https://github.com/tiev-tongji/LIMOT
A Tightly-Coupled System for LiDAR-Inertial Odometry and Multi-Object Tracking.
https://github.com/tiev-tongji/LIMOT
lidar-inertial-odometry multi-object-tracking
Last synced: over 1 year ago
JSON representation
A Tightly-Coupled System for LiDAR-Inertial Odometry and Multi-Object Tracking.
- Host: GitHub
- URL: https://github.com/tiev-tongji/LIMOT
- Owner: tiev-tongji
- License: bsd-3-clause
- Created: 2023-09-11T05:27:42.000Z (almost 3 years ago)
- Default Branch: main
- Last Pushed: 2024-07-08T17:13:35.000Z (almost 2 years ago)
- Last Synced: 2024-10-19T05:16:22.221Z (over 1 year ago)
- Topics: lidar-inertial-odometry, multi-object-tracking
- Language: C++
- Homepage: https://ieeexplore.ieee.org/abstract/document/10538416
- Size: 6.98 MB
- Stars: 75
- Watchers: 7
- Forks: 8
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# LIMOT
* A tightly-coupled multi-object tracking and LiDAR-inertial odometry system, allowing for joint estimation of the poses of both the ego-vehicle and surrounding objects.
## Dependency
We developed LIMOT on Ubuntu 20.04.
- [ROS](http://wiki.ros.org/ROS/Installation) (Noetic)
```
sudo apt-get install -y ros-noetic-navigation
sudo apt-get install -y ros-noetic-robot-localization
sudo apt-get install -y ros-noetic-robot-state-publisher
```
- [gtsam](https://gtsam.org/get_started/) (Georgia Tech Smoothing and Mapping library, recommended 4.0.3)
```
sudo add-apt-repository ppa:borglab/gtsam-release-4.0
sudo apt install libgtsam-dev libgtsam-unstable-dev
```
## Install
Use the following commands to download and compile the package.
```
mkdir -p ~/limot_ws/src
cd ~/limot_ws/src
git clone https://github.com/tiev-tongji/LIMOT.git
cd ..
catkin_make -j
```
## Run the package
1. Run the launch file:
```
source devel/setup.bash
roslaunch limot run_kitti.launch
```
2. Run your object detector, which subscribes to LiDAR scans and publishes the detection results with the formats:
[timestamp, [type, x, y, z, l, w, h, yaw, score], ...,[type ,x, ..., score]].
3. Play existing bag files:
```
rosbag play your-bag.bag
```
## Sample dataset
* Download the KITTI tracking dataset to test the functionality of the LIMOT. The dataset below are configured to run using the [params_kitti.yaml](./config/params_kitti.yaml):
- **KITTI tracking dataset:** [[Google Drive](https://drive.google.com/drive/folders/144Kp2WYfHIF6SbKHDCtjTswOk2E1_gPg?usp=sharing)]
* Download the self-collected dataset to test the functionality of the LIMOT. The dataset below are configured to run using the [params_hdl64.yaml](./config/params_hdl64.yaml):
- **Self-collected dataset:** [[Google Drive](https://drive.google.com/drive/folders/1-30POMAEe8F7kGfUjNHDNh8gOYRHjOt2?usp=sharing)]
## Paper
* LIMOT has been accepted by IEEE Robotics and Automation Letters.
```
@article{zhu2024limot,
title={LIMOT: a tightly-coupled system for LiDAR-inertial odometry and multi-object tracking},
author={Zhu, Zhongyang and Zhao, Junqiao and Huang, Kai and Tian, Xuebo and Lin, Jiaye and Ye, Chen},
journal={IEEE Robotics and Automation Letters},
year={2024},
publisher={IEEE}
}
```
* Our previous work DL-SLOT has been accepted by the IEEE Transactions on Intelligent Vehicles.
```
@article{tian2023dl,
title={DL-SLOT: Tightly-Coupled Dynamic LiDAR SLAM and 3D Object Tracking Based on Collaborative Graph Optimization},
author={Tian, Xuebo and Zhu, Zhongyang and Zhao, Junqiao and Tian, Gengxuan and Ye, Chen},
journal={IEEE Transactions on Intelligent Vehicles},
year={2023},
publisher={IEEE}
}
```
## Acknowledgments
Thanks for LOAM(J. Zhang and S. Singh. LOAM: Lidar Odometry and Mapping in Real-time) and [LIO-SAM](https://github.com/TixiaoShan/LIO-SAM).