Fast Branch Convolutional Neural Network for Traffic Sign Recognition
Authors:
- 25 July 2017
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Intelligent Transportation Systems Magazine
- Vol. 9 (3) , 114-126
Abstract
In this paper, we propose a novel framework for speeding up the test-time of traffic sign recognition, which is named Branch Convolution Neural Network. It is the first time to introduce a branch-output mechanism into a deep Convolution Neural Network. Our model has an accuracy as high as a deep convolution neural network model, while it performs faster at the same condition during test stage. It is a significantly accelerated framework for designing a real-time deep neural network system. We present a detail process to change a regular pre-trained Convolution Neural Network into a Branch Convolution Neural Network: train several simple branch classifiers, bias classifiers and optimize branches. Experiment applied on GTSRB shows that large number of traffic signs are unnecessary to go through all layers in a deep model and they can be separated out in a relative shallow neural network. This framework speeds up the recognition progress, while keeping the accuracy within an extremely minor drop.Keywords
This publication has 27 references indexed in Scilit:
- ImageNet classification with deep convolutional neural networksCommunications of the ACM, 2017
- Pedestrian Detection via Mixture of CNN Experts and Thresholded Aggregated Channel Features2015
- MatConvNet2015
- Facial landmark detection via cascade multi-channel convolutional neural network2015
- A convolutional neural network cascade for face detection2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Traffic Sign Recognition With Hinge Loss Trained Convolutional Neural NetworksIEEE Transactions on Intelligent Transportation Systems, 2014
- Multi-column deep neural network for traffic sign classificationNeural Networks, 2012
- Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition2010
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998