Urban-DETR: A Semantics-Enhanced Traffic Sign Detection Framework for Complex Urban Scenarios
Sensors · 14.11.2026 · 26 (22) · 7204
DOI: 10.3390/s26227204 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 14.11.2026. Verfasst von Liqing Gao und 5 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Tianjin.
Abstract (Originalsprache)
Traffic sign detection in urban scenes is challenged by small objects, similar category appearances, and background clutter. This paper presents Urban-DETR, a semantics-enhanced framework built on RT-DETR. Frozen image and text encoders from Contrastive Language-Image Pre-training (CLIP), referred to as CityCLIP in the architecture, supply image-level and category-level embeddings. A backbone incorporating LSKA extracts multi-scale visual features. UrbanFusion conditions learnable queries on the image embedding, attends to category text embeddings, and pools the query features into a semantic vector for channel-wise visual feature modulation. On the selected TT100K subset, the reported mean average precision (mAP) over intersection-over-union (IoU) thresholds from 0.50 to 0.95 increases from 60.4% for RT-DETR to 62.6% for Urban-DETR; precision increases from 82.9% to 86.9%. Evaluation on the Changsha University of Science and Technology Chinese Traffic Sign Detection Benchmark 2021 (CCTSDB 2021) gives 61.5% mAP over the same IoU range. These results support improved aggregate detection accuracy for the reported configurations.
Förderung
- Natural Science Foundation of Tianjin
Zitieren
APA
Gao, L., Zhu, P., Qi, G., He, C., Sun, B., & Wen, J. (2026). Urban-DETR: A Semantics-Enhanced Traffic Sign Detection Framework for Complex Urban Scenarios. Sensors, 26(22), 7204. https://doi.org/10.3390/s26227204
Vancouver
Gao L, Zhu P, Qi G, He C, Sun B, Wen J. Urban-DETR: A Semantics-Enhanced Traffic Sign Detection Framework for Complex Urban Scenarios. Sensors. 2026;26(22):7204. doi:10.3390/s26227204
BibTeX
@article{Gao2026,
author = {Gao, Liqing and Zhu, Panpan and Qi, Guanghao and He, Chengnuo and Sun, Baoshan and Wen, Jiabao},
title = {Urban-DETR: A Semantics-Enhanced Traffic Sign Detection Framework for Complex Urban Scenarios},
journal = {Sensors},
year = {2026},
volume = {26},
number = {22},
pages = {7204},
doi = {10.3390/s26227204}
}
EUVIMED