Traffic Sign Classification using Deep Learning
IEEE BASE PAPER ABSTRACT:
The ability of a vehicle to self-drive is receiving a lot of attention these days. One of the most significant features of a self-driving car is its capacity to identify traffic signs, which ensures the safety and security of passengers both inside and outside the vehicle. Negligence in viewing and interpreting traffic signs accurately is a major cause of road accidents. A system that assists in identifying traffic signs, allowing the vehicle to make appropriate judgments is essential. Therefore, a method based on a Convolutional Neural Network (CNN), which aids in the classification of traffic signs has been suggested in this paper. The main objective is to develop a system with better performance that helps in the classification of the signs efficiently to avoid accidents and encourage the development of autonomous vehicles. Moreover, the proposed model is compared with the standard Le-Net 5 model. The accuracy for the proposed TrafficSign CNN model is 95.8%.
PROJECT OUTPUT VIDEO:
ALGORITHM / MODEL USED:
OUR PROPOSED PROJECT ABSTRACT:
- System : Pentium i3 Processor.
- Hard Disk : 500 GB.
- Monitor : 15’’ LED.
- Input Devices : Keyboard, Mouse.
- Ram : 8 GB.
- Operating system : Windows 10 Pro.
- Coding Language : Python 3.10.9.
- Web Framework : Flask.
Ramya Sree Pothineni, Srinivas Inampudi, Lakshmi Yesaswini Gudavalli, T. Lakshmi Surekha, “Traffic Sign Classification using Deep Learning”, 2023 Third International Conference on Artificial Intelligence and Smart Energy (ICAIS), IEEE CONFERENCE, 2023.