Large-Scale Dense Mapping System Based on Visual-Inertial Odometry and Densely Connected U-Net
- 28 February 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-16
Abstract
Simultaneous localization and mapping (SLAM)-based 3-D reconstruction system mainly relies on visual odometry, which uses detailed scanning to obtain better reconstruction results. Among the feature-based SLAM methods, it is difficult to have good reconstruction results where features are missing even when the camera moves slowly. For the direct methods, when exposure changes and blurring occurs, tracking loss will cause unsatisfactory reconstruction effects. This article proposes a large-scale mapping system based on visual-inertial odometry (VIO) to solve these problems. The combination of vision and inertial measurement unit (IMU) is used to constrain the trajectory estimation in areas where the corners are missing. The system supports depth both obtained by the depth camera and estimated by the neural network. According to the voxel hash mechanism, we only focus on the voxels within the cutoff distance and use the hash table to represent the voxels sparsely to reduce the memory usage. Experiments show that the proposed system can obtain an ideal 3-D reconstruction model.Keywords
Funding Information
- National Natural Science Foundation of China (61873176)
- Natural Science Foundation of Jiangsu Province, China (BK20181433)
- Tang Scholar of Soochow University
This publication has 56 references indexed in Scilit:
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- ORB-SLAM: A Versatile and Accurate Monocular SLAM SystemIEEE Transactions on Robotics, 2015
- Towards unified depth and semantic prediction from a single image2015
- Fully convolutional networks for semantic segmentation2015
- Real-time large-scale dense RGB-D SLAM with volumetric fusionThe International Journal of Robotics Research, 2014
- Real-time 3D reconstruction at scale using voxel hashingACM Transactions on Graphics, 2013
- Robust real-time visual odometry for dense RGB-D mapping2013
- KinectFusion2011
- Shape and motion from image streams under orthography: a factorization methodInternational Journal of Computer Vision, 1992
- Determining optical flowArtificial Intelligence, 1981