Spectral–Spatial Feature Fusion for Hyperspectral Anomaly Detection
Hyperspectral anomaly detection is used to recognize unusual patterns or anomalies in hyperspectral data. Currently, many spectral–spatial detection methods have been proposed with a cascaded manner; however, they often neglect the complementary characteristics between the spectral and spatial dimen...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/5/1652 |
| _version_ | 1827319303652769792 |
|---|---|
| author | Shaocong Liu Zhen Li Guangyuan Wang Xianfei Qiu Tinghao Liu Jing Cao Donghui Zhang |
| author_facet | Shaocong Liu Zhen Li Guangyuan Wang Xianfei Qiu Tinghao Liu Jing Cao Donghui Zhang |
| author_sort | Shaocong Liu |
| collection | DOAJ |
| description | Hyperspectral anomaly detection is used to recognize unusual patterns or anomalies in hyperspectral data. Currently, many spectral–spatial detection methods have been proposed with a cascaded manner; however, they often neglect the complementary characteristics between the spectral and spatial dimensions, which easily leads to yield high false alarm rate. To alleviate this issue, a spectral–spatial information fusion (SSIF) method is designed for hyperspectral anomaly detection. First, an isolation forest is exploited to obtain spectral anomaly map, in which the object-level feature is constructed with an entropy rate segmentation algorithm. Then, a local spatial saliency detection scheme is proposed to produce the spatial anomaly result. Finally, the spectral and spatial anomaly scores are integrated together followed by a domain transform recursive filtering to generate the final detection result. Experiments on five hyperspectral datasets covering ocean and airport scenes prove that the proposed SSIF produces superior detection results over other state-of-the-art detection techniques. |
| first_indexed | 2024-04-25T00:18:45Z |
| format | Article |
| id | doaj.art-524abb2e1614471bb0af09027be79d94 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-25T00:18:45Z |
| publishDate | 2024-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-524abb2e1614471bb0af09027be79d942024-03-12T16:55:31ZengMDPI AGSensors1424-82202024-03-01245165210.3390/s24051652Spectral–Spatial Feature Fusion for Hyperspectral Anomaly DetectionShaocong Liu0Zhen Li1Guangyuan Wang2Xianfei Qiu3Tinghao Liu4Jing Cao5Donghui Zhang6Institute of Remote Sensing Satellite, China Academy of Space Technology (CAST), Beijing 100094, ChinaInstitute of Remote Sensing Satellite, China Academy of Space Technology (CAST), Beijing 100094, ChinaInstitute of Remote Sensing Satellite, China Academy of Space Technology (CAST), Beijing 100094, ChinaInstitute of Remote Sensing Satellite, China Academy of Space Technology (CAST), Beijing 100094, ChinaInstitute of Remote Sensing Satellite, China Academy of Space Technology (CAST), Beijing 100094, ChinaInstitute of Remote Sensing Satellite, China Academy of Space Technology (CAST), Beijing 100094, ChinaInstitute of Remote Sensing Satellite, China Academy of Space Technology (CAST), Beijing 100094, ChinaHyperspectral anomaly detection is used to recognize unusual patterns or anomalies in hyperspectral data. Currently, many spectral–spatial detection methods have been proposed with a cascaded manner; however, they often neglect the complementary characteristics between the spectral and spatial dimensions, which easily leads to yield high false alarm rate. To alleviate this issue, a spectral–spatial information fusion (SSIF) method is designed for hyperspectral anomaly detection. First, an isolation forest is exploited to obtain spectral anomaly map, in which the object-level feature is constructed with an entropy rate segmentation algorithm. Then, a local spatial saliency detection scheme is proposed to produce the spatial anomaly result. Finally, the spectral and spatial anomaly scores are integrated together followed by a domain transform recursive filtering to generate the final detection result. Experiments on five hyperspectral datasets covering ocean and airport scenes prove that the proposed SSIF produces superior detection results over other state-of-the-art detection techniques.https://www.mdpi.com/1424-8220/24/5/1652hyperspectral imageisolation forestlocal saliency detectionanomaly detectionspectral–spatial fusion |
| spellingShingle | Shaocong Liu Zhen Li Guangyuan Wang Xianfei Qiu Tinghao Liu Jing Cao Donghui Zhang Spectral–Spatial Feature Fusion for Hyperspectral Anomaly Detection Sensors hyperspectral image isolation forest local saliency detection anomaly detection spectral–spatial fusion |
| title | Spectral–Spatial Feature Fusion for Hyperspectral Anomaly Detection |
| title_full | Spectral–Spatial Feature Fusion for Hyperspectral Anomaly Detection |
| title_fullStr | Spectral–Spatial Feature Fusion for Hyperspectral Anomaly Detection |
| title_full_unstemmed | Spectral–Spatial Feature Fusion for Hyperspectral Anomaly Detection |
| title_short | Spectral–Spatial Feature Fusion for Hyperspectral Anomaly Detection |
| title_sort | spectral spatial feature fusion for hyperspectral anomaly detection |
| topic | hyperspectral image isolation forest local saliency detection anomaly detection spectral–spatial fusion |
| url | https://www.mdpi.com/1424-8220/24/5/1652 |
| work_keys_str_mv | AT shaocongliu spectralspatialfeaturefusionforhyperspectralanomalydetection AT zhenli spectralspatialfeaturefusionforhyperspectralanomalydetection AT guangyuanwang spectralspatialfeaturefusionforhyperspectralanomalydetection AT xianfeiqiu spectralspatialfeaturefusionforhyperspectralanomalydetection AT tinghaoliu spectralspatialfeaturefusionforhyperspectralanomalydetection AT jingcao spectralspatialfeaturefusionforhyperspectralanomalydetection AT donghuizhang spectralspatialfeaturefusionforhyperspectralanomalydetection |