Eigen-Gradients for Traffic Sign Recognition

Abstract EN

Traffic sign detection and recognition systems include a variety of applications like autonomous driving, road sign inventory, and driver support systems.

Machine learning algorithmsprovide useful tools for traffic sign identification tasks.

However, classification algorithms depend on the preprocessing stage to obtain high accuracy rates.

This paper proposes a road signcharacterization method based on oriented gradient maps and the Karhunen-Loeve transformin order to improve classification performance.

Dimensionality reduction may be importantfor portable applications on resource constrained devices like FPGAs; therefore, our approachfocuses on achieving a good classification accuracy by using a reduced amount of attributescompared to some state-of-the-art methods.

The proposed method was tested using GermanTraffic Sign Recognition Benchmark, reaching a dimensionality reduction of 99.3% and a classification accuracy of 95.9% with a Multi-Layer Perceptron.