Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/ethz-asl/dynablox
Real-time detection of diverse dynamic objects in complex environments.
https://github.com/ethz-asl/dynablox
detection diverse dynablox dynamic environment mapping moving objects real-time volumetric
Last synced: 2 months ago
JSON representation
Real-time detection of diverse dynamic objects in complex environments.
- Host: GitHub
- URL: https://github.com/ethz-asl/dynablox
- Owner: ethz-asl
- License: bsd-3-clause
- Created: 2022-12-14T14:33:17.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2023-09-05T17:03:19.000Z (9 months ago)
- Last Synced: 2024-01-20T04:59:10.511Z (5 months ago)
- Topics: detection, diverse, dynablox, dynamic, environment, mapping, moving, objects, real-time, volumetric
- Language: C++
- Homepage:
- Size: 80.9 MB
- Stars: 341
- Watchers: 14
- Forks: 44
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Lists
- awesome-mobile-robotics - Dynablox - based approach for real-time detection of diverse dynamic objects in complex environments (Softwares and Libraries)
README
# Dynablox
An online volumetric mapping-based approach for real-time detection of diverse dynamic objects in complex environments.
# Table of Contents
**Credits**
* [Paper](#Paper)
* [Video](#Video)
**Setup**
* [Installation](#Installation)
* [Datasets](#Datasets)
**Examples**
- [Running a DOALS sequence](#Running-a-DOALS-sequence)
- [Running a Dynablox sequence](#Running-a-Dynablox-sequence)
- [Running and Evaluating an Experiment](#Evaluating-an-Experiment)
# Paper
If you find this package useful for your research, please consider citing our paper:
* Lukas Schmid, Olov Andersson, Aurelio Sulser, Patrick Pfreundschuh, and Roland Siegwart. "**Dynablox: Real-time Detection of Diverse Dynamic Objects in Complex Environments**" in *IEEE Robotics and Automation Letters (RA-L)*, Vol. 8, No. 10, pp. 6259 - 6266, October 2023. \[ [IEEE](https://ieeexplore.ieee.org/document/10218983) | [ArXiv](https://arxiv.org/abs/2304.10049) | [Video](https://www.youtube.com/watch?v=NA13fRWlqRQ) \]
```bibtex
@article{schmid2023dynablox,
title={Dynablox: Real-time Detection of Diverse Dynamic Objects in Complex Environments},
author={Schmid, Lukas, and Andersson, Olov, and Sulser, Aurelio, and Pfreundschuh, Patrick, and Siegwart, Roland},
booktitle={IEEE Robotics and Automation Letters (RA-L)},
year={2023},
volume={8},
number={10},
pages={6259 - 6266},
doi={10.1109/LRA.2023.3305239}}
}
```
## Video
A brief overview of the problem, approach, and results is available on youtube:
[
](https://www.youtube.com/watch?v=NA13fRWlqRQ)
# Setup
There is a [docker image](https://hub.docker.com/repository/docker/zhangkin/dynablox/general) available for this package. Check the usage in the dockerhub page.
## Installation
* **Note on Versioning:** This package was developed using Ubuntu 20.04 using ROS Noetic. Other versions should also work but support can not be guaranteed.
1. If not already done so, install [ROS](http://wiki.ros.org/action/fullsearch/melodic/Installation/Ubuntu?action=fullsearch&context=180&value=linkto%3A%22melodic%2FInstallation%2FUbuntu%22). We recommend using `Desktop-Full`.
2. If not already done so, setup a catkin workspace:
```bash
mkdir -p ~/catkin_ws/src
cd ~/catkin_ws
catkin init
catkin config --extend /opt/ros/$ROS_DISTRO
catkin config --cmake-args -DCMAKE_BUILD_TYPE=RelWithDebInfo
catkin config --merge-devel
```
2. Install system dependencies:
```bash
sudo apt-get install python3-vcstool python3-catkin-tools ros-$ROS_DISTRO-cmake-modules protobuf-compiler autoconf git rsync -y
```
3. Clone the repo using [SSH Keys](https://docs.github.com/en/authentication/connecting-to-github-with-ssh):
```bash
cd ~/catkin_ws/src
git clone [email protected]:ethz-asl/dynablox.git
```
4. Install ROS dependencies:
```bash
cd ~/catkin_ws/src
vcs import . < ./dynablox/ssh.rosinstall --recursive
```
5. Build:
```bash
catkin build dynablox_ros
```
## Datasets
To run the demos we use the [Urban Dynamic Objects LiDAR (DOALS) Dataset](https://projects.asl.ethz.ch/datasets/doku.php?id=doals).
