DeepSLAM: A Robust Monocular SLAM System With Unsupervised Deep Learning
- 25 March 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 68 (4) , 3577-3587
Abstract
In this paper, we propose DeepSLAM, a novel unsupervised deep learning-based visual Simultaneous Localization and Mapping (SLAM) system. The DeepSLAM training is fully unsupervised since it only requires stereo imagery instead of annotating ground-truth poses. Its testing takes a monocular image sequence as the input. Therefore, it is a monocular SLAM paradigm. DeepSLAM consists of several essential components, including Mapping-Net, Tracking-Net, Loop-Net and a graph optimization unit. Specifically, the Mapping-Net is an encoder and decoder architecture for describing the 3D structure of the environment while the Tracking-Net is a Recurrent Convolutional Neural Network (RCNN) architecture for capturing the camera motion. The Loop-Net is a pre-trained binary classifier for detecting loop closures. DeepSLAM can simultaneously generate pose estimate, depth map and outlier rejection mask. We evaluate its performance on various datasets, and find that DeepSLAM achieves good performance in terms of pose estimation accuracy, and is robust in some challenging scenes.Keywords
Funding Information
- National Natural Science Foundation of China (61903377)
- Engineering and Physical Sciences Research Council
- Artificial Intelligence Offshore Robotics for Certification of Assets (EP/R026173/1)
- EU H2020 Program under EUMarineRobots Project (731103)
- DeepField Project (857339)
This publication has 36 references indexed in Scilit:
- Modelling uncertainty in deep learning for camera relocalization2016
- Unsupervised learning to detect loops using deep neural networks for visual SLAM systemAutonomous Robots, 2015
- Exploring Representation Learning With CNNs for Frame-to-Frame Ego-Motion EstimationIEEE Robotics and Automation Letters, 2015
- PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization2015
- ORB-SLAM: A Versatile and Accurate Monocular SLAM SystemIEEE Transactions on Robotics, 2015
- Fast relocalisation and loop closing in keyframe-based SLAM2014
- DTAM: Dense tracking and mapping in real-time2011
- Parallel Tracking and Mapping for Small AR Workspaces2007
- MonoSLAM: Real-Time Single Camera SLAMIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004