GPSが使えない環境でドローンを自律飛行させるとき、慣性航法（INS）単独では数秒でドリフトが蓄積します。カメラとIMUを密結合で融合するVIO（Visual-Inertial Odometry）は、この問題をエレガントに解決します。その仕組みと実装の実際を解説します。 ¥100,000 ...

New in iOS 11, devices with at least an A9 chip (incorporating the M9 Core Motion coprocessor, a base of more than 380 million iPhone 6s and later phones and newer iPads) can track motion sensor data ...

This report documents the complete process of implementing and evaluating monocular visual odometry using the ORB-SLAM3 framework on the HKisland_GNSS03 UAV aerial photography dataset. By modifying ...

Demonstration of different visual-inertial odometry methods: (a) traditional VIO methods, which rely on handcrafted features and geometry-based optimization; (b) existing deep learning-based methods, ...

Abstract: Visual-inertial odometry (VIO) serves as a dominant framework for real-time motion state estimation in micro aerial vehicles (MAVs). However, existing VIO techniques remain highly ...

@article{teed2023deep, title={Deep Patch Visual Odometry}, author={Teed, Zachary and Lipson, Lahav and Deng, Jia}, journal={Advances in Neural Information Processing ...

Mobile real-time systems require an estimate of their movement. This can be determined from odometry or different kind of sensors, including cameras. The change in the camera image between successive ...

Let’s face it: 3-dimensional odometry can be a computationally expensive problem often requiring expensive 3D cameras and optimized algorithms that can be difficult to wrap our head around.

Abstract: The reprojection error in Visual-Inertial Odometry (VIO) suffers from high nonlinearity due to perspective division, which degrades estimator consistency ...

On the 21st of March 2025, M.Sc. Niclas Joswig defends his PhD thesis on Robust Visual Odometry under Feature-Sparse Conditions. The thesis is related to research done in the Department of Computer ...