Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
LV-DOT: LiDAR-Visual Dynamic Obstacle Detection and Tracking (C++/Python/ROS)
| Date | Stars |
|---|---|
| 2026-07-24 | 472 |
| 2026-07-25 | 472 |
| 2026-07-28 | 473 |
| 2026-07-30 | 473 |
| 2026-08-06 | 473 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# LV-DOT: LiDAR-Visual Dynamic Obstacle Detection and Tracking for Autonomous Robots
[](https://wiki.ros.org/noetic)
[](https://releases.ubuntu.com/20.04/)
[](https://opensource.org/licenses/MIT)
[](https://releases.ubuntu.com/20.04/)
[](https://releases.ubuntu.com/20.04/)
This repository implements the LiDAR-visual Dynamic Obstacle Detection and Tracking (LV-DOT) framework which aims at detecting and tracking dynamic obstacles for robots with extremely constraint computational resources.
<table>
<tr>
<td><img src="media/LV-DOT-demo1.gif" style="width: 100%;"></td>
<td><img src="media/LV-DOT-demo2.gif" style="width: 100%;"></td>
</tr>
<tr>
<td><img src="media/LV-DOT-demo3.gif" style="width: 100%;"></td>
<td><img src="media/LV-DOT-demo4.gif" style="width: 100%;"></td>
</tr>
</table>
The LV-DOT framework supports dynamic obstacle detection and tracking with multiple sensor configurations:
- Camera-only mode.
- LiDAR-only mode.
- Combined LiDAR and camera mode.
For additional details, please refer to the related paper available here:
Zhefan Xu\*, Haoyu Shen\*, Xinming Han, Hanyu Jin, Kanlong Ye, and Kenji Shimada, "LV-DOT: LiDAR-visual dynamic obstacle detection and tracking for autonomous robot navigation”, arXiv, 2025. [\[preprint\]](https://arxiv.org/pdf/2502.20607) [\[YouTube\]](https://youtu.be/rRvgTulWqvk) [\[BiliBili\]](https://www.bilibili.com/video/BV1qC9GY6EHj/?share_source=copy_web&vd_source=1333db331406abb1b5d4cece1e253427)
*The authors contributed equally.
## News
- **2025-02-28:** The GitHub code, video demos, and relavant papers for our LV-DOT framework are released. The authors will actively maintain and update this repo!
## Table of Contents
- [Installation Guide](#I-Installation-Guide)
- [Run Demo](#II-Run-Demo)
- [Run on dataset](#a-Run-on-dataset)
- [Run on your device](#b-Run-on-your-device)
- [LV-DOT Framework and Results](#III-LV-DOT-Framework-and-Results)
- [Citation and Reference](#IV-Citation-and-Reference)
- [Acknowledgement](#V-Acknowledgement)
## I. Installation Guide
The system requirements for this repository are as follows. Please ensure your system meets these requirements:
- Ubuntu 18.04/20.04 LTS
- ROS Melodic/Noetic
This package has been tested on the following onboard computer:
- [NVIDIA Jetson Xavier NX](https://www.nvidia.com/en-us/autonomous-machines/embedded-systems/jetson-xavier-series/)
- [NVIDIA Jetson Orin NX](https://www.nvidia.com/en-us/autonomous-machines/embedded-systems/jetson-orin/)
- [Intel NUC](https://www.intel.com/content/www/us/en/products/details/nuc.html)
Please follow the instructions below to install this package.
```
# This package needs ROS vision_msgs package
sudo apt install ros-noetic-vision-msgs
# Install YOLOv11 required package
pip install ultralytics
cd ~/catkin_ws/src
git clone https://github.com/Zhefan-Xu/LV-DOT.git
cd ..
catkin_make
```
## II. Run Demo
### a. Run on dataset
Please download the rosbag file from this [link](https://cmu.box.com/s/cucvje5b9xfpdpe57ilh0jx702b3ks2p):
```
rosbag play -l corridor_demo.bag
roslaunch onboard_detector run_detector.launch
```
The perception results can be visualized in Rviz as follows:
https://github.com/user-attachments/assets/e640edab-d4f3-40d6-88dc-9e5014430732
### b. Run on your device
Please adjust the configuration file under ```cfg/detector_param.yaml``` of your LiDAR and camera device. Also, change the color image topic name in ```scripts/yolo_detector/yolov11_detector.py```
From the parameter file, you can find that the algorithm expects the following data from the robot:
- LiDAR Point Cloud: ```/pointcloud``Excerpt of 6,210 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:bda56aefc3e2b758, topic:object-detection, topic:object-tracking
matched fp:bda56aefc3e2b758, topic:robotics, topic:ros