chenfengw / visual-inertial-slam

This project contains code for visual inertial SLAM algorithm using Extended Kalman Filter.

Visual Inertial SLAM

Simultaneous localization and mapping (SLAM) is the problem of localizing the robot and creating a map of the environment at the same time. This project contains code for visual inertial SLAM algorithm using Extended Kalman Filter.

Demo

Requirements

To install requirements:

pip install -r requirements.txt

SLAM

To perform SLAM, run this script:

python slam_main.py

recommend to run this script in Python interactive.

Sensors

• Stereo camera
• IMU

Files Directory

• kalman_filter.py
  • calculating jacobain, kalman gain
• mapping.py
  • landmark and pose estimation
• sensors.py
  • IMU and stereo camera
• transform.py
  • hat map, transformation between frames

visual-inertial-slam's Issues

Dataset link

I went through your implementation. It's amazing! Can you provide the link for the dataset?