English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Traffic sign detection is an important research direction in intelligentdriving. Unfortunately, existing methods often overlook extreme conditions suchas fog, rain, and motion blur. Moreover, the end-to-end training strategy forimage denoising and object detection models fails to utilize inter-modelinformation effectively. To address these issues, we propose CCSPNet, anefficient feature extraction module based on Transformers and CNNs, whicheffectively leverages contextual information, achieves faster inference speedand provides stronger feature enhancement capabilities. Furthermore, weestablish the correlation between object detection and image denoising tasksand propose a joint training model, CCSPNet-Joint, to improve data efficiencyand generalization. Finally, to validate our approach, we create the CCTSDB-AUGdataset for traffic sign detection in extreme scenarios. Extensive experimentshave shown that CCSPNet achieves state-of-the-art performance in traffic signdetection under extreme conditions. Compared to end-to-end methods,CCSPNet-Joint achieves a 5.32% improvement in precision and an 18.09%improvement in mAP@.5.

CCSPNet-Joint: Efficient Joint Training Method for Traffic Sign Detection Under Extreme Conditions