DA-RNN: Semantic Mapping with Data Associated Recurrent Neural Networks

Yu Xiang, Dieter Fox
2017 Robotics: Science and Systems XIII  
3D scene understanding is important for robots to interact with the 3D world in a meaningful way. Most previous works on 3D scene understanding focus on recognizing geometrical or semantic properties of a scene independently. In this work, we introduce Data Associated Recurrent Neural Networks (DA-RNNs), a novel framework for joint 3D scene mapping and semantic labeling. DA-RNNs use a new recurrent neural network architecture for semantic labeling on RGB-D videos. The output of the network is
more » ... tegrated with mapping techniques such as KinectFusion in order to inject semantic information into the reconstructed 3D scene. Experiments conducted on real world and synthetic RGB-D videos demonstrate the superior performance of our method.
doi:10.15607/rss.2017.xiii.013 dblp:conf/rss/XiangF17 fatcat:5jcxse4pqndr5ln26u3w6yxodm