TY - GEN
T1 - Traffic Sign Recognition with Light Convolutional Networks
AU - Wu, Bo Xun
AU - Wang, Pin Yu
AU - Yang, Yi Ta
AU - Guo, Jiun-In
PY - 2018/8/27
Y1 - 2018/8/27
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85053867671&partnerID=8YFLogxK
U2 - 10.1109/ICCE-China.2018.8448685
DO - 10.1109/ICCE-China.2018.8448685
M3 - Conference contribution
AN - SCOPUS:85053867671
SN - 9781538663011
T3 - 2018 IEEE International Conference on Consumer Electronics-Taiwan, ICCE-TW 2018
BT - 2018 IEEE International Conference on Consumer Electronics-Taiwan, ICCE-TW 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 5th IEEE International Conference on Consumer Electronics-Taiwan, ICCE-TW 2018
Y2 - 19 May 2018 through 21 May 2018
ER -