Abstract
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)