EUVIMEDEUVIMED entdecken
Crossref

Stereo Real-Time 3-D Object Detection With Adaptive ROI Enhancement for Rail Transit

Xin Liu, Quanli Liu, Wei Wang, Liyong Zhang

IEEE Transactions on Instrumentation and Measurement · 2026 · 75 · 5015516-5015516

DOI: 10.1109/tim.2026.3718568 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Instrumentation and Measurement, 2026. Verfasst von Xin Liu und 3 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Science and Technology Joint Plan of Liaoning Province, Fundamental Research Funds for the Central Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid and accurate obstacle detection is crucial for reducing collision risk in urban rail transit. Given the long braking distance and limited onboard computing resources of urban rail vehicles, this article proposes a real-time 3-D object detection model based on a monocular-stereo cascaded architecture, named ARE-stereo. To mitigate the loss of critical stereo cues due to inaccurate depth estimates in the monocular stage, two novel optimization strategies are proposed: pseudo disparity guided enhancement (PDE) and adaptive region of interest augmentation (ARA). The PDE strategy warps right-view region-of-interest (ROI) features into the left image coordinate frame guided by pseudo disparity and fuses them with left-view ROI features to increase the confidence of proposals suppressed in the monocular stage. During the stereo stage, the ARA strategy dynamically expands the ROIs, effectively preventing the loss of object-relevant stereo features without introducing excessive redundancy, achieving a balance between inference speed and accuracy. Experiments on the KITTI dataset demonstrate that ARE-stereo achieves competitive performance in both inference speed and accuracy. Furthermore, the validation in real-world urban rail transit scenarios confirms the practical effectiveness of our model, providing a viable solution for high-precision obstacle detection in resource-constrained urban rail transit environments. Our code is available at https://github.com/Xliu1009/ARE-stereo

Förderung

  • National Natural Science Foundation of China
  • Science and Technology Joint Plan of Liaoning Province
  • Fundamental Research Funds for the Central Universities
  • Key Field Innovation Team Support Plan of Dalian, China

Zitieren

APA

Liu, X., Liu, Q., Wang, W., & Zhang, L. (2026). Stereo Real-Time 3-D Object Detection With Adaptive ROI Enhancement for Rail Transit. IEEE Transactions on Instrumentation and Measurement, 75, 5015516-5015516. https://doi.org/10.1109/tim.2026.3718568

Vancouver

Liu X, Liu Q, Wang W, Zhang L. Stereo Real-Time 3-D Object Detection With Adaptive ROI Enhancement for Rail Transit. IEEE Transactions on Instrumentation and Measurement. 2026;75:5015516-5015516. doi:10.1109/tim.2026.3718568

BibTeX
@article{Liu2026,
  author = {Liu, Xin and Liu, Quanli and Wang, Wei and Zhang, Liyong},
  title = {Stereo Real-Time 3-D Object Detection With Adaptive ROI Enhancement for Rail Transit},
  journal = {IEEE Transactions on Instrumentation and Measurement},
  year = {2026},
  volume = {75},
  pages = {5015516--5015516},
  doi = {10.1109/tim.2026.3718568}
}
Kostenlos starten →