{"id":31696641,"url":"https://github.com/pavankumar0426-arch/realtimeobjecttracking","last_synced_at":"2026-04-15T16:03:19.162Z","repository":{"id":316950583,"uuid":"1065439325","full_name":"Pavankumar0426-arch/RealTimeObjectTracking","owner":"Pavankumar0426-arch","description":"Real-Time Object Detection \u0026 Multi-Person Tracking with Bidirectional People Counting","archived":false,"fork":false,"pushed_at":"2025-09-27T20:00:59.000Z","size":7289,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-09-27T20:42:38.318Z","etag":null,"topics":["opencv","python","pytorch","yolov8"],"latest_commit_sha":null,"homepage":"","language":"Python","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/Pavankumar0426-arch.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":"2025-09-27T18:21:36.000Z","updated_at":"2025-09-27T20:01:02.000Z","dependencies_parsed_at":"2025-09-27T20:42:40.342Z","dependency_job_id":null,"html_url":"https://github.com/Pavankumar0426-arch/RealTimeObjectTracking","commit_stats":null,"previous_names":["pavankumar0426-arch/realtimeobjecttracking"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/Pavankumar0426-arch/RealTimeObjectTracking","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Pavankumar0426-arch%2FRealTimeObjectTracking","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Pavankumar0426-arch%2FRealTimeObjectTracking/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Pavankumar0426-arch%2FRealTimeObjectTracking/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Pavankumar0426-arch%2FRealTimeObjectTracking/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Pavankumar0426-arch","download_url":"https://codeload.github.com/Pavankumar0426-arch/RealTimeObjectTracking/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Pavankumar0426-arch%2FRealTimeObjectTracking/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278981518,"owners_count":26079640,"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":"2025-10-08T02:00:06.501Z","response_time":56,"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":["opencv","python","pytorch","yolov8"],"created_at":"2025-10-08T17:10:16.756Z","updated_at":"2025-10-08T17:10:20.649Z","avatar_url":"https://github.com/Pavankumar0426-arch.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🚀 Real-Time People Tracking \u0026 Counting System\n---\n## 📄 Abstract\nThis project implements a **Real-Time Object Detection and Multi-Object Tracking system** with **Bidirectional People Counting** using **YOLOv8** and **DeepSORT**. The system accurately detects people in live video streams, assigns unique IDs for multi-person tracking, and counts people crossing a virtual line in both directions. The system provides real-time visualization, stores annotated videos, and generates statistical graphs of people count over time.  \n\n**Applications:**\nSmart surveillance, crowd management, retail analytics, public space monitoring, and research.  \n\n---\n## **Description**\nThe **Real-Time Object Detection \u0026 Multi-Object Tracking with People Counting** system combines:  \n- **YOLOv8:** High-speed, accurate object detection.  \n- **DeepSORT:** Robust multi-object tracking with unique IDs.  \n- **Bidirectional Counting:** Counts people moving upward and downward across a virtual line.  \n- **Visualization \u0026 Output:** Displays bounding boxes, track IDs, live counts, saves annotated video, and generates people count graphs.  \n\n**Key Applications:**  \n- Crowd monitoring in public spaces  \n- Retail store customer flow analysis  \n- Smart surveillance and security systems  \n- Event management and public transportation monitoring\n---\n## ✨ Features\n- ✅ Real-time object detection with **YOLOv8**  \n- ✅ Multi-object tracking with **DeepSORT** and unique IDs  \n- ✅ Bidirectional people counting (up/down crossings)  \n- ✅ Live annotated video display with bounding boxes, IDs, and counts  \n- ✅ Save annotated video for analysis in `outputs/`  \n ---\n## 📁 Folder Structure\n```\nRealTimeObjectTracking/\n├── src/\n│ └── multi_track_count_bidirectional.py # Main script\n├── models/\n│ └── yolov8n.pt # YOLO model (auto-download works)\n├── outputs/\n\u003c\u003c\u003c\u003c\u003c\u003c\u003c HEAD\n│ └── people_count_bidirectional.mp4\n├── requirements.txt\n└── README.md\n```\n---\n## ⚙️ Installation\n1. **Create and activate a virtual environment**:\n```\npython -m venv objtrack_env\nobjtrack_env\\Scripts\\activate       # Windows\n# source objtrack_env/bin/activate  # Linux/macOS\n```\n2. **Install dependencies**:\n```\npip install -r requirements.txt\n```\n3. **▶️ Usage**\n```\nInstall dependencies:\npip install -r requirements.txt\n\nNavigate to the src/ folder:\ncd src\nRun the main script:\npython multi_track_count_bidirectional.py\n\nThe webcam will open:\nPeople will be tracked with bounding boxes and unique IDs.\nThe counting line will detect upward and downward crossings.\nCounts will display live on the video.\n\nPress q to stop the webcam.\n\nThe annotated video will be saved in:\noutputs/people_count_bidirectional.mp4\n🔧 Optional Customizations\nChange the counting line position in the script (line_position).\nFilter other object classes by COCO class ID (0 = person, 1 = bicycle, 2 = car, etc.).\nAdjust YOLOv8 model (yolov8n.pt, yolov8s.pt, etc.) for speed vs accuracy.\nAdd trajectory lines for each tracked person.\n```\n---\n## **🛠 Requirements:**\n1. Python 3.8+\n2. Webcam\n3. GPU recommended for faster YOLOv8 inference\n---\n## **Dependencies**\n1. lua\n2. Copy code\n3. ultralytics\n4. opencv-python\n5. opencv-python-headless\n6. numpy\n7.torch\n8. torchvision\n9. deep-sort-realtime\n---\n## **🔗 References**\n1. YOLOv8 Documentation\n2. DeepSORT Realtime Tracker\n3. COCO Dataset Class IDs\n---\n## 👤 Author\n### M. PAVAN KUMAR\nPython \u0026 Computer Vision Enthusiast\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpavankumar0426-arch%2Frealtimeobjecttracking","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpavankumar0426-arch%2Frealtimeobjecttracking","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpavankumar0426-arch%2Frealtimeobjecttracking/lists"}