Search

This paper discusses landcover classification using high density airborne LiDAR data and multispectral imagery. The study area is located at the Duursche Waarden floodplain, the Netherlands. The density of the FLI-MAP 400 LiDAR system is between 50 and 100 points per m2. Other than height and intensity, the LiDAR system also measures spectral information (Red, Green, and Blue). Several features are created for height, intensity, Red, Green, and Blue. The landcover classification process is divided into Support Vector Machine (SVM) and Maximum Likelihood (ML) classifiers. Each classifier is used on three different datasets: 1) FLI-MAP 400-generated multispectral images, 2) LiDAR-derived features, and 3) a combination of the multispectral images and the LiDAR-derived features. The results show that the SVM method produces better classification results than the ML method. Landcover classification based on the combination of LiDAR-derived features and multispectral images produces better results than classification based on either dataset only. [ABSTRACT FROM PUBLISHER]

A linear relationship among the HH, HV, and VV components of polarimetric synthetic aperture radar (SAR) data is studied. A regression model was developed to predict the real and imaginary parts of the VV polarimetric component from the HH and HV components in dual polarimetric SAR and the resulting dataset is called pseudo-fully polarimetric SAR data. Freeman-Wishart classification was applied to evaluate the preservation of scattering characteristics in the pseudo-fully polarimetric dataset. A kappa coefficient is 0.81 indicates very good agreement between the two classification results. An SVM was used for the land cover classification. Finally, post-processing was implemented to remove noise in the form of isolated pixels. AVNIR-2 optical data taken over the same area at nearly same time was used as ground truth data to assess the classification accuracy. The land cover classification result obtained from the SVM shows that using the pseudo-fully polarimetric data gives more than a 2% improvement of mean producer's accuracy over dual polarimetric datasets. [ABSTRACT FROM PUBLISHER]

This paper proposes the classification framework based on the Bayesian theory with the single polarization multi-temporal synthetic aperture radar (SAR) and an optical data, and incorporates the proposed training sample selection (SS) methods. Within this framework, the combination with gray level co-occurrence matrix (GLCM)-based mean textural measure is investigated. The two procedures of the classification and proposed SS are united, where SS generates accurate and dispersed training samples. Extracted features from multi-temporal SAR data—namely, the average backscattering coefficient, backscatter temporal variability, and long-term coherence and reflectance values from optical data, are integrated with GLCM mean textural data in the framework. Classification results were generated by taking Osaka City, Japan, as the study area. The selected major classes were built-up areas, fields, woodlands, and water bodies. The most suitable data used for classification is the multi-temporal SAR and an optical data fusion with the mean textural, because of the supplement of different data used and the smoothing effect on the images of the texture. Moreover, the higher quality training samples obtained by using the combined SVM and NN-based SS method for training the Bayesian classifier generated the highest classification accuracies in all of tested cases. [ABSTRACT FROM PUBLISHER]

An unsupervised classification scheme based on the use of polarimetric entropy, alpha angle and complex Wishart classifier is widely used for landcover classification. The segmented zones in the entropy/alpha plane is fed as the initial input to Wishart based classifiers. The Wishart based classifiers highly depend on this initial input. However as the entropy/alpha boundaries are fixed, this scheme does not perform satisfactorily in some cases. We propose a modified version of this scheme in which the entropy/alpha boundaries are set based on the nature of the dataset. The popular Gaussian mixture model clustering method is used in deciding the boundaries. The proposed procedure which is reported in this paper is found to enhance the landcover classification capability and computational efficiency of the classic entropy based Wishart classifiers. [ABSTRACT FROM PUBLISHER]