{"id":49543744,"url":"https://github.com/zaabola/projet_mining_pollution","last_synced_at":"2026-05-02T17:01:28.891Z","repository":{"id":355238156,"uuid":"1227329181","full_name":"zaabola/Projet_Mining_Pollution","owner":"zaabola","description":"EcoGuard AI: A comprehensive computer vision platform for environmental monitoring and worker safety. Features real-time detection models for PPE compliance, mining footprint segmentation, deforestation tracking, soil health analysis, and wildlife monitoring via an interactive Django dashboard.","archived":false,"fork":false,"pushed_at":"2026-05-02T15:16:04.000Z","size":5933,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-05-02T16:27:27.491Z","etag":null,"topics":["ai","computer-vision","django","llm","minning","pandas","python","pytorch","web","webdevelopment"],"latest_commit_sha":null,"homepage":"","language":"HTML","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/zaabola.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-05-02T14:31:51.000Z","updated_at":"2026-05-02T15:16:07.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/zaabola/Projet_Mining_Pollution","commit_stats":null,"previous_names":["zaabola/projet_mining_pollution"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/zaabola/Projet_Mining_Pollution","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zaabola%2FProjet_Mining_Pollution","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zaabola%2FProjet_Mining_Pollution/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zaabola%2FProjet_Mining_Pollution/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zaabola%2FProjet_Mining_Pollution/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zaabola","download_url":"https://codeload.github.com/zaabola/Projet_Mining_Pollution/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zaabola%2FProjet_Mining_Pollution/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32542201,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-02T12:25:33.646Z","status":"ssl_error","status_checked_at":"2026-05-02T12:24:51.733Z","response_time":132,"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":["ai","computer-vision","django","llm","minning","pandas","python","pytorch","web","webdevelopment"],"created_at":"2026-05-02T17:00:41.322Z","updated_at":"2026-05-02T17:01:28.818Z","avatar_url":"https://github.com/zaabola.png","language":"HTML","funding_links":[],"categories":[],"sub_categories":[],"readme":"# EcoGuard AI 🌍🛡️\n\n**EcoGuard AI** is a comprehensive, AI-powered computer vision platform designed to tackle industrial pollution, enforce worker safety compliance, and monitor environmental health. \n\nDeveloped at **ESPRIT (École Supérieure Privée d'Ingénierie et de Technologies / Esprit School of Engineering)**, EcoGuard utilizes advanced deep learning architectures (YOLOv8 \u0026 PyTorch U-Net) and is deployed via a modern Django web application. It provides real-time, interactive insights into high-risk industrial zones (like mining operations) and their surrounding ecosystems.\n\n---\n\n## ✨ Key Features\n\n### 👷‍♂️ Industrial Worker Safety\n* **PPE Compliance Tracking:** Real-time YOLOv8 models fine-tuned to detect hard hats, medical masks, and heavy-duty gas masks.\n* **Explainable AI (XAI):** EigenCAM integrations to visualize exactly *what* the model is looking at when making safety predictions.\n\n### 🏭 Environmental \u0026 Mining Monitoring\n* **Mining Area Segmentation:** PyTorch U-Net models trained on satellite imagery to precisely calculate the footprint of legal and illegal mining operations.\n* **Soil Health Analysis:** The custom \"Ghada\" U-Net model evaluates land degradation and soil health based on the proximity and density of mining excavations.\n* **Deforestation Tracking:** Automated tracking of forest loss around industrial zones using custom satellite segmentation.\n* **Smoke \u0026 Fire Detection:** Early warning systems for industrial exhaust and wildfires.\n\n### 🐟 Wildlife \u0026 Ecosystem Tracking\n* **Aquatic Contamination Analysis:** Advanced fish behavior tracking. The system uses Re-Identification (Re-ID) and trajectory mapping to classify fish swimming patterns (Normal vs. Stressed) as an early indicator of phosphogypsum water contamination.\n* **Terrestrial Wildlife:** YOLO-based animal detection to monitor wildlife displacement near mining zones.\n\n### 🔐 Smart Authentication \u0026 Administration\n* **OCR-Powered Registration:** Employees register by uploading their ID cards. The system uses `EasyOCR` to automatically extract their First and Last names, auto-generate a corporate email (`first_last@EcoGuard.ai`), and generate a highly secure random password.\n* **Approval Workflow:** New accounts are placed in a \"Pending Approval\" state.\n* **Admin Dashboard:** Superusers have access to a User Management interface to view ID cards and securely Approve, Reject, or Delete employee access.\n\n---\n\n## 🛠️ Technology Stack\n\n**Machine Learning \u0026 Computer Vision:**\n* `PyTorch` / `Torchvision`\n* `Ultralytics YOLOv8`\n* `Segmentation Models PyTorch (SMP)`\n* `OpenCV` / `NumPy`\n* `EasyOCR`\n\n**Web Development:**\n* `Django` (Python Web Framework)\n* `SQLite3` (Database)\n* `Bootstrap 5` (Mazer Admin Template)\n* `Chart.js` / `ApexCharts` (Data Visualization)\n\n---\n\n## 🚀 Installation \u0026 Setup\n\n1. **Clone the repository:**\n   ```bash\n   git clone https://github.com/zaabola/Projet_Mining_Pollution.git\n   cd Projet_Mining_Pollution\n   ```\n\n2. **Create and activate a virtual environment:**\n   ```bash\n   python -m venv venv\n   # On Windows:\n   venv\\Scripts\\activate\n   # On Mac/Linux:\n   source venv/bin/activate\n   ```\n\n3. **Install dependencies:**\n   *(Ensure you have PyTorch installed according to your CUDA version first)*\n   ```bash\n   pip install -r requirements.txt\n   ```\n\n4. **Run Database Migrations:**\n   ```bash\n   cd web_app\n   python manage.py makemigrations\n   python manage.py migrate\n   ```\n\n5. **Create an Admin User:**\n   ```bash\n   python manage.py createsuperuser\n   ```\n\n6. **Start the Development Server:**\n   ```bash\n   python manage.py runserver\n   ```\n   Access the dashboard at `http://localhost:8000`.\n\n---\n\n## 📸 Screenshots\n\n\u003cimg width=\"1920\" height=\"1080\" alt=\"Screenshot (103)\" src=\"https://github.com/user-attachments/assets/b704807b-093e-4a17-8bcc-450ede839489\" /\u003e\n\u003cimg width=\"1920\" height=\"1080\" alt=\"Screenshot (80)\" src=\"https://github.com/user-attachments/assets/647c0e70-8f3e-47bc-b606-ec7f7ba472bc\" /\u003e\n\u003cimg width=\"1920\" height=\"1080\" alt=\"Screenshot (81)\" src=\"https://github.com/user-attachments/assets/de4a7b7f-92bc-416e-b27b-9f42e4e3fef1\" /\u003e\n\u003cimg width=\"1920\" height=\"1080\" alt=\"Screenshot (83)\" src=\"https://github.com/user-attachments/assets/07f3a62e-d0bb-4802-a290-1964e683d940\" /\u003e\n\n\n---\n\n## 📄 Credits \u0026 Academic Context\nThis project was developed at **ESPRIT (Esprit School of Engineering)** as part of an advanced environmental technology and artificial intelligence initiative. All rights reserved.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzaabola%2Fprojet_mining_pollution","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzaabola%2Fprojet_mining_pollution","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzaabola%2Fprojet_mining_pollution/lists"}