capability of scene adaptation by leveraging the spectral similarities among in-scene targets. To validate the performance of the ICLTD under spectral variability, multi-temporal HSIs captured under various imaging conditions are collected to generate prior spectra and in-scene spectra. Comparative evaluations against several DL detectors and classical methods reveal the superior performance of the ICLTD in achieving a balance between target detectability and background suppressibility under spectral variability.
Förderung
- Science and Technology Ministry of China
- National Natural Science Foundation of China
Zitieren
APA
Zhang, X., Gao, K., Wang, J., Wang, P., Hu, Z., Yang, Z., Zhao, X., & Li, W. (2024). Target Detection Adapting to Spectral Variability in Multi-Temporal Hyperspectral Images Using Implicit Contrastive Learning. Remote Sensing, 16(4), 718. https://doi.org/10.3390/rs16040718
Vancouver
Zhang X, Gao K, Wang J, Wang P, Hu Z, Yang Z, et al. Target Detection Adapting to Spectral Variability in Multi-Temporal Hyperspectral Images Using Implicit Contrastive Learning. Remote Sensing. 2024;16(4):718. doi:10.3390/rs16040718
BibTeX
@article{Zhang2024,
author = {Zhang, Xiaodian and Gao, Kun and Wang, Junwei and Wang, Pengyu and Hu, Zibo and Yang, Zhijia and Zhao, Xiaobin and Li, Wei},
title = {Target Detection Adapting to Spectral Variability in Multi-Temporal Hyperspectral Images Using Implicit Contrastive Learning},
journal = {Remote Sensing},
year = {2024},
volume = {16},
number = {4},
pages = {718},
doi = {10.3390/rs16040718}
}
EUVIMED