Multi-column deep neural network for traffic sign classification.

The authors describe the approach that won the final phase of the German traffic sign recognition benchmark. Their method is the only one that achieved a better-than-human recognition rate of 99.46%. A fast, fully parameterizable GPU implementation was used of a Deep Neural Network (DNN) that does not require careful design of pre-wired feature extractors, which are rather learned in a supervised way. Combining various DNNs trained on differently preprocessed data into a Multi-Column DNN (MCDNN) further boosts recognition performance, making the system insensitive also to variations in contrast and illumination. (Author/publisher)