DEEP-RX FOR HYPERSPECTRAL ANOMALY DETECTION

Yingjie Song; Shuaikai Shi; Jie Chen

doi:10.1109/IGARSS52108.2023.10283137

DEEP-RX FOR HYPERSPECTRAL ANOMALY DETECTION

Yingjie Song
, Shuaikai Shi
, Jie Chen

School of Marine Science and Technology

Northwestern Polytechnical University Xian

Research output: Contribution to conference › Paper › peer-review

14 Scopus citations

Abstract

Hyperspectral anomaly detection is a widely studied topic that has garnered significant attention in recent years. However, designing effective nonlinear detectors remains a challenge for many traditional methods. To address this issue, we propose the integration of a variational autoencoder (VAE) in this paper. The VAE enables efficient feature extraction from hyperspectral images (HSIs) by mapping inputs to latent variables that follow a Gaussian distribution. The resulting latent representations are subsequently passed to the Reed-Xiaoli (RX) detector to obtain the final detection results. Through extensive testing on three real datasets, the detection results demonstrate the superiority of our proposed method.

Original language	English
Pages	7348-7351
Number of pages	4
DOIs	https://doi.org/10.1109/IGARSS52108.2023.10283137
State	Published - 2023
Event	2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023 - Pasadena, United States Duration: 16 Jul 2023 → 21 Jul 2023

Conference

Conference	2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023
Country/Territory	United States
City	Pasadena
Period	16/07/23 → 21/07/23

Keywords

Hyperspectral anomaly detection
RX detector
variational autoencoder (VAE)

Access to Document

10.1109/IGARSS52108.2023.10283137

Cite this

@conference{aab38b6e438141d592df7a2d0b3e938a,

title = "DEEP-RX FOR HYPERSPECTRAL ANOMALY DETECTION",

abstract = "Hyperspectral anomaly detection is a widely studied topic that has garnered significant attention in recent years. However, designing effective nonlinear detectors remains a challenge for many traditional methods. To address this issue, we propose the integration of a variational autoencoder (VAE) in this paper. The VAE enables efficient feature extraction from hyperspectral images (HSIs) by mapping inputs to latent variables that follow a Gaussian distribution. The resulting latent representations are subsequently passed to the Reed-Xiaoli (RX) detector to obtain the final detection results. Through extensive testing on three real datasets, the detection results demonstrate the superiority of our proposed method.",

keywords = "Hyperspectral anomaly detection, RX detector, variational autoencoder (VAE)",

author = "Yingjie Song and Shuaikai Shi and Jie Chen",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023 ; Conference date: 16-07-2023 Through 21-07-2023",

year = "2023",

doi = "10.1109/IGARSS52108.2023.10283137",

language = "英语",

pages = "7348--7351",

}

TY - CONF

T1 - DEEP-RX FOR HYPERSPECTRAL ANOMALY DETECTION

AU - Song, Yingjie

AU - Shi, Shuaikai

AU - Chen, Jie

PY - 2023

Y1 - 2023

N2 - Hyperspectral anomaly detection is a widely studied topic that has garnered significant attention in recent years. However, designing effective nonlinear detectors remains a challenge for many traditional methods. To address this issue, we propose the integration of a variational autoencoder (VAE) in this paper. The VAE enables efficient feature extraction from hyperspectral images (HSIs) by mapping inputs to latent variables that follow a Gaussian distribution. The resulting latent representations are subsequently passed to the Reed-Xiaoli (RX) detector to obtain the final detection results. Through extensive testing on three real datasets, the detection results demonstrate the superiority of our proposed method.

AB - Hyperspectral anomaly detection is a widely studied topic that has garnered significant attention in recent years. However, designing effective nonlinear detectors remains a challenge for many traditional methods. To address this issue, we propose the integration of a variational autoencoder (VAE) in this paper. The VAE enables efficient feature extraction from hyperspectral images (HSIs) by mapping inputs to latent variables that follow a Gaussian distribution. The resulting latent representations are subsequently passed to the Reed-Xiaoli (RX) detector to obtain the final detection results. Through extensive testing on three real datasets, the detection results demonstrate the superiority of our proposed method.

KW - Hyperspectral anomaly detection

KW - RX detector

KW - variational autoencoder (VAE)

UR - https://www.scopus.com/pages/publications/85187955868

U2 - 10.1109/IGARSS52108.2023.10283137

DO - 10.1109/IGARSS52108.2023.10283137

M3 - 论文

AN - SCOPUS:85187955868

SP - 7348

EP - 7351

T2 - 2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023

Y2 - 16 July 2023 through 21 July 2023

ER -

DEEP-RX FOR HYPERSPECTRAL ANOMALY DETECTION

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this