Carnegie Mellon University
file.pdf (1.86 MB)

3-D Scene Analysis via Sequenced Predictions over Points and Regions

Download (1.86 MB)
journal contribution
posted on 2011-05-01, 00:00 authored by Xuehan Xiong, Daniel Munoz, J. Andrew Bagnell, Martial Hebert

We address the problem of understanding scenes from 3-D laser scans via per-point assignment of semantic labels. In order to mitigate the difficulties of using a graphical model for modeling the contextual relationships among the 3-D points, we instead propose a multi-stage inference procedure to capture these relationships. More specifically, we train this procedure to use point cloud statistics and learn relational information (e.g., tree-trunks are below vegetation) over fine (point-wise) and coarse (region-wise) scales. We evaluate our approach on three different datasets, that were obtained from different sensors, and demonstrate improved performance.