Open AccessReal-time Traffic Sign Text Detection Based on Deep Learning
Author(s) -
Ximing Peng,
Xianqiao Chen,
Chang Liu
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/768/7/072039
Subject(s) - computer science , artificial intelligence , detector , convolutional neural network , sign (mathematics) , cascade , deep learning , rotation (mathematics) , task (project management) , text detection , pattern recognition (psychology) , computer vision , image (mathematics) , mathematics , engineering , mathematical analysis , telecommunications , systems engineering , chemical engineering
Aiming at the task of traffic sign text detection in natural scenes, a two-stage cascade detection model based on deep learning is proposed. The proposed model first locates the regions of interest (RoI) of text-based traffic sign by applying improved SSD (Single Shot MultiBox Detector) network. Then a rotation-based text detection network is used to detect text strings in the located RoI. Moreover, the lightweight convolutional neural network MobileNetV2 is combined with the deep learning component in two stages, which reduces network parameters and improves detection speed of the model. On the one hand, the proposed approach takes full advantage of the information of traffic signs. By this way the search area of text detection can be reduced, which makes it possible to simplify the text detector. On the other hand, it can obtain more complete text detection results by using rotation-based text detector. The experimental results show that the proposed method can perform well on different data sets, it can not only keep a high accuracy of detection, but also meets the realtime requirements.