{"id":48203654,"url":"https://github.com/cbaezp/roulette","last_synced_at":"2026-04-04T18:29:46.415Z","repository":{"id":217590743,"uuid":"744269600","full_name":"cbaezp/roulette","owner":"cbaezp","description":"Proof of concept using a custom-trained vision model for object tracking . First step in exploring AI risks and use cases for online casinos.","archived":false,"fork":false,"pushed_at":"2024-01-21T17:09:40.000Z","size":26166,"stargazers_count":8,"open_issues_count":0,"forks_count":3,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-10-12T23:29:57.674Z","etag":null,"topics":["computer-vision","machine-learning","roulette"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/cbaezp.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2024-01-17T00:22:58.000Z","updated_at":"2025-07-31T16:25:07.000Z","dependencies_parsed_at":"2024-01-21T18:46:21.178Z","dependency_job_id":null,"html_url":"https://github.com/cbaezp/roulette","commit_stats":null,"previous_names":["cbaezp/roulette"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/cbaezp/roulette","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cbaezp%2Froulette","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cbaezp%2Froulette/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cbaezp%2Froulette/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cbaezp%2Froulette/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/cbaezp","download_url":"https://codeload.github.com/cbaezp/roulette/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cbaezp%2Froulette/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31408646,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-04T10:20:44.708Z","status":"ssl_error","status_checked_at":"2026-04-04T10:20:06.846Z","response_time":60,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["computer-vision","machine-learning","roulette"],"created_at":"2026-04-04T18:29:45.319Z","updated_at":"2026-04-04T18:29:46.386Z","avatar_url":"https://github.com/cbaezp.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Roulette Video Processor\n\n## Overview\nThis project is a proof of concept designed to explore the capabilities of computer vision in the context of object tracking. Using OpenCV and YOLO (You Only Look Once). The implementation includes `RouletteWheelTracker` and `RouletteBallTracker` for tracking the roulette wheel and ball, respectively.\n\n## Prerequisites\n- Python 3.10\n- **Important:** PyTorch must be installed before proceeding with the installation of other dependencies. Visit the [official PyTorch website](https://pytorch.org/get-started/locally/) for detailed installation instructions.\n\n## Installation\nClone the repository to your local machine:\n\n```bash\ngit clone https://github.com/cbaezp/roulette\ncd roulette\n```\n\nAfter installing PyTorch, install the remaining Python dependencies:\n\n```bash\npip install -r requirements.txt\n```\n\n## Usage\nTo run the video processing script, navigate to the repository's root directory and execute:\n\n```bash\npython roulette.py\n```\n\n### Parameters\n- `VIDEO_PATH`: Path to the input video file (e.g., `videos/roulette_test.mp4`).\n- `OUTPUT_PATH`: Path for the output video file (e.g., `output_video.mp4`).\n- Both, `RouletteWheelTracker` and `RouletteBallTracker` have additional parameters that could be updated based on the video, angle, etc.\n\n\n### Customization\nYou can customize the behavior of the trackers by modifying their initialization parameters in `roulette.py`.\n\n## Components\n### VideoProcessor\nManages the video processing pipeline, handling frame reading and writing operations.\n\n### RouletteWheelTracker\nDetects and tracks the roulette wheel in video frames.\n\n### RouletteBallTracker\nUtilizes YOLO, powered by PyTorch, for the precise tracking of the ball's position and trajectory.\n\n## Proof of Concept\nThis project demonstrates the practical application of computer vision techniques, showcasing object tracking under dynamic conditions.\n\n\n## YouTube\n[![Check out the youtube video]](https://youtu.be/bpy933SQ6Q0)\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcbaezp%2Froulette","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcbaezp%2Froulette","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcbaezp%2Froulette/lists"}