StreetFighter Computer Vision Project
Labelling Guidelines
Draw a bounding box (BB) around each character. The class name/label for each BB should consist of the character's name first, and then the state they are currently in. Currently, we are only annotating the following characters:
These are the states we will be looking out for:
- Idle
- Hit
- 5LP
- 5MP
- 5HP
- 5LK
- 5MK
- 5HK
- 2LP
- 2MP
- 2HP
- 2LK
- 2MK
- 2HK
- j.LP
- j.MP
- j,HP
- j.LK
- j.MK
- j.HK
- 6HP
- 4HP
- 6HK
- 4HK
So, example annotations would be as follows:
- Ryu-Idle
- Ken-5MP
- Ken-Hit
- Ryu-4HK
Be sure to annotate ALL FIGHTERS IN THE IMAGE, and to make the BBs as TIGHT AS POSSIBLE.
Current Assignments
- Femi: 5LP, 5LK, 2LP, 2LK, DO AT LEAST 150 OF EACH
- Viraj: 2MK, 2MP, 2HK, 5HP DO AT LEAST 150 OF EACH
- Kevin: 2HP, 5MK, 5MP, 5HK DO AT LEAST 150 OF EACH
Trained Model API
This project has a trained model available that you can try in your browser and use to get predictions via our Hosted Inference API and other deployment methods.
Cite This Project
If you use this dataset in a research paper, please cite it using the following BibTeX:
@misc{
streetfighter_dataset,
title = { StreetFighter Dataset },
type = { Open Source Dataset },
author = { DojoCapstoneProject },
howpublished = { \url{ https://universe.roboflow.com/dojocapstoneproject-xnq0n/streetfighter } },
url = { https://universe.roboflow.com/dojocapstoneproject-xnq0n/streetfighter },
journal = { Roboflow Universe },
publisher = { Roboflow },
year = { 2023 },
month = { dec },
note = { visited on 2024-06-26 },
}
Connect Your Model With Program Logic
Find utilities and guides to help you start using the StreetFighter project in your project.