Indoor 3D Semantic Robot VSLAM Based on Mask Regional Convolutional Neural Network

Indoor 3D Semantic Robot VSLAM Based on Mask Regional Convolutional Neural Network

During the construction of indoor environmental semantic maps by robot Vision SLAM (VSLAM), there exist some problems such as low label classification accuracy and low precision under the situation of sparse feature points. In this case, this paper proposes an indoor three-dimensional semantic VSLAM...

Full description

Bibliographic Details
Main Authors: Chongben Tao, Zhen Gao, Jinli Yan, Chunguang Li, Guozeng Cui
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
VSLAM
deep learning
target detection
instance segmentation
semantic map
Online Access:https://ieeexplore.ieee.org/document/9040422/

Internet

https://ieeexplore.ieee.org/document/9040422/

Similar Items