K. Lai, L. Bo, X. Ren, and D. Fox.

Detection-based Object Labeling in 3D Scenes

Proc. of International Conference on Robotics and Automation (ICRA), 2012



We propose a view-based approach for labeling objects in 3D scenes reconstructed from RGB-D (color+depth) videos. We utilize sliding window detectors trained from object views to assign class probabilities to pixels in every RGB-D frame. These probabilities are projected into the reconstructed 3D scene and integrated using a voxel representation. We perform efficient inference on a Markov Random Field over the voxels, combining cues from view-based detection and 3D shape, to label the scene. Our detection-based approach produces accurate scene labeling on the RGB-D Scenes Dataset and improves the robustness of object detection.


Full paper [pdf] (7 pages)


[To the RSE-lab]