ordfts-hackathon-vehicles-detection
This is an example of a hackathon project making use of the pNeuma vision dataset
https://github.com/sdsc-ordes/ordfts-hackathon-vehicles-detection
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 4 DOI reference(s) in README -
✓Academic publication links
Links to: zenodo.org -
○Committers with academic emails
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (10.1%) to scientific vocabulary
Repository
This is an example of a hackathon project making use of the pNeuma vision dataset
Basic Info
- Host: GitHub
- Owner: sdsc-ordes
- License: bsd-3-clause
- Language: Jupyter Notebook
- Default Branch: main
- Size: 1.49 MB
Statistics
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 2
Metadata Files
README.md
ORD for the Sciences Hackathon - Vehicles Detection
[!CAUTION] This project is an example of a hackathon project. The quality of the data produced has not been evaluated. Its goal is to provide an example on how a dataset can be update to Hugginface.
This is an example of a hackathon project presented to ORD for the sciences hackathon using the openly available pNeuma vision dataset.
Description
The goal of this project is to create a training dataset derived from the publicly available pNeuma Vision dataset, which contains drone footage and coordinates of vehicles. By leveraging machine learning techniques, specifically the "Segment Anything" model by Meta, we will accurately segment and mask the pixels corresponding to each vehicle within the footage. The resulting dataset, stored in the efficient Parquet format, will be shared on Hugging Face as a new, open-access resource for the research community. Additionally, we will document our methodology in a detailed Jupyter notebook, which will be hosted in a public GitHub repository. Our work will be registered as a derived contribution in the pNeuma RDI Hub prototype, ensuring proper attribution and fostering further research and development.
Datasets created:
- pneuma-vision-parquet
- ordfts-hackathon-pneuma-vehicles-segmentation (doi:10.57967/hf/3028)
How is structured this repository?
- 001parquetconverter.ipynb:
- In this notebook we downloaded part of the original dataset pNeuma Vision, converted into parquet and then uploaded in Huggingface
- 002vehiclesdetection.ipynb
- Here we take the coordinates of each vehicles tagged, we cropped an region of interest around it, and use Segment Anything by Meta in order to segment the vehicle.
How to run this project in docker?
docker build -t vehicles-detection .
And then run with:
docker run -it --rm --gpus all --env-file .env odtp-whisperx
Developed by:
Developed by Carlos Vivar Rios (SDSC), as an example for the ORD for the sciences Hackathon.
Owner
- Name: Swiss Data Science Center - ORD
- Login: sdsc-ordes
- Kind: organization
- Location: Switzerland
- Repositories: 1
- Profile: https://github.com/sdsc-ordes
Open Research Data team at the Swiss Data Science Center.
Citation (citation.cff)
cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
- family-names: Vivar Rios
given-names: Carlos
orcid: https://orcid.org/0000-0002-8076-2034
title: "ORD for the sciences hackathon - Vehicles detection"
version: 0.0.1
identifiers:
- type: doi
value: 10.5281/zenodo.12751861
date-released: 2024-07-08
GitHub Events
Total
Last Year
Committers
Last synced: 10 months ago
Top Committers
| Name | Commits | |
|---|---|---|
| Carlos Vivar Rios | c****s@g****m | 10 |
Issues and Pull Requests
Last synced: 10 months ago
All Time
- Total issues: 0
- Total pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Total issue authors: 0
- Total pull request authors: 0
- Average comments per issue: 0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 0
- Pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Issue authors: 0
- Pull request authors: 0
- Average comments per issue: 0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0