期刊
CHINESE JOURNAL OF ELECTRONICS
卷 30, 期 6, 页码 1080-1086出版社
WILEY
DOI: 10.1049/cje.2021.08.005
关键词
Small traffic sign; Attentive context; Attentive loss; Hard negative samples
资金
- National Natural Science Foundation of China [61502094, 51774090, 51104030]
- Heilongjiang Province Natural Science Foundation of China
Accurate recognition of small traffic signs is crucial for the safety of intelligent transportation systems. A novel recognition framework named attentive context region-based detection framework (AC-RDF) is proposed in this paper, which utilizes attentive context feature and attentive loss function to improve recognition accuracy. Experimental results on the Tsinghua-Tencent 100K dataset demonstrate the superiority of the proposed framework in detecting small traffic signs and achieving state-of-the-art performance.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据