HMPACN-YOLO: Traffic Signal Head Detection in Complex Road Scenes via YOLO11 and Hypergraph Computation
Applied Sciences · 18.11.2026 · 16 (22) · 11435
DOI: 10.3390/app162211435 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 18.11.2026. Verfasst von Zhi Chen und 6 weiteren Autor:innen. Die Arbeit nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Traffic signal head detection in complex road scenes is challenged by variations in target scale, progressive degradation of fine-grained features, interference from visually similar light sources, and limited aggregation of contextual information across spatial locations. To address these challenges, we propose HMPACN-YOLO, a traffic signal head detector built on YOLO11n. The name combines Hyper-MFM (HM), CSP-PMSFA (P), ADown (A), C2TSSA-DyT (C), and NWD-Focaler-WisePIoUv2 (N). Using YOLO11n as the baseline, the method jointly optimizes feature representation, information preservation, bounding-box regression, and model compression. First, Hyper-MFM combines hypergraph propagation with adaptive feature fusion to aggregate contextual information and model higher-order dependencies among spatial feature nodes. Second, multi-scale feature extraction, detail-preserving downsampling, and adaptive attention are integrated to mitigate the loss of fine-grained information during downsampling and suppress spurious background responses under uneven illumination. Third, an NWD-Focaler-WisePIoUv2 composite loss is designed to improve robustness to slight localization deviations of signal-head targets and enhance bounding-box regression across samples with a broad quality distribution. In addition, cross-granularity transfer learning is used for initialization, and Layer-Adaptive Magnitude-based Pruning (LAMP) with subsequent L2 knowledge distillation is applied to compress the enhanced model. Experiments on the self-constructed LTLD dataset use 856 validation images for configuration selection and a held-out test split of 1712 images for final evaluation. On the test split, HMPACN-YOLO achieves 83.2% mAP@0.5 and 41.2% mAP@0.5:0.95, compared with 81.3% and 39.4% for YOLO11n, corresponding to differences of 1.9 and 1.8 percentage points in a single training run per configuration. At 640 × 640 input resolution, LAMP pruning reduces the enhanced model from 7.8 to 4.8 GFLOPs, compared with 6.3 GFLOPs for YOLO11n; L2 distillation retains the pruned inference architecture. This final configuration represents the combined architecture and compression pipeline. The reported performance gains were observed under the evaluated settings; their consistency across independent training runs remains to be assessed. No wall-clock latency or frame-rate measurement was performed, so the reported complexity figures describe arithmetic cost only.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Chen, Z., Ku, Y., Zhang, C., Cao, X., Han, W., Lu, B., & Wu, Y. (2026). HMPACN-YOLO: Traffic Signal Head Detection in Complex Road Scenes via YOLO11 and Hypergraph Computation. Applied Sciences, 16(22), 11435. https://doi.org/10.3390/app162211435
Vancouver
Chen Z, Ku Y, Zhang C, Cao X, Han W, Lu B, et al. HMPACN-YOLO: Traffic Signal Head Detection in Complex Road Scenes via YOLO11 and Hypergraph Computation. Applied Sciences. 2026;16(22):11435. doi:10.3390/app162211435
BibTeX
@article{Chen2026,
author = {Chen, Zhi and Ku, Yaokun and Zhang, Chen’ao and Cao, Xiaoxue and Han, Wenyan and Lu, Bailiang and Wu, Yutian},
title = {HMPACN-YOLO: Traffic Signal Head Detection in Complex Road Scenes via YOLO11 and Hypergraph Computation},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {22},
pages = {11435},
doi = {10.3390/app162211435}
}
EUVIMED