ktyl
/
basalt
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
25 Commits 1 Branch 0 Tags 19 MiB
C++ 85.1%
Python 9.3%
CMake 3.8%
Shell 1.3%
C 0.3%
Other 0.2%
Go to file
Vladyslav Usenko 660155376e Update .gitlab-ci.yml 2019-04-18 09:29:31 +00:00
cmake_modules Initial commit 2019-04-14 21:08:32 +02:00
data Initial commit 2019-04-14 21:08:32 +02:00
doc Update doc/Calibration.md, doc/Simulation.md, doc/VioMapping.md files 2019-04-17 10:47:25 +00:00
docker Initial commit 2019-04-14 21:08:32 +02:00
include/basalt updated docs 2019-04-15 13:40:52 +02:00
scripts Update run_evaluations.sh 2019-04-15 20:57:26 +00:00
src Make names of the buttons consistent. 2019-04-16 12:48:08 +00:00
test Initial commit 2019-04-14 21:08:32 +02:00
thirdparty updated Readme.md 2019-04-16 08:13:21 +02:00
.clang-format Initial commit 2019-04-14 21:08:32 +02:00
.gitignore Initial commit 2019-04-14 21:08:32 +02:00
.gitlab-ci.yml Update .gitlab-ci.yml 2019-04-18 09:29:31 +00:00
.gitmodules Initial commit 2019-04-14 21:08:32 +02:00
CMakeLists.txt Change vocabulary location 2019-04-15 14:17:27 +02:00
LICENSE Initial commit 2019-04-14 21:08:32 +02:00
README.md Update README.md 2019-04-17 11:23:17 +00:00

README.md

pipeline status

Basalt

For more information see https://vision.in.tum.de/research/vslam/basalt

teaser

This project contains tools for:

  • Camera, IMU and motion capture calibration.
  • Visual-inertial odometry and mapping.
  • Simulated environment to test different components of the system.

Some reusable components of the system are availble as a separate header-only library.

Related Publications

Visual-Inertial Odometry and Mapping:

  • Visual-Inertial Mapping with Non-Linear Factor Recovery, V. Usenko, N. Demmel, D. Schubert, J. Stückler, D. Cremers, In [arXiv:1904.06504].

Calibration (explains implemented camera models):

Calibration (demonstrates how these tools can be used for dataset calibration):

  • The TUM VI Benchmark for Evaluating Visual-Inertial Odometry, D. Schubert, T. Goll, N. Demmel, V. Usenko, J. Stückler, D. Cremers, In 2018 International Conference on Intelligent Robots and Systems (IROS), [DOI:10.1109/IROS.2018.8593419], [arXiv:1804.06120].

Installation

APT installation for Ubuntu 16.04 and 18.04 (Fast)

Set up keys

sudo apt-key adv --keyserver keyserver.ubuntu.com --recv-keys 0D97B6C9

Add the repository to the sources list. On Ubuntu 18.04 run:

sudo sh -c 'echo "deb [arch=amd64] http://packages.usenko.eu/ubuntu bionic main" > /etc/apt/sources.list.d/basalt.list'

On Ubuntu 16.04 run:

sudo sh -c 'echo "deb [arch=amd64] http://packages.usenko.eu/ubuntu xenial main" > /etc/apt/sources.list.d/basalt.list'

Update the Ubuntu package index and install Basalt:

sudo apt-get update
sudo apt-get install basalt

Source installation for Ubuntu 18.04 and MacOS 10.14 Mojave

Clone the source code for the project and build it. For MacOS you should have Homebrew installed.

git clone --recursive https://gitlab.com/VladyslavUsenko/basalt.git
cd basalt
./scripts/install_deps.sh
mkdir build
cd build
cmake .. -DCMAKE_BUILD_TYPE=RelWithDebInfo
make -j8

NOTE: It is possible to compile the code on Ubuntu 16.04, but you need to install cmake-3.10 or higher and gcc-7. See corresponding Dockerfile as an example.

Usage

Licence

The code is provided under a BSD 3-clause license. See the LICENSE file for details. Note also the different licenses of thirdparty submodules.