This project performs real-time object detection and tracking using YOLOv8 and Deep SORT. It captures video from a webcam or a video file, detects multiple objects per frame, and tracks them with unique IDs over time.
- 📹 Real-time detection from webcam or video file
- 🧠 Uses YOLOv8 for object detection (pre-trained)
- 👣 Deep SORT for object tracking with persistent IDs
- 🖼️ Bounding boxes, class labels, and track IDs displayed on video
- 💾 Option to save processed video output
- ⚡ Runs on CPU (optimized for low-spec systems)
object_tracking/ ├── main.py # Main app (runs everything) ├── detector.py # YOLOv8 object detection logic ├── tracker.py # Deep SORT tracker class ├── utils.py # Drawing + label utilities ├── README.md # Project documentation └── requirements.txt # Python dependencies
- Clone the repository
git clone https://github.com/your-username/object-tracking.git cd object-tracking
Notes: ✅ ultralytics: For YOLOv8 detection (YOLO() class)
✅ opencv-python: For video capture, drawing, and UI
✅ deep-sort-realtime: For tracking with persistent IDs
✅ numpy: Required by OpenCV and Deep SORT
✅ torch: Required by YOLOv8 (PyTorch backend)