MEGHÍVÓ
A Villamosmérnöki és Információs Rendszerek Tanszék
március 5-én (kedden) 15 órakor tanszéki szemináriumot tart
Low- and High-level Methods for Optical Tree Segmentation
címmel.
Előadó: Karim Ben Alaya (Képfeldolgozás Kutatólaboratórium)
A szeminárium helye: I épület, II. emelet, 214. terem
The detection/recognition of trees (trunks and braches) from 2D images is a challenging task in image processing. The large variety of visual appearance, occlusion makes it an ill-posed problem. In our work we overview different approaches to solve this problem including the performance analysis of a pixel-level clustering and a deep neural network based approach. Besides discussing low-level approaches we proceed from low-level (pixel-level) representations to a high-level model using graphs. Thus the problem is transformed to fitting graph structures to 2D images based on appearance, and on prior information about trees. We use Reversible Jump Markov Chain Monte Carlo optimization to solve the energy optimization problem corresponding to the maximization of the probability of the graph model. Besides the color information (which is modeled by Gaussian mixtures) other properties (such as width and direction of branches) are coded by different energy terms corresponding to probability.
Minden érdeklődőt szeretettel várunk!