Overview / Usage

Traffic signs recognition is an essential technology that is needed to improve road safety and prevent accidents. The critical elements of the road infrastructure that provide information to drivers, pedestrians, and cyclist about the rules and regulations of the road. The ability to recognize and interpret traffic signs is crucial for safe and efficient driving. In the world of Artificial Intelligence, many researchers and big companies like Tesla, Uber, Google, Mercedes, Ford, Audi, etc., are working on autonomous vehicle and self-driving cars. To achieve the autonomous, it is necessary for vehicles to understand the traffic rules.This can help drivers and provide information such as the speed limit, road conditions and directions. It is an essential component of intelligent transportation systems that can help improve road safety and reduce accidents.

Methodology / Approach

Deep learning technique such as computer vision have shown promising results for traffic signs recognition. This could be integrated with other transportation systems, such as traffic light control systems or autonomous vehicle systems. This would allow for a more coordinated and efficient transportation system.

General steps in approach:

1. Data collection
2. Data preprocessing
3. Feature extraction
4. Model training
5. Model evauation
6. Deployment

​

Technologies Used

• InteloneAPI

Intel OneAPI is a software development kit (SDK) that allows developers to create high-performance applications for a variety of hardware platforms, including CPUs, GPUs, FPGAs, and AI accelerators.

The traffic signs recognition uses computer vision and deep learning techniques to automatically detect and recognize the traffic signs in real time.

LIBRARIES USED

• Numpy
• Pandas
• Keras
• Tensorflow
• Sklearn
• Resnet50

Repository

https://github.com/Gayathri-raja/Trafficsignrecognition_IntelOneAPI