Automatic Feature Learning for Spatio-Spectral Image Classification With Sparse SVM

By Devis Tuia, Michele Volpi, M. Dalla Mura, Alain Rakotomamonjy, Rémi Flamary. 2014

118 citations recorded by the source corpus.

Including spatial information is a key step for successful remote sensing image classification. In particular, when dealing with high spatial resolution, if local variability is strongly reduced by spatial filtering, the classification performance results are boosted. In this paper, we consider the triple objective of designing a spatial/spectral classifier, which is compact (uses as few features as possible), discriminative (enhances class separation), and robust (works well in small sample situations). We achieve this triple objective by discovering the relevant features in the (possibly infinite) space of spatial filters by optimizing a margin-maximization criterion. Instead of imposing a filter bank with predefined filter types and parameters, we let the model figure out which set of filters is optimal for class separation. To do so, we randomly generate spatial filter banks and use an active-set criterion to rank the candidate features according to their benefits to margin maximization (and, thus, to generalization) if added to the model. Experiments on multispectral very high spatial resolution (VHR) and hyperspectral VHR data show that the proposed algorithm, which is sparse and linear, finds discriminative features and achieves at least the same performances as models using a large filter bank defined in advance by prior knowledge.

Subfields: Atmospheric Science, Computer Vision and Pattern Recognition, Media Technology, Optimization & Training

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atmospheric Science

In Computer Vision and Pattern Recognition

In Media Technology

In Optimization & Training

Citations in the corpus

Remote Sensing Image Scene Classification: Benchmark and State of the Art (2017, background): “wide range of applications, such as natural hazards detection [5-7], LULC determination [8-43], geospatial object detection [27, 44-52], geographic image retrieval [53-63], vegetation mapping [64-68], environment monitoring, and urban planning.”
Strathprints Institutional Repository Shuhui and Ren, Jinchang (2015) Effective and Efficient Midlevel Visual Elements-oriented Land-use Classification Using Vhr Remote Sensing Images. Ieee Transactions on Geoscience and Remote Sensing, 53 (8). Pp. 4238-4249. Issn 0196-2892 Effective and Efficient M (unknown): “Most previous works [8] [9] [10] [11] [12] [13] [14] [15] [16] [17] mainly focus on classifying pixels or objects (or rather, grouping of local homogeneous pixels) into their thematic class by extracting low-level image features (e.g. texture feature [9] [10], color feature [8], spatial and…”
Dense Semantic Labeling of Subdecimeter Resolution Images With Convolutional Neural Networks (2016, background): “Exhaustive and global optimization of such values is unfeasible in reasonable time, but the selection from random feature ensembles has shown to be an effective proxy [5]–[7].”
Spectral-Spatial Classification of Hyperspectral Imagery with 3D Convolutional Neural Network (2017, background): “In other words, the spatial dependence is extracted in advance through various spatial filters, such as morphological profiles [10–12], entropy [13], attribute profiles [14], and low-rank representation [15,16].”
A Survey on Spectral–Spatial Classification Techniques Based on Attribute Profiles (2015, background): “In [63], a strategy for the selection of spatial features (among”