ValerioSpagnoli/Monocular-Visual-Inertial-MSCKF

Multi-State Constraint Kalman Filter for Monocular Visual-Inertial Navigation.

27
/ 100
Experimental

This project helps robots, drones, or augmented reality systems understand their position and orientation in real-time, especially in environments where GPS might be unavailable or unreliable. It takes a stream of images from a single camera and simulated motion data (from an Inertial Measurement Unit, or IMU) as input. The output is a highly accurate and computationally efficient estimation of the system's movement and location, useful for navigation and spatial awareness. Robotics engineers and AR/VR developers would primarily use this.

Use this if you need precise, real-time tracking of a system's 3D pose using only a single camera and IMU, particularly in resource-constrained environments.

Not ideal if your application requires global mapping or long-term drift-free localization without any form of loop closure or external corrections.

robot-navigation augmented-reality drone-localization visual-inertial-odometry pose-estimation
No Package No Dependents
Maintenance 6 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

13

Forks

Language

Python

License

GPL-3.0

Last pushed

Oct 22, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/ValerioSpagnoli/Monocular-Visual-Inertial-MSCKF"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.