Traffic Sign Recognition System using Deep Learning
Done by Chris Michel SURJU, BSc (Hons) Computer Science Yr 3 (Completed August 2021)
University of Mauritius
Road traffic signs in Mauritius provide vital information about the traffic rules, road conditions, and route directions to assist drivers in safe driving. Recognition of traffic signs is also one of the key features of Advanced Driver Assistance Systems (ADAS). Standard computer vision methods are traditionally employed to detect and classify traffic signs, but these required considerable and time-consuming effort.
Instead, by applying deep learning (such as deep neural networks) to this problem, we create a better model that reliably classifies traffic signs, learning to identify the most appropriate features for this problem by itself. Deep learning can be used to classify traffic signs with high accuracy, employing a variety of pre-processing and regularization techniques, and trying different model architectures.
The goal of this project is to implement, train and deploy a deep learning network (such as Faster Recurrent Convolutional Neural Networks (F-RCNN)) for traffic sign recognition system with Mauritian Traffic Sign Dataset (to be constructed). Sample video files containing images of road traffic signs will then be used to evaluate the performance.
![[REMAKE] Work Out - J. Cole - [FREE FLP]](https://images.videosashka.com/watch/POi4OadmGa0)
