Projects / Computer Science / Computer Science project 38

Traffic Sign Recognition for Indian Roads

Deep Learning / Computer VisionMediumFaster with a GPU

Approx. component budget: Rs. 0 - 2,000

Objective

Train a sign recogniser and check how it behaves with blur, rain and partly hidden signs.

A model that detects and classifies traffic signs such as speed limit, stop and no entry in images and dashcam video.

CNN classification, data augmentation, robustness testing, and the difference between detection and classification.

Python, TensorFlow or PyTorch, GTSRB dataset plus your own phone photos, OpenCV, free notebook GPU.

Built and tested Traffic Sign Recognition for Indian Roads; objective: train a sign recogniser and check how it behaves with blur, rain and partly hidden signs.
Measured and analysed classification accuracy per sign and detection mAP if using YOLO; 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.

The short guide for this project is prepared when you ask for it. Message us on WhatsApp and we will prepare it and tell you when it is ready.

Payment details are shared in the chat. We send the PDF on WhatsApp after your payment is confirmed.

Train and compare several classifiers and explain each prediction in simple language, so a student knows what...

Build a baseline with TF-IDF and then a transformer model, and measure how much the better model improves resu...

Train a convolutional neural network with transfer learning on a public leaf dataset and test how well it work...