TY - JOUR
T1 - A three-stage real-time detector for traffic signs in large panoramas
AU - Song, Yizhi
AU - Fan, Ruochen
AU - Huang, Sharon
AU - Zhu, Zhe
AU - Tong, Ruofeng
N1 - Funding Information:
We thank all anonymous reviewers for their valuable comments and suggestions. This paper was supported by the National Natural Science Foundation of China (No. 61832016) and Science and Technology Project of Zhejiang Province (No. 2018C01080).
Funding Information:
We thank all anonymous reviewers for their valuable comments and suggestions. This paper was supported by the National Natural Science Foundation of China (No. 61832016) and Science and Technology Project of Zhejiang Province (No. 2018C01080).
Publisher Copyright:
© 2019, The Author(s).
PY - 2019/12/1
Y1 - 2019/12/1
N2 - Traffic sign detection is one of the key components in autonomous driving. Advanced autonomous vehicles armed with high quality sensors capture high definition images for further analysis. Detecting traffic signs, moving vehicles, and lanes is important for localization and decision making. Traffic signs, especially those that are far from the camera, are small, and so are challenging to traditional object detection methods. In this work, in order to reduce computational cost and improve detection performance, we split the large input images into small blocks and then recognize traffic signs in the blocks using another detection module. Therefore, this paper proposes a three-stage traffic sign detector, which connects a BlockNet with an RPN–RCNN detection network. BlockNet, which is composed of a set of CNN layers, is capable of performing block-level foreground detection, making inferences in less than 1 ms. Then, the RPN–RCNN two-stage detector is used to identify traffic sign objects in each block; it is trained on a derived dataset named TT100KPatch. Experiments show that our framework can achieve both state-of-the-art accuracy and recall; its fastest detection speed is 102 fps.
AB - Traffic sign detection is one of the key components in autonomous driving. Advanced autonomous vehicles armed with high quality sensors capture high definition images for further analysis. Detecting traffic signs, moving vehicles, and lanes is important for localization and decision making. Traffic signs, especially those that are far from the camera, are small, and so are challenging to traditional object detection methods. In this work, in order to reduce computational cost and improve detection performance, we split the large input images into small blocks and then recognize traffic signs in the blocks using another detection module. Therefore, this paper proposes a three-stage traffic sign detector, which connects a BlockNet with an RPN–RCNN detection network. BlockNet, which is composed of a set of CNN layers, is capable of performing block-level foreground detection, making inferences in less than 1 ms. Then, the RPN–RCNN two-stage detector is used to identify traffic sign objects in each block; it is trained on a derived dataset named TT100KPatch. Experiments show that our framework can achieve both state-of-the-art accuracy and recall; its fastest detection speed is 102 fps.
UR - http://www.scopus.com/inward/record.url?scp=85073810344&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85073810344&partnerID=8YFLogxK
U2 - 10.1007/s41095-019-0152-1
DO - 10.1007/s41095-019-0152-1
M3 - Article
AN - SCOPUS:85073810344
SN - 2096-0433
VL - 5
SP - 403
EP - 416
JO - Computational Visual Media
JF - Computational Visual Media
IS - 4
ER -