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.
DynaVINS : A Visual-Inertial SLAM for Dynamic Environments
| Date | Stars |
|---|---|
| 2026-07-24 | 440 |
| 2026-07-25 | 440 |
| 2026-07-28 | 440 |
| 2026-07-30 | 440 |
| 2026-08-06 | 440 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# DynaVINS: A Visual-Inertial SLAM for Dynamic Environments
## :bookmark_tabs: About DynaVINS (IEEE RA-L'22)
* A robust **visual-inertial state estimator algorithm** for dynamic environments.
* The robust bundle adjustment is used for dynamic objects such as cars :car:, humans :runner:, buses :bus:, etc.
<p align="center"><img src=readme_resource/city_main.gif alt="animated" width="30%"/> <img src=readme_resource/parking_main.gif alt="animated" width="30%"/></p>
* Please refer our [paper][arXivlink] for detailed explanantions and experimental results\!
* The BA module validated on [VIODE dataset][VIODElink] dataset\.
* The loop closure module validated on [Our dataset][ourdatalink]\.
* Algorithm is based on [VINS\-Fusion][vinsfusionlink]\.
* Youtube video for the detailed explanation and the demo video.
[](http://www.youtube.com/watch?v=a9jXZYc4tYw "DynaVINS")
[arXivlink]: https://arxiv.org/abs/2208.11500
[VIODElink]: https://github.com/kminoda/VIODE
[ourdatalink]: http://gofile.me/4355j/tsjdofd6S
[vinsfusionlink]: https://github.com/HKUST-Aerial-Robotics/VINS-Fusion
## :heavy_plus_sign: Additional package : VINS-Fusion-SC (SwitchableConstraints)
* In our paper\, [VINS\-Fusion][vinsfusionlink] combined with [Switchable Constraints][switchpaperlink] \([git][switchgitlink]\)was compared with DynaVINS\.
* VINS-Fusion-SC, an algorithm that integrates Switchable Constraints into the loop closure module of VINS-Fusion, is also useful, so we released the algorithm.
* You can visit [here][vfsclink] to use VINS\-Fusion\-SC\.
* When using VINS-Fusion-SC for your paper, don't forget to cite our paper!:wink:
[switchpaperlink]: https://ieeexplore.ieee.org/document/6385590
[switchgitlink]: https://github.com/sswan940505/switchable\_constraints
[vfsclink]:https://github.com/url-kaist/VinsFusionSC
---
## Test Env.
This code is tested on
* Linux 18.04 LTS
* ROS Melodic
* Ceres Solver 1.14.0
* OpenCV 3.4.1
## :package: Prerequisites
The dependency of DynaVINS is equal to that of VINS-Fusion.
### 1. **Ubuntu** and **ROS**
Ubuntu 64-bit 16.04 or 18.04.
ROS Kinetic or Melodic. [ROS Installation](http://wiki.ros.org/ROS/Installation)
### 2. **Ceres Solver**
Follow [Ceres Installation](http://ceres-solver.org/installation.html).
### 3. **Support file from VINS-Fusion**
Due to the limiting file size of Github, we need **one** package and **two** files from the [VINS-Fusion repository](https://github.com/HKUST-Aerial-Robotics/VINS-Fusion/tree/master/support_files).
1. Set the `camera_models` package in your workspace, which is included in VINS-Fusion.
2. Copy `support_files/brief_k10L6.bin` in VINS-Fusion into our `support_files` folder
3. Copy `support_files/brief_pattern.yml` in VINS-Fusion into our `support_files` folder
## :building_construction: How to build
> Please follow the below commands to build DynaVINS (on ROS).
``` bash
$ cd ~/catkin_ws/src
$ git clone https://github.com/url-kaist/dynaVINS
$ cd ../
$ catkin_make
(or if you use catkin tools) catkin build
$ source ~/catkin_ws/devel/setup.bash
```
## :runner: To run the demo codes
### VIODE dataset (Only BA) examples
For convenience, we also provide `3_high.bag` file in the `parking_lot` scene. You can download the file by the following command:
```bash
$ wget https://urserver.kaist.ac.kr/publicdata/dynaVINS/VIODE_dataset/parking_lot/3_high.bag
```
* If direct download not works, download the dataset from : [Link](https://urserver.kaist.ac.kr:8148/sharing/rNg30Nh0Q)
* Other sequence of VIODE dataset can be found in original repository : https://github.com/kminoda/VIODE
Note that the larger the number of bag files in the VIODE dataset is, the more dynamic objects exist.
#### 1. **VIODE sequence with monocular camera + IMU**
``` bash
$ roslaunch dynaVINS viode_mono.launch
$ rosbag play 3_high.bag (or 0_none.bag, 1_low.bag, ...)
```
#### 2. **VIODE sequence with stereo camera + IMUExcerpt of 7,434 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:045a8b4b7fef6a19, topic:robotics, topic:slam, readme:robotics