Traffic Sign Detection Using Traffic Convolutional Neural
TSD (Traffic Sign Detection) is a key milestone of automated and assisted driving. TSD research has gained much importance in terms of improving road traffic control. In recent years, CNN (Convolutional Neural Networks) has had a lot of success with target detection tasks. It shows higher accuracy or faster execution than the traditional approach. This paper suggests a Convolutional Neural Network (CNN) VGG Net 16-based approach to detecting and classifying traffic signals that is robust to extreme environmental conditions. The IVGG model has 29 layers, as opposed to the original VGG model , which has 16 layers to speed model convergence, capture major features, and minimize training time even further. The classification impact would improve as a result. The investigator in this paper conducted the experiment using the German Traffic Sign Benchmark (GTSRB) dataset.