Active Learning Methods for Remote Sensing Image Classification

• Published in: IEEE transactions on geoscience and remote sensing 2009-07, Vol.47 (7), p.2218-2232
• Main Authors: Tuia, D., Ratle, F., Pacifici, F., Kanevski, M.F., Emery, W.J.
• Format: Article
• Language: English
• Subjects: Active learning; Algorithms; Applied geophysics; Construction; Earth sciences; Earth, ocean, space; entropy; Exact sciences and technology; hyperspectral imagery; Hyperspectral imaging; Hyperspectral sensors; Image classification; image information mining; Image resolution; Image sampling; Internal geophysics; Learning; Learning systems; margin sampling (MS); Mathematical models; Methods; Pixels; query learning; Remote sensing; Spatial resolution; Studies; Support vector machine classification; Support vector machines; support vector machines (SVMs); Training; very high resolution (VHR) imagery
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2008.2010404

In this paper, we propose two active learning algorithms for semiautomatic definition of training samples in remote sensing image classification. Based on predefined heuristics, the classifier ranks the unlabeled pixels and automatically chooses those that are considered the most valuable for its improvement. Once the pixels have been selected, the analyst labels them manually and the process is iterated. Starting with a small and nonoptimal training set, the model itself builds the optimal set of samples which minimizes the classification error. We have applied the proposed algorithms to a variety of remote sensing data, including very high resolution and hyperspectral images, using support vector machines. Experimental results confirm the consistency of the methods. The required number of training samples can be reduced to 10% using the methods proposed, reaching the same level of accuracy as larger data sets. A comparison with a state-of-the-art active learning method, margin sampling, is provided, highlighting advantages of the methods proposed. The effect of spatial resolution and separability of the classes on the quality of the selection of pixels is also discussed.