Fast Branch Convolutional Neural Network for Traffic Sign Recognition
In this paper, the authors 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. The authors' 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. The authors 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 German Traffic Sign Recognition Benchmark (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.
- Record URL:
-
Availability:
- Find a library where document is available. Order URL: http://worldcat.org/issn/19391390
-
Supplemental Notes:
- Copyright © 2017, IEEE.
-
Authors:
- Hu, Wenzheng
- Zhuo, Qing
- Zhang, Changshui
- Li, Jianke
- Publication Date: 2017
Language
- English
Media Info
- Media Type: Web
- Features: References;
- Pagination: pp 114-126
-
Serial:
- IEEE Intelligent Transportation Systems Magazine
- Volume: 9
- Issue Number: 3
- Publisher: Institute of Electrical and Electronics Engineers (IEEE)
- ISSN: 1939-1390
- Serial URL: http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=5117645
Subject/Index Terms
- TRT Terms: Benchmarks; Neural networks; Traffic signs
- Identifier Terms: Traffic Sign Recognition Test
- Uncontrolled Terms: Recognition
- Subject Areas: Data and Information Technology; Highways; Operations and Traffic Management;
Filing Info
- Accession Number: 01644503
- Record Type: Publication
- Files: TRIS
- Created Date: Jul 27 2017 10:51AM