{"id":18132629,"url":"https://github.com/apsurt/omni-geo-ai","last_synced_at":"2026-02-13T13:08:08.055Z","repository":{"id":241842324,"uuid":"807999136","full_name":"Apsurt/omni-geo-ai","owner":"Apsurt","description":"Omni Geoguessr AI: A Vision Transformer AI integrated with Geoguessr for automated geographic location prediction and gameplay using streetview panoramas.","archived":false,"fork":false,"pushed_at":"2024-07-21T19:28:32.000Z","size":499,"stargazers_count":1,"open_issues_count":7,"forks_count":1,"subscribers_count":4,"default_branch":"main","last_synced_at":"2024-07-21T21:14:03.095Z","etag":null,"topics":["ai","automated-gameplay","city-recognition","climate-classification","computer-vision","deep-learning","elevation-detection","geography","geoguessr","geolocation","google-maps-api","image-recognition","location-prediction","machine-learning","python","streetview","vision-transformer"],"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/Apsurt.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","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":"ROADMAP.md","authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-05-30T07:25:33.000Z","updated_at":"2024-07-21T19:28:35.000Z","dependencies_parsed_at":"2024-10-26T16:35:49.972Z","dependency_job_id":"1d4c6e2b-2af8-44f2-a1f1-35b9be289f02","html_url":"https://github.com/Apsurt/omni-geo-ai","commit_stats":null,"previous_names":["apsurt/omni-geo-ai"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Apsurt/omni-geo-ai","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Apsurt%2Fomni-geo-ai","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Apsurt%2Fomni-geo-ai/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Apsurt%2Fomni-geo-ai/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Apsurt%2Fomni-geo-ai/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Apsurt","download_url":"https://codeload.github.com/Apsurt/omni-geo-ai/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Apsurt%2Fomni-geo-ai/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274583707,"owners_count":25311897,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-09-11T02:00:13.660Z","response_time":74,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["ai","automated-gameplay","city-recognition","climate-classification","computer-vision","deep-learning","elevation-detection","geography","geoguessr","geolocation","google-maps-api","image-recognition","location-prediction","machine-learning","python","streetview","vision-transformer"],"created_at":"2024-11-01T13:05:09.723Z","updated_at":"2026-02-13T13:08:03.024Z","avatar_url":"https://github.com/Apsurt.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Omni Geoguessr AI (Phase 1: Data \u0026 Hemisphere Model)\n\n## Overview\nThis project focuses on building a pipeline to collect Google Street View panoramas and training a Vision Transformer (ViT) AI to predict the hemisphere (Northern/Southern) from images. This phase lays the groundwork for future geographic recognition models.\n\n## Features\n- **Automated Data Collection**: Fetches and labels panoramas using Google Street View API.\n- **Hemisphere Prediction**: ViT-B/16 model trained to classify panoramas into Northern/Southern hemispheres.\n- **Scalable Storage**: Images stored in Google Cloud Storage, metadata in PostgreSQL.\n\n## Getting Started\n### Prerequisites\n- Python 3.10+\n- PostgreSQL\n- Google Cloud account with:\n  - Street View Static API enabled\n  - Geocoding API enabled\n  - Google Cloud Storage\n\n### Installation\n1. Clone the repository:\n   ```bash\n   git clone https://github.com/Apsurt/apsurt-omni-geo-ai.git\n   cd apsurt-omni-geo-ai\n   ```\n2. Install dependencies:\n   ```bash\n   pip install -r requirements.txt\n   ```\n3. Configure environment variables:\n   ```bash\n   cp .env.example .env\n   # Add your Google API key and PostgreSQL credentials to .env\n   ```\n4. Initialize the database:\n   ```bash\n   # Create PostgreSQL database\n   createdb omni_geo_ai\n   \n   # Run the data collection script to initialize tables\n   python scripts/fetch_panoramas.py --num_images 5 --dry_run\n   ```\n\n### Usage\n#### Data Collection\nRun the panorama scraper to collect a specific number of images:\n```bash\npython scripts/fetch_panoramas.py --num_images 1000\n```\n\nAdvanced options:\n```bash\n# Control the ratio of Northern/Southern hemisphere images\npython scripts/fetch_panoramas.py --num_images 100 --north_ratio 0.7\n\n# Save collection statistics to a JSON file\npython scripts/fetch_panoramas.py --num_images 50 --output_stats stats.json\n\n# Enable verbose logging\npython scripts/fetch_panoramas.py --num_images 20 --verbose\n\n# Clear existing data before collecting new images\npython scripts/fetch_panoramas.py --num_images 50 --clear\n\n# Only clear data without collecting new images\npython scripts/fetch_panoramas.py --clear_only\n\n# Update the StreetViewClient with ~1000 cities\npython scripts/update_streetview_cities.py\n```\n\n#### Database Backup\nBackup the PostgreSQL database to Google Cloud Storage:\n```bash\npython scripts/backup_db.py\n```\n\nBackup options:\n```bash\n# Specify a different GCS bucket\npython scripts/backup_db.py --bucket my-backup-bucket\n\n# Custom backup directory path in GCS\npython scripts/backup_db.py --backup_dir database/daily\n```\n\n#### Train Hemisphere Model\n```bash\npython train.py --model vit_hemisphere --epochs 50\n```\n\n## License\nMIT License. See [LICENSE](LICENSE).\n\n## Roadmap\nSee [ROADMAP.md](ROADMAP.md) for phase details.\n\n## Contact\ntymon.becella@gmail.com","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fapsurt%2Fomni-geo-ai","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fapsurt%2Fomni-geo-ai","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fapsurt%2Fomni-geo-ai/lists"}