Name
Abstract | ||
|---|---|---|
In the last few years, active learning has been gaining growing interest in the remote sensing community in optimizing the process of training sample collection for supervised image classification. Current strategies formulate the active learning problem in the spectral domain only. However, remote sensing images are intrinsically defined both in the spectral and spatial domains. In this paper, we explore this fact by proposing a new active learning approach for support vector machine classification. In particular, we suggest combining spectral and spatial information directly in the iterative process of sample selection. For this purpose, three criteria are proposed to favor the selection of samples distant from the samples already composing the current training set. In the first strategy, the Euclidean distances in the spatial domain from the training samples are explicitly computed, whereas the second one is based on the Parzen window method in the spatial domain. Finally, the last criterion involves the concept of spatial entropy. Experiments on two very high resolution images show the effectiveness of regularization in spatial domain for active learning purposes. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/TGRS.2013.2258676 | Geoscience and Remote Sensing, IEEE Transactions |
Keywords | Field | DocType |
entropy,geophysical image processing,image classification,image resolution,iterative methods,remote sensing,support vector machines,Euclidean distances,Parzen window method,SVM active learning approach,active learning problem,high resolution images,iterative process,regularization,remote sensing community,remote sensing images,sample selection,spatial domain,spatial entropy,spatial information,spectral domain,spectral information,supervised image classification,support vector machine classification,training sample collection,training set,Active learning,image classification,spatial information,support vector machine (SVM),very high resolution (VHR) | Spatial analysis,Computer science,Artificial intelligence,Contextual image classification,Kernel density estimation,Computer vision,Active learning,Pattern recognition,Iterative and incremental development,Iterative method,Support vector machine,Image resolution,Machine learning | Journal |
Volume | Issue | ISSN |
52 | 4 | 0196-2892 |
Citations | PageRank | References |
42 | 1.40 | 29 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Edoardo Pasolli | 1 | 285 | 17.04 |
| Melgani, F. | 2 | 46 | 2.09 |
| Devis Tuia | 3 | 1715 | 101.88 |
| Pacifici, F. | 4 | 217 | 9.86 |