Ever wondered if your computer could “see” and track objects in real-time? 👀
During my CodeAlpha internship, I built a system in Python that does exactly that. It detects objects in video files and live webcam streams, assigning each object a unique ID as it moves.
What I learned / challenges:
- Objects sometimes got “lost” between frames — tweaking the tracking algorithm fixed it
- Switching between video files and webcam input required careful testing
- Managing Python dependencies and real-time performance was tricky
Tech Stack:
- YOLOv8 (Ultralytics)
- Deep SORT
- OpenCV
- Python
💡 Fun part: Watching the bounding boxes follow objects in real-time felt magical ✨
Check out my code and demo: [GitHub Repo]
CodeAlpha_ObjectDetection
🔍 Real-Time Object Detection & Tracking
Internship Task 4 — CodeAlpha
📌 About This Project
This project implements real-time object detection and tracking using:
- YOLOv8 (via ultralytics) for object detection
- Deep SORT for tracking objects across frames
- OpenCV for video input/output (webcam or video files)
It fulfills all internship requirements:
Real-time video input (webcam or video file)
Pre-trained model for object detection
Bounding boxes with tracking IDs
Python implementation with clear, real-time results
🚀 Features
- Detects objects in every video frame
- Tracks detected objects with unique IDs
- Works with multiple video files or webcam input
- Outputs video frames with bounding boxes and labels
📦 Installation
- Clone the repository
git clone https://github.com/Urooj25/CodeAlpha_ObjectDetection.git cd CodeAlpha_ObjectDetection
2- Create a virtual environment python -m venv venv source venv/bin/activate # Windows: venv\Scripts\activate
3-Install dependencies pip install -r requirements.txt
Usage Run on Video Files Place your video(s) in the videos/ folder or detect real time…
Question for you: Have you tried real-time object tracking? How did you approach it?
Top comments (0)