Multi-column deep neural network for traffic sign classification

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.