Multiobjective Optimization-Based Hyperspectral Unsupervised Band Selection for Anomaly Detection
Band selection (BS) is a critical topic in hyperspectral image dimensionality reduction, focusing on identifying representative bands that can convey the essential information of the full bands without significant loss. Recently, BS based on multiobjective optimization (MO) has become the predominan...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10771661/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Band selection (BS) is a critical topic in hyperspectral image dimensionality reduction, focusing on identifying representative bands that can convey the essential information of the full bands without significant loss. Recently, BS based on multiobjective optimization (MO) has become the predominant method. However, there are still two problems that need to be solved. First, the majority of multiobjective BS methods predominantly optimize accuracy in classification tasks, neglecting the emphasis on anomaly detection. Second, in the process of addressing the combinatorial optimization problem of multiobjective BS using evolutionary algorithms, insufficient consideration is given to the impact of bands on the recognition capability of an anomaly when devising solution strategies and determining optimal solutions. To handle the above-mentioned problems, a novel anomaly-oriented multiobjective optimization band selection (AOMOBS) is developed to better suppress background and identify anomalies. Specifically, for the first problem, by calculating the degree of deviation of the band, the noise estimates of the band, and the degree of redundancy between bands, an unsupervised BS algorithm for anomaly detection tasks, based on MO, is designed. For the second problem, an MO band similarity sorting strategy for anomaly detection tasks is designed for nondominated sorting, and for decision makers to choose the most appropriate solution from the tradeoff solutions. Experiments conducted on real hyperspectral datasets demonstrate that the algorithm effectively identifies a subset of bands with high representational power for anomaly detection. Moreover, AOMOBS outperforms current state-of-the-art methods in both effectiveness and robustness. |
|---|---|
| ISSN: | 1939-1404 2151-1535 |