Open AccessTraffic Sign Recognition Using an Attentive Context Region‐Based Detection Framework
Author(s) -
Zhigang LIU,
Juan DU,
Feng TIAN,
Jiazheng WEN
Publication year - 2021
Publication title -
chinese journal of electronics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.267
H-Index - 25
eISSN - 2075-5597
pISSN - 1022-4653
DOI - 10.1049/cje.2021.08.005
Subject(s) - computer science , traffic sign recognition , concatenation (mathematics) , pointwise , artificial intelligence , feature (linguistics) , pattern recognition (psychology) , context (archaeology) , exploit , entropy (arrow of time) , object detection , traffic sign , machine learning , sign (mathematics) , mathematics , mathematical analysis , paleontology , linguistics , philosophy , physics , computer security , combinatorics , quantum mechanics , biology
Accurate small traffic sign recognition is more important for the safety of intelligent transportation systems. A recognition framework named attentive context region‐based detection framework (AC‐RDF) is proposed in this paper. We construct the attentive context feature for the recognition of small traffic signs, which combines the target information and the contextual information by the concatenation operation following a pointwise convolutional layer. The proposed attentive context feature exploits the surrounding information for a given object proposal. Next, we propose a novel attentive loss function to replace the original cross‐entropy function. It distinguishes hard negative samples from easy positive ones in the total loss, allows the proposed framework to obtain enough training, and further improve the recognition accuracy. The proposed method is evaluated on the challenging Tsinghua‐Tencent 100K dataset. The experimental results indicate that the attentive context region‐based detection framework is superior at detecting small traffic signs and achieves state‐of‐the‐art performance compared with other methods.