What question did this study set out to answer?

This research aims to improve traffic sign classification accuracy utilizing neural networks.

July 1, 2011

A committee of neural networks for traffic sign classification

Key Points

This research aims to improve traffic sign classification accuracy utilizing neural networks.
Developed a neural network approach that includes Convolutional Neural Networks (CNN) and Multi-Layer Perceptrons (MLP).
Used GPU implementation for fast processing and trained networks in a supervised manner.
Achieved further improvement through a committee approach combining multiple neural networks.
Initial recognition rate of 98.98% improved to 99.15% with further training.
The system outperformed human recognition rates in traffic sign classification.

Abstract

We describe the approach that won the preliminary phase of the German traffic sign recognition benchmark with a better-than-human recognition rate of 98.98%.We obtain an even better recognition rate of 99.15% by further training the nets. Our fast, fully parameterizable GPU implementation of a Convolutional Neural Network does not require careful design of pre-wired feature extractors, which are rather learned in a supervised way. A CNN/MLP committee further boosts recognition performance.

A committee of neural networks for traffic sign classification

Key Points

Abstract

Cite This Study