6533b855fe1ef96bd12b12bb
RESEARCH PRODUCT
Minimal learning machine in anomaly detection from hyperspectral images
Leevi AnnalaIlkka PölönenAnna-maria HakolaKimmo Aukusti Riihiahosubject
lcsh:Applied optics. PhotonicsComputer sciencehyperspectral imagingData needs0211 other engineering and technologies02 engineering and technologylcsh:TechnologyConstant false alarm rateremote sensing0202 electrical engineering electronic engineering information engineering021101 geological & geomatics engineeringData collectionlcsh:Tbusiness.industryspektrikuvausProcess (computing)lcsh:TA1501-1820Hyperspectral imagingPattern recognitionminimal learning machineDroneanomaly detectionkoneoppiminenMinimal learning machinelcsh:TA1-2040020201 artificial intelligence & image processingAnomaly detectionArtificial intelligencekaukokartoituslcsh:Engineering (General). Civil engineering (General)businessdescription
Abstract. Anomaly detection from hyperspectral data needs computationally efficient methods to process the data when the data gathering platform is a drone or a cube satellite. In this study, we introduce a minimal learning machine for hyperspectral anomaly detection. Minimal learning machine is a novel distance-based classification algorithm, which is now modified to detect anomalies. Besides being computationally efficient, minimal learning machine is also easy to implement. Based on the results, we show that minimal learning machine is efficient in detecting global anomalies from the hyperspectral data with low false alarm rate.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2020-08-19 |