Spectral and Spatial Classification of Hyperspectral Data Using SVMs and Morphological Profiles

Signal & Image Dept., Grenoble Inst. of Technol., Grenoble
IEEE Transactions on Geoscience and Remote Sensing (Impact Factor: 3.47). 12/2008; DOI: 10.1109/TGRS.2008.922034
Source: OAI

ABSTRACT A method is proposed for the classification of urban hyperspectral data with high spatial resolution. The approach is an extension of previous approaches and uses both the spatial and spectral information for classification. One previous approach is based on using several principal components (PCs) from the hyperspectral data and building several morphological profiles (MPs). These profiles can be used all together in one extended MP. A shortcoming of that approach is that it was primarily designed for classification of urban structures and it does not fully utilize the spectral information in the data. Similarly, the commonly used pixelwise classification of hyperspectral data is solely based on the spectral content and lacks information on the structure of the features in the image. The proposed method overcomes these problems and is based on the fusion of the morphological information and the original hyperspectral data, i.e., the two vectors of attributes are concatenated into one feature vector. After a reduction of the dimensionality, the final classification is achieved by using a support vector machine classifier. The proposed approach is tested in experiments on ROSIS data from urban areas. Significant improvements are achieved in terms of accuracies when compared to results obtained for approaches based on the use of MPs based on PCs only and conventional spectral classification. For instance, with one data set, the overall accuracy is increased from 79% to 83% without any feature reduction and to 87% with feature reduction. The proposed approach also shows excellent results with a limited training set.

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In the past decade, there has been a growing need for machine learning and computer vision components (seg-mentation, classification) in the hyperspectral imaging do-main. Due to the complexity and size of hyperspectral im-agery and the enormous number of wavelength channels, the need for combining compact representations with im-age segmentation and superpixel estimation has emerged in this area. Here, we present an approach to superpixel esti-mation in hyperspectral images by adapting the well known UCM approach to hyperspectral volumes. This approach benefits from the channel information at each pixel of the hyperspectral image while obtaining a compact represen-tation of the hyperspectral volume using principal compo-nent analysis. Our experimental evaluation demonstrates that the additional information of spectral channels will substantially improve superpixel estimation from a single "monochromatic" channel. Furthermore, superpixel esti-mation performed on the compact hyperspectral represen-tation outperforms the same when executed on the entire volume.
    IEEE Computer Vision and Pattern Recognition Workshops; 01/2014
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Context-based unmixing has been studied by several re-searchers. Recent techniques, such as piece-wise convex unmixing using fuzzy and possibilistic clustering or Bayesian methods proposed in [11] attempt to form contexts via clus-tering. It is assumed that the linear mixing model applies to each cluster (context) and endmembers and abundances are found for each cluster. As the clusters are spatially coher-ent, hyperspectral image segmentation can significantly aid unmixing approaches that perform cluster specific estimation of endmembers. In this work, we integrate a graph-cuts seg-mentation algorithm with piece-wise convex unmixing. This is compared to fuzzy clustering (FCM) with results obtained on two datasets. The results demonstrate that the integrated approach achieves better segmentation and more precise end-member identification (in terms of comparisons with known ground truth).
    IEEE Workshop on Hyperspectral Image and SIgnal Processing: Evolution in Remote Sensing; 01/2014
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Accurate landuse classification maps show the current status of natural and manmade objects on the earth's surface and such information can be used to monitor the health of forests, contamination of watercourses and climate change. This paper shows that the classification accuracy of airborne hyperspectral images is improved when fused with LiDAR data. Two widely used methods—the support vector machine and segmentation—were tested and both showed an improvement in the accuracy. To verify the accuracy, a digital cadastral map displaying land categories by parcel was used as reference data. The study showed classification using fused data proved to be useful, regardless of the number of classes or the classifier used for analysis.
    Disaster Advances 12/2013; 6(12):117-126. · 2.27 Impact Factor

Full-text (2 Sources)

Available from
May 30, 2014