Adopting Hyperspectral Anomaly Detection for Near Real-Time Camouflage Detection in Multispectral Imagery
Tactical reconnaissance using small unmanned aerial vehicles has become a common military scenario. However, since their sensor systems are usually limited to rudimentary visual or thermal imaging, the detection of camouflaged objects can be a particularly hard challenge. With respect to SWaP-C crit...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/15/3755 |
| _version_ | 1827618389394194432 |
|---|---|
| author | Tobias Hupel Peter Stütz |
| author_facet | Tobias Hupel Peter Stütz |
| author_sort | Tobias Hupel |
| collection | DOAJ |
| description | Tactical reconnaissance using small unmanned aerial vehicles has become a common military scenario. However, since their sensor systems are usually limited to rudimentary visual or thermal imaging, the detection of camouflaged objects can be a particularly hard challenge. With respect to SWaP-C criteria, multispectral sensors represent a promising solution to increase the spectral information that could lead to unveiling camouflage. Therefore, this paper investigates and evaluates the applicability of four well-known hyperspectral anomaly detection methods (RX, LRX, CRD, and AED) and a method developed by the authors called local point density (LPD) for near real-time camouflage detection in multispectral imagery based on a specially created dataset. Results show that all targets in the dataset could successfully be detected with an AUC greater than 0.9 by multiple methods, with some methods even reaching an AUC relatively close to 1.0 for certain targets. Yet, great variations in detection performance over all targets and methods were observed. The dataset was additionally enhanced by multiple vegetation indices (BNDVI, GNDVI, and NDRE), which resulted in generally higher detection performances of all methods. Overall, the results demonstrated the general applicability of the hyperspectral anomaly detection methods for camouflage detection in multispectral imagery. |
| first_indexed | 2024-03-09T10:05:54Z |
| format | Article |
| id | doaj.art-dcf45d8687cd4f1f966f1cd38f787225 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T10:05:54Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-dcf45d8687cd4f1f966f1cd38f7872252023-12-01T23:08:38ZengMDPI AGRemote Sensing2072-42922022-08-011415375510.3390/rs14153755Adopting Hyperspectral Anomaly Detection for Near Real-Time Camouflage Detection in Multispectral ImageryTobias Hupel0Peter Stütz1Institute of Flight Systems, Universität der Bundeswehr München, 85577 Neubiberg, GermanyInstitute of Flight Systems, Universität der Bundeswehr München, 85577 Neubiberg, GermanyTactical reconnaissance using small unmanned aerial vehicles has become a common military scenario. However, since their sensor systems are usually limited to rudimentary visual or thermal imaging, the detection of camouflaged objects can be a particularly hard challenge. With respect to SWaP-C criteria, multispectral sensors represent a promising solution to increase the spectral information that could lead to unveiling camouflage. Therefore, this paper investigates and evaluates the applicability of four well-known hyperspectral anomaly detection methods (RX, LRX, CRD, and AED) and a method developed by the authors called local point density (LPD) for near real-time camouflage detection in multispectral imagery based on a specially created dataset. Results show that all targets in the dataset could successfully be detected with an AUC greater than 0.9 by multiple methods, with some methods even reaching an AUC relatively close to 1.0 for certain targets. Yet, great variations in detection performance over all targets and methods were observed. The dataset was additionally enhanced by multiple vegetation indices (BNDVI, GNDVI, and NDRE), which resulted in generally higher detection performances of all methods. Overall, the results demonstrated the general applicability of the hyperspectral anomaly detection methods for camouflage detection in multispectral imagery.https://www.mdpi.com/2072-4292/14/15/3755camouflage detectionanomaly detectionmultispectralhyperspectralinfraredimage processing |
| spellingShingle | Tobias Hupel Peter Stütz Adopting Hyperspectral Anomaly Detection for Near Real-Time Camouflage Detection in Multispectral Imagery Remote Sensing camouflage detection anomaly detection multispectral hyperspectral infrared image processing |
| title | Adopting Hyperspectral Anomaly Detection for Near Real-Time Camouflage Detection in Multispectral Imagery |
| title_full | Adopting Hyperspectral Anomaly Detection for Near Real-Time Camouflage Detection in Multispectral Imagery |
| title_fullStr | Adopting Hyperspectral Anomaly Detection for Near Real-Time Camouflage Detection in Multispectral Imagery |
| title_full_unstemmed | Adopting Hyperspectral Anomaly Detection for Near Real-Time Camouflage Detection in Multispectral Imagery |
| title_short | Adopting Hyperspectral Anomaly Detection for Near Real-Time Camouflage Detection in Multispectral Imagery |
| title_sort | adopting hyperspectral anomaly detection for near real time camouflage detection in multispectral imagery |
| topic | camouflage detection anomaly detection multispectral hyperspectral infrared image processing |
| url | https://www.mdpi.com/2072-4292/14/15/3755 |
| work_keys_str_mv | AT tobiashupel adoptinghyperspectralanomalydetectionfornearrealtimecamouflagedetectioninmultispectralimagery AT peterstutz adoptinghyperspectralanomalydetectionfornearrealtimecamouflagedetectioninmultispectralimagery |