MLSS-VO: A Multi-Level Scale Stabilizer with Self-Supervised Features for Monocular Visual Odometry in Target Tracking

In this study, a multi-level scale stabilizer intended for visual odometry (MLSS-VO) combined with a self-supervised feature matching method is proposed to address the scale uncertainty and scale drift encountered in the field of monocular visual odometry. Firstly, the architecture of an instance-level recognition model is adopted to propose a feature matching model based on a Siamese neural network. Combined with the traditional approach to feature point extraction, the feature baselines on different levels are extracted, and then treated as a reference for estimating the motion scale of the camera. On this basis, the size of the target in the tracking task is taken as the top-level feature baseline, while the motion matrix parameters as obtained by the original visual odometry of the feature point method are used to solve the real motion scale of the current frame. The multi-level feature baselines are solved to update the motion scale while reducing the scale drift. Finally, the spatial target localization algorithm and the MLSS-VO are applied to propose a framework intended for the tracking of target on the mobile platform. According to the experimental results, the root mean square error (RMSE) of localization is less than 3.87 cm, and the RMSE of target tracking is less than 4.97 cm, which demonstrates that the MLSS-VO method based on the target tracking scene is effective in resolving scale uncertainty and restricting scale drift, so as to ensure the spatial positioning and tracking of the target.

WPO-Net: Windowed Pose Optimization Network for Monocular Visual Odometry Estimation

Visual odometry is the process of estimating incremental localization of the camera in 3-dimensional space for autonomous driving. There have been new learning-based methods which do not require camera calibration and are robust to external noise. In this work, a new method that do not require camera calibration called the “windowed pose optimization network” is proposed to estimate the 6 degrees of freedom pose of a monocular camera. The architecture of the proposed network is based on supervised learning-based methods with feature encoder and pose regressor that takes multiple consecutive two grayscale image stacks at each step for training and enforces the composite pose constraints. The KITTI dataset is used to evaluate the performance of the proposed method. The proposed method yielded rotational error of 3.12 deg/100 m, and the training time is 41.32 ms, while inference time is 7.87 ms. Experiments demonstrate the competitive performance of the proposed method to other state-of-the-art related works which shows the novelty of the proposed technique.

Visual odometry in local underwater navigation problems

The work processes of the ORB-SLAM algorithm are presented. The results of experimental studies on temporal comparisons of the operation of the algorithm with different parameters and cameras are presented. The necessity of forming a visual odometry (VO) system as a local navigation of remote-controlled and autonomous underwater robots has been substantiated. The two most suitable odometry methods in the underwater environment are described, such as their advantages and disadvantages. The work processes of the ORB-SLAM algorithm are presented. The results of experimental studies on temporal comparisons of the operation of the algorithm with different parameters and cameras are presented. The procedure for preparing video data is described: processing a video stream, adjusting camera parameters for calibration. The experiments represent the testing of the ORB-SLAM3 algorithm on a sample of video filmed as part of the ecological monitoring of the Caspian shelf in 2020.