Place: Large Lecture Room
Classifying 3D measurement data has become a core problem in photogrammetry and 3D computer vision, since the rise of modern multiview geometry techniques, combined with affordable range sensors. We introduce a Markov Random Field-based approach for segmenting textured meshes generated via multi-view stereo into urban classes of interest. The input mesh is first partitioned into small clusters, referred to as superfacets, from which geometric and photometric features are computed. A random forest is then trained to predict the class of each superfacet as well as its similarity with the neighboring superfacets. Similarity is used to assign the weights of the Markov Random Field pairwise-potential and to account for contextual information between the classes.
Mohammad Rouhani is Computer Scientist at Pixmap working on visual SLAM and textured surface reconstruction. His research fields overlap computer vision, graphics and machine learning. In 2012, Mohammad received a PhD degree in computer vision from the Autonomous University of Barcelona (UAB, Computer Vision Center). Mohammad has worked on various topics of computer vision in prestigious labs in Europe such as Imperial College London in UK and INRIA Grenoble and Nice in France. Mohammad has been involved on different projects including 4D motion capture, visual SLAM, surface reconstruction, deformation modeling and real-time machine learning for object detection and semantic segmentation.