Traffic sign recognition with multi-scale Convolutional Networks
Top Cited Papers
- 1 July 2011
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2809-2813
- https://doi.org/10.1109/ijcnn.2011.6033589
Abstract
We apply Convolutional Networks (ConvNets) to the task of traffic sign classification as part of the GTSRB competition. ConvNets are biologically-inspired multi-stage architectures that automatically learn hierarchies of invariant features. While many popular vision approaches use hand-crafted features such as HOG or SIFT, ConvNets learn features at every level from data that are tuned to the task at hand. The traditional ConvNet architecture was modified by feeding 1 st stage features in addition to 2 nd stage features to the classifier. The system yielded the 2nd-best accuracy of 98.97% during phase I of the competition (the best entry obtained 98.98%), above the human performance of 98.81%, using 32×32 color input images. Experiments conducted after phase 1 produced a new record of 99.17% by increasing the network capacity, and by using greyscale images instead of color. Interestingly, random features still yielded competitive results (97.33%).Keywords
This publication has 12 references indexed in Scilit:
- Human Tracking Using Convolutional Neural NetworksIEEE Transactions on Neural Networks, 2010
- Hardware accelerated convolutional neural networks for synthetic vision systemsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Real-Time Speed Sign Detection Using the Radial Symmetry DetectorIEEE Transactions on Intelligent Transportation Systems, 2008
- Real-time recognition of U.S. speed signsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Why is Real-World Visual Object Recognition Hard?PLoS Computational Biology, 2008
- Detection and classification of road signs in natural environmentsNeural Computing & Applications, 2007
- Efficient recognition of speed limit signsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Traffic sign shape classification evaluation I: SVM using distance to bordersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Road traffic sign detection and classificationIEEE Transactions on Industrial Electronics, 1997