Semi-automatic choice of scale-dependent features for satellite SAR image classification.
ABSTRACT In this work we compare two different approaches to the use of multiple scales in the classification process of satellite SAR images. These are (I) the multi-scale co-occurrence texture analysis and (II) the semivariogram approach. Moreover, we propose a scheme for optimizing the co-occurrence window size and the semivariogram lag distances in terms of classification accuracy performance. To improve the results even further, we introduce a methodology to compute the co-occurrence features with a window consistent with the local scale, provided by the semivariogram analysis.Examples of satellite SAR image segmentation for urban area characterization are shown to validate the procedure.
- SourceAvailable from: Dragana Sandic
Conference Proceeding: Mathematical morphology in image analysis[show abstract] [hide abstract]
ABSTRACT: Mathematical morphology provides an effective approach to the analyzing of digital images. Basic operations in mathematical morphology are erosion, dilation, opening and closing. Morphological filters are based on the theory of mathematical morphology. This filters exploit geometric rather than analytic features of signals. The advantages of the morphological over linear filtering are direct geometric interpretations, simplicity and efficiency in hardware implementation. Subband decomposition is a procedure of filtering digital image source into a desired number of nonoverlapping frequency bands. Then, each band can be decimated and coded efficiently for data transmission. In this paper morphological filters are used for image decomposition. The image is represented by subband and Laplacian pyramid. The original image can be reconstructed from the subbands. Some image examples are presented to show the effectiveness of this approach.Conference of applied mathematics, PRIM; 06/1996
- [show abstract] [hide abstract]
ABSTRACT: A new methodology for automatic mapping from Landsat thematic mapper (TM) and terrain data, based on the fuzzy ARTMAP neural network, is developed. System capabilities are tested on a challenging remote sensing classification problem, using spectral and terrain features for vegetation classification in the Cleveland National Forest. After training at the pixel level, system performance is tested at the stand level, using sites not seen during training. Results are compared to those of maximum likelihood classifiers, as well as back propagation neural networks and K nearest neighbor algorithms. ARTMAP dynamics are fast, stable, and scalable, overcoming common limitations of back propagation. Best results are obtained using a hybrid system based on a convex combination of fuzzy ARTMAP and maximum likelihood predictions. A prototype remote sensing example introduces each aspect of data processing and fuzzy ARTMAP classification. The example shows how the network automatically constructs a minimal number of recognition categories to meet accuracy criteria. A voting strategy improves prediction and assigns confidence estimates by training the system several times on different orderings of an input setIEEE Transactions on Geoscience and Remote Sensing 04/1997; · 3.47 Impact Factor
- [show abstract] [hide abstract]
ABSTRACT: Semivariogram functions are compared to co-occurrence matrices for classification of digital image texture, and accuracy is assessed using test sites. Images acquired over the following six different spectral bands are used: 1) SPOT HRV, near infrared; 2) Landsat thematic mapper (TM), visible red; 3) India Remote Sensing (IRS) LISS-II, visible green; 4) Magellan, Venus, S-band microwave; 5) shuttle imaging radar (SIR)-C, X-band microwave; 6) SIR-C, L-band microwave. The semivariogram textural measure provides a larger classification accuracy than a classifier based on a co-occurrence matrix for the microwave images and a smaller classification accuracy for the optical imagesIEEE Transactions on Geoscience and Remote Sensing 12/1998; · 3.47 Impact Factor