To download the data and pre-process it for our demos, use the provided script:
```bash
roscd dynablox_ros/scripts
./download_doals_data.sh /home/$USER/data/DOALS # Or your preferred data destination.
```
We further collect a new dataset featuring diverse dynamic objects in complex scenes.
The full dataset and description ca nbe found [here](https://projects.asl.ethz.ch/datasets/doku.php?id=dynablox).
To download the processed ready-to-run data for our demos, use the provided script:
```bash
roscd dynablox_ros/scripts
./download_dynablox_data.sh /home/$USER/data/Dynablox # Or your preferred data destination.
```
# Examples
## Running a DOALS Sequence
1. If not done so, download the DOALS dataset as explained [here](#datasets).
2. Adjust the dataset path in `dynablox_ros/launch/run_experiment.launch`:
```xml
```
3. Run
```bash
roslaunch dynablox_ros run_experiment.launch
```
4. You should now see dynamic objects being detected as the sensor moves through the scene:
## Running a Dynablox Sequence
1. If not done so, download the Dynablox dataset as explained [here](#datasets).
2. Adjust the dataset path in `dynablox_ros/launch/run_experiment.launch` and set `use_doals` to false:
```xml
```
3. Run
```bash
roslaunch dynablox_ros run_experiment.launch
```
4. You should now see dynamic objects being detected as the sensor moves through the scene:
## Running and Evaluating an Experiment
### Running an Experiment
1. If not done so, download the DOALS dataset as explained [here](#datasets).
2. Adjust the dataset path in `dynablox_ros/launch/run_experiment.launch`:
```xml
```
3. In `dynablox_ros/launch/run_experiment.launch`, set the `evaluate` flag, adjust the ground truth data path, and specify where to store the generated outpuit data:
```xml
```
3. Run
```bash
roslaunch dynablox_ros run_experiment.launch
```
4. Wait till the dataset finished processing. Dynablox should shutdown automatically afterwards.
### Analyzing the Data
- **Printing the Detection Performance Metrics:**
1. Run:
```bash
roscd dynablox_ros/src/evaluation
python3 evaluate_data.py /home/$USER/dynablox_output
```
2. You should now see the performance statistics for all experiments in that folder:
```
1/1 data entries are complete.
Data object_IoU object_Precision object_Recall
hauptgebaeude_1 89.8 +- 5.6 99.3 +- 0.4 90.3 +- 5.6
All 89.8 +- 5.6 99.3 +- 0.4 90.3 +- 5.6
```
- **Inspecting the Segmentation:**
1. Run:
```bash
roslaunch dynablox_ros cloud_visualizer.launch file_path:=/home/$USER/dynablox_output/clouds.csv
```
2. You should now see the segmentation for the annotated ground truth clouds, showing True Positives (green), True Negatives (black), False Positives (blue), False Negatives (red), and out-of-range (gray) points:
- **Inspecting the Run-time and Configuration:**
Additional information is automatically stored in `timings.txt` and `config.txt` for each experiment.
### Advanced Options
* **Adding Drift to an Experiment:**
To run an experiment with drift specify one of the pre-computed drift rollouts in `dynablox_ros/launch/run_experiment.launch`:
```xml
```
All pre-computed rollouts can be found in `drift_simulation/config/rollouts`. Note that the specified sequence needs to match the data being played. For each sequence, there exist 3 rollouts for each intensity.
Alternatively, use the `drift_simulation/launch/generate_drift_rollout.launch` to create new rollouts for other datasets.
* **Changing th Configuration of Dynablox:**
All parameters that exist in dynablox are listed in `dynablox_ros/config/motion_detector/default.yaml`, feel free to tune the method for your use case!