Traffic Accident Rescue Action Recognition Method Based on Real-Time UAV Video
Drones · 24.07.2025 · 9 (8) · 519
DOI: 10.3390/drones9080519 ↗Kurz gefasst
Fachartikel in der Zeitschrift Drones, online erschienen am 24.07.2025. Verfasst von Bo Yang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Central Government Guides Local Funds for Science and Technology Development, Fundamental Research Funds for the Central Universities, Hebei Province higher education teaching reform research and practice project.
Abstract (Originalsprache)
Low-altitude drones, which are unimpeded by traffic congestion or urban terrain, have become a critical asset in emergency rescue missions. To address the current lack of emergency rescue data, UAV aerial videos were collected to create an experimental dataset for action classification and localization annotation. A total of 5082 keyframes were labeled with 1–5 targets each, and 14,412 instances of data were prepared (including flight altitude and camera angles) for action classification and position annotation. To mitigate the challenges posed by high-resolution drone footage with excessive redundant information, we propose the SlowFast-Traffic (SF-T) framework, a spatio-temporal sequence-based algorithm for recognizing traffic accident rescue actions. For more efficient extraction of target–background correlation features, we introduce the Actor-Centric Relation Network (ACRN) module, which employs temporal max pooling to enhance the time-dimensional features of static backgrounds, significantly reducing redundancy-induced interference. Additionally, smaller ROI feature map outputs are adopted to boost computational speed. To tackle class imbalance in incident samples, we integrate a Class-Balanced Focal Loss (CB-Focal Loss) function, effectively resolving rare-action recognition in specific rescue scenarios. We replace the original Faster R-CNN with YOLOX-s to improve the target detection rate. On our proposed dataset, the SF-T model achieves a mean average precision (mAP) of 83.9%, which is 8.5% higher than that of the standard SlowFast architecture while maintaining a processing speed of 34.9 tasks/s. Both accuracy-related metrics and computational efficiency are substantially improved. The proposed method demonstrates strong robustness and real-time analysis capabilities for modern traffic rescue action recognition.
Förderung
- Central Government Guides Local Funds for Science and Technology Development
- Fundamental Research Funds for the Central Universities
- Hebei Province higher education teaching reform research and practice project
Zitieren
APA
Yang, B., Lu, J., Liu, T., Zhang, B., Geng, C., Tian, Y., & Zhang, S. (2025). Traffic Accident Rescue Action Recognition Method Based on Real-Time UAV Video. Drones, 9(8), 519. https://doi.org/10.3390/drones9080519
Vancouver
Yang B, Lu J, Liu T, Zhang B, Geng C, Tian Y, et al. Traffic Accident Rescue Action Recognition Method Based on Real-Time UAV Video. Drones. 2025;9(8):519. doi:10.3390/drones9080519
BibTeX
@article{Yang2025,
author = {Yang, Bo and Lu, Jianan and Liu, Tao and Zhang, Bixing and Geng, Chen and Tian, Yan and Zhang, Siyu},
title = {Traffic Accident Rescue Action Recognition Method Based on Real-Time UAV Video},
journal = {Drones},
year = {2025},
volume = {9},
number = {8},
pages = {519},
doi = {10.3390/drones9080519}
}
EUVIMED