Localized Traffic Sign Detection with Multi-scale Deconvolution Networks

04/27/2018

∙

by   Songwen Pei, et al.

∙

0

∙

share

Autonomous driving is becoming a future practical lifestyle greatly driven by deep learning. Specifically, an effective traffic sign detection by deep learning plays a critical role for it. To address the issues of taking amount of time to compute complicate algorithm and low ratio of detecting blurred and sub-pixel images of traffic sign, we propose Multi-scale Deconvolution Networks(MDN) by flexibly combining multi-scale convolutional neural network with deconvolution sub-network. It is certified that the MDN is effective by comparing with classical algorithms on the benchmarks of the localized traffic sign, such as Chinese Traffic Sign Dataset(CTSD), and the German Traffic Sign Benchmarks(GTSRB).