EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Intelligent Obstacle Detection Method for Rail Transit Scenarios

Zhao Sheng, Tianyang Liu, Wei Shangguan, Yijing Wang, Yige Wang, Zhiyu He

Sensors · 06.03.2026 · 26 (5) · 1673

DOI: 10.3390/s26051673 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 06.03.2026. Verfasst von Zhao Sheng und 5 weiteren Autor:innen. Beteiligte Einrichtung: Signal and Communication Research Institute, China Academy of Railway Sciences Corporation Limited, Beijing 100081, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Science and Technology Research Project of China Railway, The State Key Laboratory of Advanced Rail Autonomous Operation, The Youth Research Project of the Signal & Communication Research Institute, China Academy of Railway Sciences Corporation Limited.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Traditional signal equipment is incapable of real-time monitoring of foreign objects intruding into track zones. To effectively ensure the operational safety of trains, this paper presents an intelligent obstacle detection approach of visual sensing for railway track regions based on YOLOv8, named ACX-YOLOv8. Built upon the baseline YOLOv8 framework, the proposed method first incorporates the spatial coordinate attention mechanism (SCAM) to enhance the model’s ability to capture long-range dependencies and local fine-grained details, thereby improving its perceptual capacity and feature representation performance. Subsequently, the cascaded dilated convolution (CDConv) module is integrated to effectively extract multi-scale image features, strengthening the model’s capability to identify foreign objects in complex railway environments. Finally, an X6 decoupled detection head is devised to further elevate the model’s detection accuracy and inference efficiency. Field experiments in real-world scenarios are conducted to validate the effectiveness of the improved algorithm. Experimental results demonstrate that the optimized ACX-YOLOv8 model has a total parameter count of 4.85 million and achieves a mean average precision at IoU = 0.5 (mAP50) of 87.1% on the test dataset, which is a 2.7% improvement over the original YOLOv8 baseline model. The lightweight property and detection precision of the model are both effectively guaranteed. Furthermore, to verify the generalization ability of the algorithm, tests are performed on the public PASCAL VOC dataset, where the mAP50 value is increased by 1.8%. These findings indicate that the ACX-YOLOv8 algorithm can detect various foreign objects invading railway track areas rapidly and accurately. It provides efficient and reliable technical support for real-time obstacle monitoring in complex and variable railway track environments and contributes to enhancing the safety and intelligentization level of railway operations.

Schlagwörter

Stichwörter der Autor:innen

CDConvYOLOv8detection decoupled headrailway obstacle detectionvisual sensing

Autor:innen und Institutionen

  • Signal and Communication Research Institute, China Academy of Railway Sciences Corporation Limited, Beijing 100081, China.
  • Cooperation and Development Department, China Academy of Railway Sciences Corporation Limited, Beijing 100081, China.
  • School of Automation and Intelligence, Beijing Jiaotong University, Beijing 100044, China.

Förderung

  • The Science and Technology Research Project of China Railway
  • The State Key Laboratory of Advanced Rail Autonomous Operation
  • The Youth Research Project of the Signal & Communication Research Institute, China Academy of Railway Sciences Corporation Limited
  • Science and Technology Research Project of China Railway
  • State Key Laboratory of Advanced Rail Autonomous Operation
  • Youth Research Project of the Signal and Communication Research Institute, China Academy of Railway Sciences Corporation Limited

Zitieren

APA

Sheng, Z., Liu, T., Shangguan, W., Wang, Y., Wang, Y., & He, Z. (2026). An Intelligent Obstacle Detection Method for Rail Transit Scenarios. Sensors, 26(5), 1673. https://doi.org/10.3390/s26051673

Vancouver

Sheng Z, Liu T, Shangguan W, Wang Y, Wang Y, He Z. An Intelligent Obstacle Detection Method for Rail Transit Scenarios. Sensors. 2026;26(5):1673. doi:10.3390/s26051673

BibTeX
@article{Sheng2026,
  author = {Sheng, Zhao and Liu, Tianyang and Shangguan, Wei and Wang, Yijing and Wang, Yige and He, Zhiyu},
  title = {An Intelligent Obstacle Detection Method for Rail Transit Scenarios},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {5},
  pages = {1673},
  doi = {10.3390/s26051673}
}
Kostenlos starten →