Direct Visual-Inertial Ego-Motion Estimation via Iterated Extended Kalman Filter

By Shangkun Zhong and Pakpong Chirarattananon

Introduction

This letter proposes a reactive navigation strategyfor recovering the altitude, translational velocity and orientationof Micro Aerial Vehicles. The main contribution lies in the direct and tight fusion of Inertial Measurement Unit (IMU) measurements with monocular feedback under an assumption of a single planar scene. For more details, please refer to our RA-L paper.

Dependencies

c++11, opencv, eigen, kindr, boost, glog, gflags

Getting started

Compilation

Please run the following commands to compile the code.

mkdir build
cd build
cmake ..
make

Run

One example sequence can be downloaded here. Extract the files to the root directory of the project

unzip example_seq.zip

and run:

./build/main

Contact

If you have any questions, please contact me at 291790832@qq.com.