Recovering Line-networks in Images by Junction-Point Processes

Dengfeng Chai (1) , Wolfgang Forstner (2) , Florent Lafarge (3)

1 Zhejiang University
2 Universität Bonn = University of Bonn
3 TITANE - Geometric Modeling of 3D Environments

The automatic extraction of line-networks from images is a well-known computer vision issue. Appearance and shape considerations have been deeply explored in the literature to improve accuracy in presence of occlusions, shadows, and a wide variety of irrelevant objects. However most existing works have ignored the structural aspect of the problem. We present an original method which provides structurally-coherent solutions. Contrary to the pixel-based and object-based methods, our result is a graph in which each node represents either a connection or an ending in the line-network. Based on stochastic geometry, we develop a new family of point processes consisting in sampling junction-points in the input image by using a Monte Carlo mechanism. The quality of a configuration is measured by a probability density which takes into account both image consistency and shape priors. Our experiments on a variety of problems illustrate the potential of our approach in terms of accuracy, flexibility and efficiency.

Domaines: Mathématique discrète [cs.DM]

Dengfeng Chai, Wolfgang Forstner, Florent Lafarge. Recovering Line-networks in Images by Junction-Point Processes. Computer Vision and Pattern Recognition (CVPR), Jun 2013, Portland, United States. ⟨hal-00814262⟩