SemanticFusionSemanticFusion is a real-time visual SLAM system capable of semantically annotating a dense 3D scene using Convolutional Neural Networks. It is based on the techniques described in the following publication:

 

 

 

John McCormac, Ankur Handa, Andrew J Davison, Stefan Leutenegger. SemanticFusion: Dense 3D Semantic Mapping with Convolutional Neural Networks. IEEE International Conference on Robotics and Automation (ICRA), 2017

The SemanticFusion software is available through the following link and is free to be used for non-commercial purposes.  Full terms and conditions which govern its use are detailed here:

https://bitbucket.org/dysonroboticslab/semanticfusion/overview

Videos of this software in action are availabe in the videos section of this site.