Minimal learning machine in anomaly detection from hyperspectral images
Pölönen, Ilkka; Riihiaho, Kimmo; Hakola, Anna-Maria; Annala, Leevi (2020). Minimal learning machine in anomaly detection from hyperspectral images. In Paparoditis, N.; Mallet, C.; Lafarge, F.; Jiang, J.; Shaker, A.; Zhang, H.; Liang, X.; Osmanoglu, B.; Soergel, U.; Honkavaara, E.; Scaioni, M.; Zhang, J.; Peled, A.; Wu, L.; Li, R.; Yoshimura, M. et al. (Eds.) XXIV ISPRS Congress, Commission III, International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLIII-B3-2020. Hannover: International Society for Photogrammetry and Remote Sensing, 467-472. DOI: 10.5194/isprs-archives-XLIII-B3-2020-467-2020
Published inInternational Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Wu, L. |
Li, R. |
Di, K. |
© Authors 2020.
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.