Traffic Sign Recognition Using an Attentive Context Region-Based Detection Framework

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.

Automated summary

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.