Robust multi-stage progressive autoencoder for hyperspectral anomaly detection
Recently, Autoencoders (AEs) have demonstrated remarkable performance in the field of hyperspectral anomaly detection, owing to their powerful capability in handling high-dimensional data. However, they often overlook the inherent global distribution characteristics and long-range dependencies in hy...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-11-01
|
| Series: | International Journal of Applied Earth Observations and Geoinformation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1569843224005569 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846166176201179136 |
|---|---|
| author | Qing Guo Yi Cen Lifu Zhang Yan Zhang Shunshi Hu Xue Liu |
| author_facet | Qing Guo Yi Cen Lifu Zhang Yan Zhang Shunshi Hu Xue Liu |
| author_sort | Qing Guo |
| collection | DOAJ |
| description | Recently, Autoencoders (AEs) have demonstrated remarkable performance in the field of hyperspectral anomaly detection, owing to their powerful capability in handling high-dimensional data. However, they often overlook the inherent global distribution characteristics and long-range dependencies in hyperspectral images (HSI). This oversight makes it challenging to accurately characterize and describe boundaries between different backgrounds and anomalies in complex HSI, thereby affecting detection accuracy. To address this issue, a robust multi-stage progressive autoencoder for hyperspectral anomaly detection (RMSAD) is proposed. Initially, a progressive multi-stage learning framework based on convolutional autoencoders is employed. This framework incrementally reveals and integrates deep contextual features along with their long-range dependencies in HSI, aiming to accurately characterize the background and anomalies. Subsequently, an innovative multi-scale fusion strategy is introduced at the intersections of each stage, reinforcing the learning and representation of background and global spatial details across multiple stages. Finally, by collectively extracting abnormal spatial information across stages, effectively reducing the tendency of autoencoders to reconstruct anomalies. This ensures the efficient restoration and replication of global textural details in HSI. The experimental results on the six HSI datasets demonstrate that the proposed RMSAD is superior to other state-of-the-art methods. |
| format | Article |
| id | doaj-art-17f9642dfb3a45859d3d6c08a5be8811 |
| institution | Kabale University |
| issn | 1569-8432 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Applied Earth Observations and Geoinformation |
| spelling | doaj-art-17f9642dfb3a45859d3d6c08a5be88112024-11-16T05:10:12ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322024-11-01134104200Robust multi-stage progressive autoencoder for hyperspectral anomaly detectionQing Guo0Yi Cen1Lifu Zhang2Yan Zhang3Shunshi Hu4Xue Liu5State Key·Laboratory·of Remote·Sensing·Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100101, China; University of Chinese Academy of Sciences, Beijing 100049, ChinaState Key·Laboratory·of Remote·Sensing·Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100101, China; School of Computer Science, Hubei University of Technology, Wuhan 430068, China; Corresponding author.State Key·Laboratory·of Remote·Sensing·Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100101, ChinaState Key·Laboratory·of Remote·Sensing·Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100101, China; University of Chinese Academy of Sciences, Beijing 100049, ChinaChina School of Geographic Sciences, Hunan Normal University, Changsha 410081, China; Hunan Key Laboratory of Geospatial Big Data Mining and Application, Changsha 410081, ChinaState Key·Laboratory·of Remote·Sensing·Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100101, ChinaRecently, Autoencoders (AEs) have demonstrated remarkable performance in the field of hyperspectral anomaly detection, owing to their powerful capability in handling high-dimensional data. However, they often overlook the inherent global distribution characteristics and long-range dependencies in hyperspectral images (HSI). This oversight makes it challenging to accurately characterize and describe boundaries between different backgrounds and anomalies in complex HSI, thereby affecting detection accuracy. To address this issue, a robust multi-stage progressive autoencoder for hyperspectral anomaly detection (RMSAD) is proposed. Initially, a progressive multi-stage learning framework based on convolutional autoencoders is employed. This framework incrementally reveals and integrates deep contextual features along with their long-range dependencies in HSI, aiming to accurately characterize the background and anomalies. Subsequently, an innovative multi-scale fusion strategy is introduced at the intersections of each stage, reinforcing the learning and representation of background and global spatial details across multiple stages. Finally, by collectively extracting abnormal spatial information across stages, effectively reducing the tendency of autoencoders to reconstruct anomalies. This ensures the efficient restoration and replication of global textural details in HSI. The experimental results on the six HSI datasets demonstrate that the proposed RMSAD is superior to other state-of-the-art methods.http://www.sciencedirect.com/science/article/pii/S1569843224005569Anomaly detectionautoencoder (AE)hyperspectral image (HSI)Multi-scale feature fusionMulti-stage learning |
| spellingShingle | Qing Guo Yi Cen Lifu Zhang Yan Zhang Shunshi Hu Xue Liu Robust multi-stage progressive autoencoder for hyperspectral anomaly detection International Journal of Applied Earth Observations and Geoinformation Anomaly detection autoencoder (AE) hyperspectral image (HSI) Multi-scale feature fusion Multi-stage learning |
| title | Robust multi-stage progressive autoencoder for hyperspectral anomaly detection |
| title_full | Robust multi-stage progressive autoencoder for hyperspectral anomaly detection |
| title_fullStr | Robust multi-stage progressive autoencoder for hyperspectral anomaly detection |
| title_full_unstemmed | Robust multi-stage progressive autoencoder for hyperspectral anomaly detection |
| title_short | Robust multi-stage progressive autoencoder for hyperspectral anomaly detection |
| title_sort | robust multi stage progressive autoencoder for hyperspectral anomaly detection |
| topic | Anomaly detection autoencoder (AE) hyperspectral image (HSI) Multi-scale feature fusion Multi-stage learning |
| url | http://www.sciencedirect.com/science/article/pii/S1569843224005569 |
| work_keys_str_mv | AT qingguo robustmultistageprogressiveautoencoderforhyperspectralanomalydetection AT yicen robustmultistageprogressiveautoencoderforhyperspectralanomalydetection AT lifuzhang robustmultistageprogressiveautoencoderforhyperspectralanomalydetection AT yanzhang robustmultistageprogressiveautoencoderforhyperspectralanomalydetection AT shunshihu robustmultistageprogressiveautoencoderforhyperspectralanomalydetection AT xueliu robustmultistageprogressiveautoencoderforhyperspectralanomalydetection |