交通信号灯识别We describe the approach that won the final phase of the German traffic sign recognition benchmark. Our method is the only one that achieved a better-than-human recognition rate of 99.46%. We use a fast, fully parameterizable GPU implementation 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 trainedon differently preprocessed data into aMulti-Column DNN (MCDNN) further boosts recognition performance, m aking the system insensitive also to variations in contrast and illumination.