Semiautomatic right-angle building extraction from very high-resolution aerial images using graph cuts with star shape constraint and regularization
Abstract
This paper proposes a method of semiautomatic right-angle building extraction from very high resolution (VHR) aerial images, based on graph cuts with star shape constraint and regularization. In the proposed method, first, the image block containing the target building is obtained by a seed line from humans. Next, the image block is preprocessed by bilateral filtering and then the simple linear iterative clustering oversegmentation method was used to segment the image into small regions. Then regions that contain the pixels belonging to the seed line are merged as the foreground area, and the background area is automatically composed by annular regions near the imagery boundary. With the obtained foreground and background areas, the graph cuts model with the star shape prior is used to acquire the building object. Finally, we defined a method of detecting the building orientation and proposed a regularizing building method based on the corners and the building orientation. The experiments performed on two VHR aerial images demonstrate the accuracy and stability of the proposed method.
- Publication:
-
Journal of Applied Remote Sensing
- Pub Date:
- April 2018
- DOI:
- 10.1117/1.JRS.12.026005
- Bibcode:
- 2018JARS...12b6005Z