Projects / Computer Science / Computer Science project 6

Helmet and Mask Detection Using YOLO

Approx. component budget: Rs. 0 - 3,000

Objective

Train a YOLO model on a public dataset and measure how well it works in daylight, low light and at different distances.

What you will build

An object detector that finds riders with and without helmets (or people with and without masks) in images and video and draws labelled boxes.

Results you can expect

• MAP@0.5
• Precision and recall per class
• Frames per second on laptop CPU and on a free GPU
• And a table of failure cases (night, blur, occlusion)

What you will learn

Object detection, annotation, training and tuning, the speed vs accuracy trade-off, and real-time video processing.

Tools and notes

Python, Ultralytics YOLO, Roboflow or LabelImg, OpenCV, free notebook GPU. Use only public or self-recorded data with consent and do not store faces.

Resume points from this project

• Built and tested Helmet and Mask Detection Using YOLO; objective: train a YOLO model on a public dataset and measure how well it works in daylight, low light and at different distances.
• Measured and analysed mAP@0.5 and precision and recall per class; wrote the report and presented the results in a viva. Add your own numbers: [x].

Replace [x] with your own measured results. Write only what you really did.

More computer science projects

Back to all projects