Dense Real-Time Mapping of Object-Class Semantics from RGB-D Video

Jorg Stuckler, Benedikt Waldvogel, Hannes Schulz, Sven Behnke
Computer Science Insitute VI, Autonomous Intelligent Systems, University of Bonn, Germany
Journal of Real-Time Image Processing, 2014


   title={Dense real-time mapping of object-class semantics from RGB-D video},

   author={St{"u}ckler, J{"o}rg and Waldvogel, Benedikt and Schulz, Hannes and Behnke, Sven},

   journal={Journal of Real-Time Image Processing},





Download Download (PDF)   View View   Source Source   



We propose a real-time approach to learning semantic maps from moving RGB-D cameras. Our method models geometry, appearance, and semantic labeling of surfaces. We recover camera pose using simultaneous localization and mapping while concurrently recognizing and segmenting object classes in the images. Our object-class segmentation approach is based on random decision forests and yields a dense probabilistic labeling of each image. We implemented it on GPU to achieve a high frame rate. The probabilistic segmentation is fused in octree-based 3D maps within a Bayesian framework. In this way, image segmentations from various view points are integrated within a 3D map which improves segmentation quality.We evaluate our system on a large benchmark dataset and demonstrate state-of-the-art recognition performance of our object-class segmentation and semantic mapping approaches.
Rating: 2.5/5. From 1 vote.
Please wait...

Recent source codes

* * *

* * *

HGPU group © 2010-2023 hgpu.org

All rights belong to the respective authors

Contact us: