Multimedia Tools and Applications https://doi.org/10.1007/s11042-020-08722-y Real-time traffic sign detection and classification towards real traffic scene Yiqiang Wu 1,2 · Zhiyong Li 1,2 · Ying Chen 1,2 · Ke Nai 1,2 · Jin Yuan 1,2 Received: 7 May 2019 / Revised: 4 December 2019 / Accepted: 31 January 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020 Abstract In this paper we propose a real-time traffic sign recognition algorithm which is robust to the small-sized objects and can identify all traffic sign categories. Specifically, we present a two-level detection framework which consists of the region proposal module(RPM) which is responsible for locating the objects and the classification module(CM) which aims to clas- sify the located objects. In addition, to solve the problem of insufficient samples, we present an effective data augmentation method based on traffic sign logo to generate enough train- ing data. The experiments are conducted in TT100k, and the results show the superiority of our method. Keywords Traffic sign recognition · Small object detection · Data augmentation · Image synthesis 1 Introduction Traffic sign recognition is an important sub-task in the advanced driver assistant systems and autonomous driving systems. In general, there are two stages in a traffic sign recog- nition system: finding the locations of the traffic signs in real traffic scenes (traffic sign detection) and classifying the detected traffic signs into their specific sub-classes (traffic sign classification). Traffic sign detection faces many difficulties in real traffic scenes due to illumination changes, partial occlusion, cluttered background, and small size, as shown in Fig. 1. And in the second stage, there are also many problems, such as missing samples, unbalanced sample categories, the rare sample numbers etc. TT100k [37] is a Chinese traf- fic sign dataset and contains over 150 categories, which is the most widely covered traffic sign dataset in the current. However, many rather rare traffic signs are still not included. And not only that, the existing categories in the dataset are extremely imbalanced, let alone  Zhiyong Li zhiyong.li@hnu.edu.cn 1 College of Computer Science and Electronic Engineering Hunan University, Changsha, China 2 Key Laboratory for Embedded and Network Computing of Hunan Province, Changsha, China