Knowledge-Based Object Oriented Land Use Classification Using WorldView-2 Images
Abstract:Accurate land use information is the basis and premise for land use survey and management. So, it is very important to improve the accuracy of the Land use automatic classification and decrease the manual post processing In recent years as the applications of high spatial resolution remotely sensed images becoming more and more extensive object oriented classification techniques correspondingly, have been developed rapidly In this paper a knowledge-based method is produced using spectral features texture features derived from the gray-level co-occurrence or differential matrix and the prior classification experience. Moreover, the combination of two different classifiers and the construction of hierarchical classification system are achieved. High-resolution remotely sensed data WorldView-2 covering a rural area in Shunyi District in Beijing is chosen as the study area, and the total accuracy increases from 83.1% to 92.3%. The results show that the deficiencies of methods in which only one classifier is used can be evidently reduced by the proposed method the problem of similar spectral in multispectral images can be effectively solved and relatively higher classification accuracy is reached.
Document Type: Research Article
Publication date: January 1, 2012
More about this publication?
- The growing interest and activity in the field of sensor technologies requires a forum for rapid dissemination of important results: Sensor Letters is that forum. Sensor Letters offers scientists, engineers and medical experts timely, peer-reviewed research on sensor science and technology of the highest quality. Sensor Letters publish original rapid communications, full papers and timely state-of-the-art reviews encompassing the fundamental and applied research on sensor science and technology in all fields of science, engineering, and medicine. Highest priority will be given to short communications reporting important new scientific and technological findings.
- Editorial Board
- Information for Authors
- Subscribe to this Title
- Terms & Conditions
- Ingenta Connect is not responsible for the content or availability of external websites