Please use this identifier to cite or link to this item:
|Title:||Automatic 3d building extraction from stereo Ikonos images||Authors:||Xiong, Z.
|Issue Date:||2006||Citation:||Xiong, Z.,Zhang, Y. (2006). Automatic 3d building extraction from stereo Ikonos images. American Society for Photogrammetry and Remote Sensing - Annual Conference of the American Society for Photogrammetry and Remote Sensing 2006: Prospecting for Geospatial Information Integration 3 : 1649-1658. ScholarBank@NUS Repository.||Abstract:||In 3D GIS research and development, how to effectively acquire and input a large amount of 3D buildings is always a tough challenge. To date, as the most stable and accurate method, through a photogrammetric instrument, manually measuring buildings one by one, is really a tiring and time-consuming work. Therefore, many researchers have been trying to develop semi-automatic building extraction method or even completely automatic building extraction methods. In this paper we introduce a new method of automatic 3D building extraction based on stereo Ikonos images. This method includes several steps, such as edge detection and connection, building block detection and corner detection, and building extraction and image matching. The final result is 3D coordinates of buildings. We used a scene of stereo images to test our program. Only about 15 minutes were needed to process a scene of Ikonos image (2613 by 3539 pixels). The final result is reported. Corresponding discussions are conducted and conclusions are given based on the test results and discussions.||Source Title:||American Society for Photogrammetry and Remote Sensing - Annual Conference of the American Society for Photogrammetry and Remote Sensing 2006: Prospecting for Geospatial Information Integration||URI:||http://scholarbank.nus.edu.sg/handle/10635/116696||ISBN:||9781604237290|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on Sep 21, 2023
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.