集成RGB-D语义分割网络的室内语义地图构建.

At present, the research on combining deep learning with Visual SLAM(Simultaneous Localization And Mapping) to construct indoor 3 D pointcloud semantic map is in full swing. In order to solve the problems that traditional Visual SLAM networks have low accuracy and poor speed and lack semantic information, this paper proposed a novel RGB-D semantic segmentation network. The network uses the depth information which less affected by the light in indoor scenes to improve the accuracy of segmentation, and meanwhile designs the lightweight multi-scale residual module(MRAM) and Atrous Spatial Pyramid Pooling(ASPP) module to lightweight the segmentation network and improve the segmentation accuracy. Firstly, ORB-SLAM2 network screens the input image sequences to obtain keyframes. Then, the keyframes go into the proposed semantic segmentation network to get the 2 D semantic label, and then map the 2 D semantic information to 3 D pointcloud space. Finally, the method uses the Bayesian algorithm to update the 3 D map to obtain the globally consistent 3 D pointcloud semantic map. The experiments adopt NYUv2 dataset to verify the performance of semantic segmentation network, and adopt TUM dataset construct pointcloud semantic map. The results show that the performance and speed of the semantic segmentation network in this paper are better than the existing models, and the combination of semantic segmentation network with visual SLAM can meet the requirements of constructing 3 D dense semantic pointcloud map accurately and quickly. [ABSTRACT FROM AUTHOR]