Minimal learning machine in hyperspectral imaging classification
Hakola, A.-M., & Pölönen, I. (2020). Minimal learning machine in hyperspectral imaging classification . In L. Bruzzone, F. Bovolo, & E. Santi (Eds.), Image and Signal Processing for Remote Sensing XXVI (Article 115330R). SPIE. Proceedings of SPIE : the International Society for Optical Engineering, 11533. https://doi.org/10.1117/12.2573578
© 2020 SPIE
A hyperspectral (HS) image is typically a stack of frames, where each frame represents the intensity of a diﬀerent wavelength of light. Each spatial pixel has a spectrum. In the classiﬁcation of the HS image, each spectrum is classiﬁed pixel-by-pixel. In some of the real-time applications, the amount of the HS image data causes performance challenges. Those issues relate to the platforms (e.g. drones) payload restrictions, the issues of the available energy and to the complexity of the machine learning models. In this study, we introduce the minimal learning machine (MLM) as a computationally cheap training and classiﬁcation machine learning method for the hyperspectral imaging classiﬁcation. MLM is a distance-based method that utilizes mapping between input and and output distances. Input distance is a distance between the training set and its subset R. Output distance is corresponding distances between the label values of the training set and the subset R. We propose a training point selection framework, which reduces the number of data points in the R by selecting the points class-by-class, in the direction of the principal components of each class. We test MLM’s performance against four other classiﬁcation machine learning methods: Random Forest, Artiﬁcial Neural Network, Support Vector Machine and Nearest Neighbours classiﬁer with three known hyper- spectral data sets. As the main outcomes, we will show how the performance is aﬀected by the size of the subset R. We compare our subset selection method MLM’s performance to the random selection MLM’s perfor- mance. Results show that MLM is an computationally eﬃcient way to train large training sets. MLM reduces the complexity of the analysis and provides computational beneﬁts against other models. Proposed framework oﬀers tools that can improve the MLM’s classiﬁcation time and the accuracy rate compared to the MLM with randomly picked training points. ...
Parent publication ISBN978-1-5106-3879-2
ConferenceSPIE Remote Sensing
Is part of publicationImage and Signal Processing for Remote Sensing XXVI
Publication in research information system
MetadataShow full item record
Related funder(s)Academy of Finland
Funding program(s)Academy Project, AoF
Additional information about fundingThis study is partly funded by Jane and Aatos Erkko Foundation (Grant No. 170015) and Academy of Finland(Grant No. 327862)
Showing items with similar title or keywords.
Raita-Hakola, A.-M.; Pölönen, I. (Copernicus Publications, 2021)Hyperspectral imaging, with its applications, offers promising tools for remote sensing and Earth observation. Recent development has increased the quality of the sensors. At the same time, the prices of the sensors are ...
Tree species classification of drone hyperspectral and RGB imagery with deep learning convolutional neural networks Nezami, Somayeh; Khoramshahi, Ehsan; Nevalainen, Olli; Pölönen, Ilkka; Honkavaara, Eija (MDPI AG, 2020)Interest in drone solutions in forestry applications is growing. Using drones, datasets can be captured flexibly and at high spatial and temporal resolutions when needed. In forestry applications, fundamental tasks include ...
Raita-Hakola, Anna-Maria; Pölönen, Ilkka (Copernicus Publications, 2022)The idea is to create a self-learning Minimal Learning Machine (MLM) model that is computationally efficient, easy to implement and performs with high accuracy. The study has two hypotheses. Experiment A examines the ...
Editorial for the special issue "Frontiers in spectral imaging and 3D technologies for geospatial solutions" Honkavaara, Eija; Karantzalos, Konstantinos; Liang, Xinlian; Nocerino, Erica; Pölönen, Ilkka; Rönnholm, Petri (MDPI, 2019)This Special Issue hosts papers on the integrated use of spectral imaging and 3D technologies in remote sensing, including novel sensors, evolving machine learning technologies for data analysis, and the utilization of ...
Pölönen, Ilkka; Riihiaho, Kimmo; Hakola, Anna-Maria; Annala, Leevi (International Society for Photogrammetry and Remote Sensing, 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 ...