A Family of Quadratic Snakes for Road Extraction
The geographic information system industry would benefit from flexible automated systems capable of extracting linear structures from satellite imagery. Quadratic snakes allow global interactions between points along a contour, and are well suited to segmentation of linear structures such as roads. However, a single quadratic snake is unable to extract disconnected road networks and enclosed regions. We propose to use a family of cooperating snakes, which are able to split, merge, and disappear as necessary. We also propose a preprocessing method based on oriented filtering, thresholding, Canny edge detection, and Gradient Vector Flow (GVF) energy. We evaluate the performance of the method in terms of precision and recall in comparison to ground truth data. The family of cooperating snakes consistently outperforms a single snake in a variety of road extraction tasks, and our method for obtaining the GVF is more suitable for road extraction tasks than standard methods.
KeywordsRoad Network Active Contour Ground Truth Data Active Contour Model Initial Contour
Unable to display preview. Download preview PDF.
- 3.Fortier, A., Ziou, D., Armenakis, C., Wang, S.: Survey of work on road extraction in aerial and satellite images. Technical Report 241, Université de Sherbrooke, Quebec, Canada (1999)Google Scholar
- 8.Xu, C., Prince, J.L.: Gradient Vector Flow: A new external force for snakes. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 66–71 (1997)Google Scholar
- 9.Marikhu, R.: A GUI environment for road extraction with quadratic snakes Matlab software (2007), available at http://www.cs.ait.ac.th/~mdailey/snakes.Google Scholar
- 10.Rochery, M.: Contours actifs d’order supérieur et leur application à la détection de linéiques dans des images de télédétection. PhD thesis, Université de Nice, Sophia Antipolis — UFR Sciences (2005)Google Scholar