A higher-order active contour model for tree detection

Horvath, P.; Jermyn, I.H.; Kato, Z.; Zerubia, J.

Abstract

We present a model of a `gas of circles', the ensemble of regions in the image domain consisting of an unknown number of circles with approximately fixed radius and short range repulsive interactions, and apply it to the extraction of tree crowns from aerial images. The method uses the recently introduced `higher order active contours' (HOACs), which incorporate long-range interactions between contour points, and thereby include prior geometric information without using a template shape. This makes them ideal when looking for multiple instances of an entity in an image. We study an existing HOAC model for networks, and show via a stability calculation that circles stable to perturbations are possible for constrained parameter sets. Combining this prior energy with a data term, we show results on aerial imagery that demonstrate the effectiveness of the method and the need for prior geometric knowledge. The model has many other potential applications.

Citation

Horvath, P., Jermyn, I., Kato, Z., & Zerubia, J. (2006, August). A higher-order active contour model for tree detection. Presented at 18th International Conference on Pattern Recognition (ICPR'06), Hong Kong

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 18th International Conference on Pattern Recognition (ICPR'06)
• Publication Date: Aug 1, 2006
• Deposit Date: Aug 12, 2011
• Publicly Available Date: Apr 22, 2016
• Volume: 4
• Pages: 130-133
• Series ISSN: 1051-4651
• Book Title: 18th International Conference on Pattern Recognition
• DOI: https://doi.org/10.1109/icpr.2006.79
• Public URL: https://durham-repository.worktribe.com/output/1697520