The objective of this study is to build a model for the classification of traffic signs available in the image into many categories using a CNN and Keras library to detect the traffic sign. The goal of the traffic sign recognition is to build a deep neural network (DNN), which is used to classify traffic signs. The authors suggest training the model so it can decode traffic signs from natural images using the German Traffic Sign Dataset. This data should be firstly preprocessed in order to maximize the model performance. After choosing model architecture, fine tuning, and training, the model will be tested on new images of traffic signs found on the web. Because it deals with image classification, a convolutional neural network is chosen as a type of DNN, which is a common choice for this type of problem. The code is written in Python with use of tensor flow library. The proposed CNN model identifies traffic signs and classifies them with 95% accuracy. GUI of this model makes it easy to understand how signs are classified into several classes.
TopIntroduction
In this era of Artificial Intelligence, humans are becoming more dependent on technology. With the enhanced technology, multinational companies like Google, Tesla, Uber, Ford, Audi, Toyota, Mercedes-Benz, and many more are working on automating vehicles. They are trying to make more accurate autonomous or driverless vehicles (Harley, 2015; Saini et al., 2017). You all might know about self-driving cars, where the vehicle itself behaves like a driver and does not need any human guidance to run on the road. This is not wrong to think about the safety aspects—a chance of significant accidents from machines. But no machines are more accurate than humans. Researchers are running many algorithms to ensure 100% road safety and accuracy like Traffic Sign Recognition (Jensen et al., 2016).
Autonomous vehicle is utilized in every field whether it is in road, water, sky for different intentions. In the advent of neural science development many researchers mainly depend on the automation of vehicle for different purpose (He, 2019). For road safety autonomous vehicle used as important tool for self-driving envelopes and path tracking (Brown et al., 2017). In underwater node localization the autonomy vehicle provides the accurate and effective result with less cost and improve lifetime of the underwater network (Dass, 2022). Sky–farming uses autonomous vehicle for agriculture and smart farming other application (Ather et al., 2022; Yinka-Banjo & Ajayi, 2019).
For all the autonomous point researchers have given emphasis on smart prediction using machine learning for various application such online retail market analysis (Nayak & Narain, 2021),
Dynamic product price prediction (Nayak & Narain, 2020), etc. As in real life while using road with heavy traffic there exist various traffic signs like traffic signals like turn left or right, speed limits, no passing of heavy vehicles, no entry, children crossing, etc., that you need to follow for a safe drive (On-Road Automated Driving Committee, 2014). Likewise, autonomous vehicles also have to interpret these signs and make decisions to achieve accuracy. The methodology of recognizing which class a traffic sign belongs to is called Traffic signs classification (Diaz et al., 2015).
In the real-world, traffic sign recognition is a two-stage process:
Deep learning object detectors can perform localization and recognition in a single forward-pass of the network (Ellahyani et al., 2021). Various Traffic sign detection and classifications have proposed in various articles with description of neural network and image processing technology (Garg et al., 2019; Kamal et al., 2017). Convolution Neural Network Model is an efficient way of description of traffic signal detection and data processing for accurate result (He et al., 2020; Karthikeyan et al., 2020; Peng et al., 2016). Hence in our model we got approached with description of convolution neural network its description and various layer application and execution process. Our model takes the dataset for various traffic signals execute through our proposed scheme. Then it finds out accuracy using various matrices and displays the result in comparison with other available model.