Research on Remote Sensing Geological Information Extraction Based on Object Oriented Classification

Abstract

ABS TRACT:The northern Tibet belongs to the Sub cold arid climate zone in the plateau. It is rarely visited by people. The geological w orking conditions are very poor. However, the stratum exposures are good and human interference is very small. Therefore, the research on the automatic classification and extraction of remote sensing geological information has typical significance and good application prospect. Based on the object-oriented classification in Northern Tibet, using the Worldview2 high-resolution remote sensing data, combined with the tectonic information and image enhancement, the lithological spectral features, shape features, spatial locations and topological relations of various geological information are excavated. By setting the threshold, based on the hierarchical classification, eight kinds of geological information were classified and extracted. Compared with the existing geological maps, the accuracy analysis shows that the overall accuracy reached 87.8561%, indicating that the classification-oriented method is effective and feasible for this study area and provides a new idea for the automatic extraction of remote sensing geological informat ion.

Evaluation of Economic Linkage between Urban Built-Up Areas in a Mid-Sized City of Uyo (Nigeria)

“…One of the common techniques used to generate the object is image segmentation [46]. Segmentation is a method of dividing a satellite image into homogenous objects by merging pixels with similar spectral signatures [48,49]. Segmentation groups pixels with similar features and ensures good image classification results with better accuracy [50].…”