2012 Special Issue: Multi-column deep neural network for traffic sign classification
Neural Networks(2012)
摘要
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 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.
更多查看译文
关键词
deep neural network,final phase,pre-wired feature extractor,boosts recognition performance,multi-column dnn,german traffic sign recognition,preprocessed data,traffic sign classification,special issue,better-than-human recognition rate,parameterizable gpu implementation,careful design,multi-column deep neural network,image classification
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要