標題: Traffic Sign Recognition with Light Convolutional Networks
作者: Wu, Bo-Xun
Wang, Pin-Yu
Yang, Yi-Ta
Guo, Jiun-In
電子工程學系及電子研究所
Department of Electronics Engineering and Institute of Electronics
公開日期: 1-Jan-2018
摘要: In this work, we aim to design a light net that can be executed on the embedded system in real time. We modify VGG Net to a small net, called Safe Net, and utilize multi-scale features for traffic sign recognition. Moreover, we convert the dataset into grayscale, which has been proved that has a better performance on GTSRB dataset. In addition, we augment the training data by about 6.6 times more via spinning, distorting and flipping to boost the accuracy. On Nvidia Jetson TX1, Safe Net only takes 4.58ms per image including preprocessing at the testing and Safe Net can even achieve 99.34% accuracy.
URI: http://hdl.handle.net/11536/150938
ISSN: 2381-5779
期刊: 2018 IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS-TAIWAN (ICCE-TW)
Appears in Collections:Conferences Paper