جستجوی مقالات مرتبط با کلیدواژه « فضای ویژگی » در نشریات گروه « جغرافیا »

High accuracy and huge density of 3D points cloud acquired by airborne Lidar makes them as a good and suitable tool in order to analyze of terrain surface. In this procedure, points cloud clustering is a fundamental step in the procedure of information extraction form LiDAR's data. In this paper a novel method is proposed for supervised classification of LiDAR points cloud based on contextual analysis on LiDAR points. The proposed method consists of three main steps. In the first step, a set of contextual features are produced for each points in LiDAR data. In second step, optimum feature selection is done in the modified prototype space using a new strategy. The last step is conducted to a simple k-means clustering on the feature space spanned by optimum contextual clusters. An urban area with the residential texture has been used as the case study to evaluation of the proposed method. The results indicate proper classification accuracies. The overall accuracies and kappa coefficients was 93.15% and 0.89 respectively.

By coming the new generation of SAR polarimetric satellites, such as TerraSAR-X, RADARSAT-2,ALOS, etc., the development of polarimetric synthetic aperture radar (PolSAR) applications in the field of natural hazard and environmental, such as subsidence, soil erosion, earthquake prediction, volcano activities and flood have been accelerated. The aim of this article is extraction of basic information from POLSAR images and determining the amount of the importance of each characteristics in feature vector spaces.The elements of the feature vector space are produced bymultiplication of HH, VV and HV bands that contained the scope of phase and amplitude information.Performed by making Fischer criterion for class separation, the significance of each features are verified and therefore, the features are ranked based upon the power of separability and correlations between the bands. In the next stage, by performing supervise Maximum likelihood classifier, theaccuracy of the different combination of the features has been analyzed. Finally, the best combination of the existing features was obtained. Extraction of the best mining consisting of at least features in the feature vector space, not only protects the most important information, but also leads to reduction in the volume of POLSAR image processing operations. In this regard, the proposed algorithm in thisarticle can be applied on any polarimetric data.