Journal
PATTERN RECOGNITION
Volume 118, Issue -, Pages -Publisher
ELSEVIER SCI LTD
DOI: 10.1016/j.patcog.2021.107992
Keywords
Anomaly detection; Hyperspectral image; Adversarial learning; Gaussian constraint learning; Unsupervised learning
Funding
- National Natural Science Foundation of China [62071360, 61801359, 61571345, 91538101, 61501346, 61502367, 61701360]
- Young Talent fund of University Association for Science and Technology in Shaanxi of China [20190103]
- China Postdoctoral Science Foundation [2019T120878, 2017M620440]
- 111 project [B08038]
- Fundamental Research Funds for the Central Universities [JB180104]
- Natural Science Basic Research Plan in Shaanxi Province of China [2019JQ153, 2016JQ6023, 2016JQ6018]
- Yangtse Rive Scholar Bonus Schemes [CJT160102]
- Ten Thousand Talent Program
- Science and Technology on ElectroOptic Control Laboratory and Aeronautical Science Foundation of China [6142504190206]
Ask authors/readers for more resources
The study introduces an unsupervised method, dual feature extraction network (DFEN), for hyperspectral anomaly detection, which gradually establishes discrimination between original data and background, calculates spatial and spectral anomaly scores, and reduces false alarm rate for comprehensive detection results.
Hyperspectral anomaly detection (HAD) is a research endeavor of high practical relevance within remote sensing scene interpretation. In this work, we propose an unsupervised approach, dual feature extraction network (DFEN) for HAD, to gradually build up ever-greater discrimination between the original data and background. In particular, we impose an end-to-end discriminative learning loss on two networks. Among them, adversarial learning aims to keep the original spectrum while Gaussian constrained learning intends to learn the background distribution in the potential space. To extract the anomaly, we calculate spatial and spectral anomaly scores based on mean squared error (MSE) spatial distance and orthogonal projection divergence (OPD) spectral distance between two latent feature matrices. Finally, the comprehensive detection result is obtained by a simple dot product between two domains to further reduce the false alarm rate. Experiments have been conducted on eight real hyperspectral data sets captured by different sensors over different scenes, which show that the proposed DFEN method is superior to other compared methods in detection accuracy or false alarm rate. (c) 2021 Elsevier Ltd. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available