Random Collective Representation-Based Detector with Multiple Features for Hyperspectral Images
Collaborative representation-based detector (CRD), as the most representative anomaly detection method, has been widely applied in the field of hyperspectral anomaly detection (HAD). However, the sliding dual window of the original CRD introduces high computational complexity. Moreover, most HAD mod...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-02-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/4/721 |
| _version_ | 1797396317922656256 |
|---|---|
| author | Zhongheng Li Fang He Haojie Hu Fei Wang Weizhong Yu |
| author_facet | Zhongheng Li Fang He Haojie Hu Fei Wang Weizhong Yu |
| author_sort | Zhongheng Li |
| collection | DOAJ |
| description | Collaborative representation-based detector (CRD), as the most representative anomaly detection method, has been widely applied in the field of hyperspectral anomaly detection (HAD). However, the sliding dual window of the original CRD introduces high computational complexity. Moreover, most HAD models only consider a single spectral or spatial feature of the hyperspectral image (HSI), which is unhelpful for improving detection accuracy. To solve these problems, in terms of speed and accuracy, we propose a novel anomaly detection approach, named Random Collective Representation-based Detector with Multiple Feature (RCRDMF). This method includes the following steps. This method first extract the different features include spectral feature, Gabor feature, extended multiattribute profile (EMAP) feature, and extended morphological profile (EMP) feature matrix from the HSI image, which enables us to improve the accuracy of HAD by combining the multiple spectral and spatial features. The ensemble and random collaborative representation detector (ERCRD) method is then applied, which can improve the anomaly detection speed. Finally, an adaptive weight approach is proposed to calculate the weight for each feature. Experimental results on six hyperspectral datasets demonstrate that the proposed approach has the superiority over accuracy and speed. |
| first_indexed | 2024-03-09T00:49:34Z |
| format | Article |
| id | doaj.art-6de5c8a53e024c8289ba868ecec395eb |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T00:49:34Z |
| publishDate | 2021-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-6de5c8a53e024c8289ba868ecec395eb2023-12-11T17:17:39ZengMDPI AGRemote Sensing2072-42922021-02-0113472110.3390/rs13040721Random Collective Representation-Based Detector with Multiple Features for Hyperspectral ImagesZhongheng Li0Fang He1Haojie Hu2Fei Wang3Weizhong Yu4School of Electronic and Information Engineering, Xi’an Jiaotong University, Xi’an 710049, ChinaXi’an Research Institute of Hi-Tech, Xi’an 710025, ChinaXi’an Research Institute of Hi-Tech, Xi’an 710025, ChinaSchool of Electronic and Information Engineering, Xi’an Jiaotong University, Xi’an 710049, ChinaSchool of Electronic and Information Engineering, Xi’an Jiaotong University, Xi’an 710049, ChinaCollaborative representation-based detector (CRD), as the most representative anomaly detection method, has been widely applied in the field of hyperspectral anomaly detection (HAD). However, the sliding dual window of the original CRD introduces high computational complexity. Moreover, most HAD models only consider a single spectral or spatial feature of the hyperspectral image (HSI), which is unhelpful for improving detection accuracy. To solve these problems, in terms of speed and accuracy, we propose a novel anomaly detection approach, named Random Collective Representation-based Detector with Multiple Feature (RCRDMF). This method includes the following steps. This method first extract the different features include spectral feature, Gabor feature, extended multiattribute profile (EMAP) feature, and extended morphological profile (EMP) feature matrix from the HSI image, which enables us to improve the accuracy of HAD by combining the multiple spectral and spatial features. The ensemble and random collaborative representation detector (ERCRD) method is then applied, which can improve the anomaly detection speed. Finally, an adaptive weight approach is proposed to calculate the weight for each feature. Experimental results on six hyperspectral datasets demonstrate that the proposed approach has the superiority over accuracy and speed.https://www.mdpi.com/2072-4292/13/4/721hyperspectral image (HSI)hyperspectral anomaly detection (HAD)multiple featurecollaborative representation-based detector (CRD)ensemble and random collaborative representation detector (ERCRD)random collective representation-based detector with multiple feature (RCRDMF) |
| spellingShingle | Zhongheng Li Fang He Haojie Hu Fei Wang Weizhong Yu Random Collective Representation-Based Detector with Multiple Features for Hyperspectral Images Remote Sensing hyperspectral image (HSI) hyperspectral anomaly detection (HAD) multiple feature collaborative representation-based detector (CRD) ensemble and random collaborative representation detector (ERCRD) random collective representation-based detector with multiple feature (RCRDMF) |
| title | Random Collective Representation-Based Detector with Multiple Features for Hyperspectral Images |
| title_full | Random Collective Representation-Based Detector with Multiple Features for Hyperspectral Images |
| title_fullStr | Random Collective Representation-Based Detector with Multiple Features for Hyperspectral Images |
| title_full_unstemmed | Random Collective Representation-Based Detector with Multiple Features for Hyperspectral Images |
| title_short | Random Collective Representation-Based Detector with Multiple Features for Hyperspectral Images |
| title_sort | random collective representation based detector with multiple features for hyperspectral images |
| topic | hyperspectral image (HSI) hyperspectral anomaly detection (HAD) multiple feature collaborative representation-based detector (CRD) ensemble and random collaborative representation detector (ERCRD) random collective representation-based detector with multiple feature (RCRDMF) |
| url | https://www.mdpi.com/2072-4292/13/4/721 |
| work_keys_str_mv | AT zhonghengli randomcollectiverepresentationbaseddetectorwithmultiplefeaturesforhyperspectralimages AT fanghe randomcollectiverepresentationbaseddetectorwithmultiplefeaturesforhyperspectralimages AT haojiehu randomcollectiverepresentationbaseddetectorwithmultiplefeaturesforhyperspectralimages AT feiwang randomcollectiverepresentationbaseddetectorwithmultiplefeaturesforhyperspectralimages AT weizhongyu randomcollectiverepresentationbaseddetectorwithmultiplefeaturesforhyperspectralimages |