Data

Tools

Indexes

Applications

Experiments

Open Source Science

mask-ukf

Instance Segmentation Aided 6D Object Pose and Velocity Tracking using an Unscented Kalman Filter

https://github.com/hsp-iit/mask-ukf

Science Score: 67.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ✓
    DOI references
    Found 7 DOI reference(s) in README
  • ✓
    Academic publication links
    Links to: frontiersin.org, zenodo.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (11.3%) to scientific vocabulary

Keywords

6-dof 6d-object-tracking 6d-pose-estimation 6d-pose-tracking gaussian-filter kalman-filter manipulation mask-ukf maskukf object-pose-estimation object-pose-tracking segmentation ycb ycb-video
Last synced: 6 months ago · JSON representation ·

Repository

Instance Segmentation Aided 6D Object Pose and Velocity Tracking using an Unscented Kalman Filter

Basic Info
  • Host: GitHub
  • Owner: hsp-iit
  • License: gpl-2.0
  • Language: C++
  • Default Branch: master
  • Homepage:
  • Size: 908 KB
Statistics
  • Stars: 33
  • Watchers: 8
  • Forks: 9
  • Open Issues: 0
  • Releases: 7
Topics
6-dof 6d-object-tracking 6d-pose-estimation 6d-pose-tracking gaussian-filter kalman-filter manipulation mask-ukf maskukf object-pose-estimation object-pose-tracking segmentation ycb ycb-video
Created over 6 years ago · Last pushed almost 3 years ago
Metadata Files
Readme License Citation

README.md

MaskUKF

An Instance Segmentation Aided Unscented Kalman Filter for 6D Object Pose and Velocity Tracking

Frontiers in Robotics and AI
Paper | Video

DOI CI badge

Reproducing the experiments

We support running the experiments via the provided Docker image.

If you want to install the repository manually, please refer to the recipe contained in the Dockerfile.

  1. Pull the docker image: console docker pull ghcr.io/hsp-iit/mask-ukf:latest
  2. Launch the container: console docker run -it --rm --user user --env="DISPLAY" --net=host ghcr.io/hsp-iit/mask-ukf:latest
  3. Clone and build the project: console git clone https://github.com/hsp-iit/mask-ukf.git cd mask-ukf mkdir build && cd build cmake ../ make
  4. Download and unzip the accompanying data DOI and the YCB-Video model set: console cd /home/user/mask-ukf bash misc/download_accompanying_data.sh bash misc/download_ycb_models.sh
  5. Run the experiments (optional): console cd /home/user/mask-ukf bash test/test_all.sh > The accompanying data contains the pre-evaluated results. If desired, the results can be re-evaluated using the above command.
  6. Run the evaluation: console cd /home/user/mask-ukf bash evaluation/evaluate_<mask_set>_<metric>_<algorithm>.sh > <mask_set> can be mrcnn (Mask R-CNN) or posecnn (PoseCNN), <metric> can be add_s (ADD-S) or rmse (RMSE) and <algorithm> can be empty (MaskUKF), icp (ICP) or densefusion (DenseFusion).
  7. Visualize the results: console cd /home/user/mask-ukf python3 evaluation/renderer/renderer.py --algorithm <algorithm> --mask_set <mask_set> --object <object_name> --video_id <video_id> > <algorithm> can be mask-ukf (MaskUKF), icp (ICP) or dense_fusion (DenseFusion), <mask_set> is as above, <object_name> is e.g. 002_master_chef_can and <video_id> is the YCB-Video video id, e.g. 0048.

In order to run the visualizer it could be required to temporarily execute xhost + in a console outside of Docker in order to allow the container accessing the X server facilities. The command can be run even after the container has been already launched.

Citing MaskUKF

If you find the MaskUKF code useful, please consider citing the associated publication:

bibtex @ARTICLE{10.3389/frobt.2021.594583, AUTHOR={Piga, Nicola A. and Bottarel, Fabrizio and Fantacci, Claudio and Vezzani, Giulia and Pattacini, Ugo and Natale, Lorenzo}, TITLE={MaskUKF: An Instance Segmentation Aided Unscented Kalman Filter for 6D Object Pose and Velocity Tracking}, JOURNAL={Frontiers in Robotics and AI}, VOLUME={8}, PAGES={38}, YEAR={2021}, URL={https://www.frontiersin.org/article/10.3389/frobt.2021.594583}, DOI={10.3389/frobt.2021.594583}, ISSN={2296-9144} }

and/or the repository itself by pressing on the Cite this respository button in the About section.

Maintainer

This repository is maintained by:

| | | |:---:|:---:| | | @xenvre |

Owner

  • Name: Humanoid Sensing and Perception
  • Login: hsp-iit
  • Kind: organization
  • Location: Istituto Italiano di Tecnologia

Humanoid Sensing and Perception research group within IIT.

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
- family-names: "Piga"
  given-names: "Nicola Agostino"
  orcid: "https://orcid.org/0000-0003-3183-8108"
- family-names: "Bottarel"
  given-names: "Fabrizio"
  orcid: "https://orcid.org/0000-0002-9377-8553"
- family-names: "Fantacci"
  given-names: "Claudio"
  orcid: "https://orcid.org/0000-0002-9980-3617"
- family-names: "Vezzani"
  given-names: "Giulia"
  orcid: "https://orcid.org/0000-0002-4151-6447"
- family-names: "Pattacini"
  given-names: "Ugo"
  orcid: "https://orcid.org/0000-0001-8754-1632"
- family-names: "Natale"
  given-names: "Lorenzo"
  orcid: "https://orcid.org/0000-0002-8777-5233"
title: "mask-ukf"
version: v1.2.0
doi: 10.5281/zenodo.5448471
date-released: 2022-07-17
url: "https://github.com/hsp-iit/mask-ukf"

GitHub Events

Total
Last Year