Deep Direct Visual Odometry

Abstract

Traditional monocular direct visual odometry (DVO) is one of the most famous methods to estimate the ego-motion of robots and map environments from images simultaneously. However, DVO heavily relies on high-quality images and accurate initial pose estimation during tracking. With the outstanding performance of deep learning, previous works have shown that deep neural networks can effectively learn 6-DoF (Degree of Freedom) poses between frames from monocular image sequences in the unsupervised manner. However, these unsupervised deep learning-based frameworks cannot accurately generate the full trajectory of a long monocular video because of the scale-inconsistency between each pose. To address this problem, we use several geometric constraints to improve the scale-consistency of the pose network, including improving the previous loss function and proposing a novel scale-to-trajectory constraint for unsupervised training. We call the pose network trained by the proposed novel constraint as TrajNet. In addition, a new DVO architecture, called deep direct sparse odometry (DDSO), is proposed to overcome the drawbacks of the previous direct sparse odometry (DSO) framework by embedding TrajNet. Extensive experiments on the KITTI dataset show that the proposed constraints can effectively improve the scale-consistency of TrajNet when compared with previous unsupervised monocular methods, and integration with TrajNet makes the initialization and tracking of DSO more robust and accurate.

arXiv comment10 pages,8 figures

References in corpus (9)

• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras
• DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks
• Monocular Depth Estimation Based On Deep Learning: An Overview
• Masked GANs for Unsupervised Depth and Pose Prediction with Scale Consistency
• Recurrent Neural Network for (Un-)supervised Learning of Monocular VideoVisual Odometry and Depth
• LDSO: Direct Sparse Odometry with Loop Closure
• Learning monocular depth estimation infusing traditional stereo knowledge
• DSVO: Direct Stereo Visual Odometry

Cited by in corpus (5)

• Monocular Depth Estimation Based On Deep Learning: An Overview
• Perception and Navigation in Autonomous Systems in the Era of Learning: A Survey
• Masked GANs for Unsupervised Depth and Pose Prediction with Scale Consistency
• GS-GVINS: A Tightly-integrated GNSS-Visual-Inertial Navigation System Augmented by 3D Gaussian Splatting
• CoFi: Coarse-to-Fine ICP for LiDAR Localization in an Efficient Long-lasting Point Cloud Map