EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Research on an Automatic Detection Method for Response Keypoints of Three-Dimensional Targets in Directional Borehole Radar Profiles

Xiaosong Tang, Maoxuan Xu, Feng Yang, Jialin Liu, Suping Peng, Xu Qiao

Remote Sensing · 07.04.2026 · 18 (7) · 1102

DOI: 10.3390/rs18071102 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 07.04.2026. Verfasst von Xiaosong Tang und 5 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

During the interpretation of Borehole Radar (BHR) B-scan profiles, the accurate determination of the azimuth of geological targets in three-dimensional space is a critical issue for achieving precise anomaly localization and spatial structure inversion. However, existing directional BHR anomaly localization methods exhibit limited intelligence, insufficient adaptability to multi-site data, and weak generalization capability, rendering them inadequate for engineering applications under complex geological conditions. To address these challenges, a robust deep learning model, termed BSS-Pose-BHR, is developed based on YOLOv11n-pose for keypoint detection in directional BHR profiles. The model incorporates three key optimizations: Bi-Level Routing Attention (BRA) replaces Multi-Head Self-Attention (MHSA) in the backbone to improve computational efficiency; Conv_SAMWS enhances keypoint-related feature weighting in the backbone and neck; and Spatial and Channel Reconstruction Convolution (SCConv) is integrated into the detection head to reduce redundancy and strengthen local feature extraction, thereby improving suitability for keypoint detection tasks. In addition, a three-dimensional electromagnetic model of limestone containing a certain density of clay particles is established to construct a simulation dataset. On the simulated test set, compared with current mainstream deep learning approaches and conventional directional borehole radar anomaly localization algorithms, BSS-Pose-BHR achieves superior performance, with an mAP50(B) of 0.9686, an mAP50–95(B) of 0.7712, an mAP50(P) of 0.9951, and an mAP50–95(P) of 0.9952. Ablation experiments demonstrate that each proposed module contributes significantly to performance improvement. Compared with the baseline, BSS-Pose-BHR improves mAP50(B) by 5.39% and mAP50(P) by 0.86%, while increasing model weight by only 1.05 MB, thereby achieving a reasonable trade-off between detection accuracy and complexity. Furthermore, indoor physical model experiments validate the effectiveness of the method on measured data. Robustness experiments under different Peak Signal-to-Noise Ratio (PSNR) conditions and varying missing-trace rates indicate that BSS-Pose-BHR maintains high detection accuracy under moderate noise and data loss, demonstrating strong engineering applicability and practical value.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Tang, X., Xu, M., Yang, F., Liu, J., Peng, S., & Qiao, X. (2026). Research on an Automatic Detection Method for Response Keypoints of Three-Dimensional Targets in Directional Borehole Radar Profiles. Remote Sensing, 18(7), 1102. https://doi.org/10.3390/rs18071102

Vancouver

Tang X, Xu M, Yang F, Liu J, Peng S, Qiao X. Research on an Automatic Detection Method for Response Keypoints of Three-Dimensional Targets in Directional Borehole Radar Profiles. Remote Sensing. 2026;18(7):1102. doi:10.3390/rs18071102

BibTeX
@article{Tang2026,
  author = {Tang, Xiaosong and Xu, Maoxuan and Yang, Feng and Liu, Jialin and Peng, Suping and Qiao, Xu},
  title = {Research on an Automatic Detection Method for Response Keypoints of Three-Dimensional Targets in Directional Borehole Radar Profiles},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {7},
  pages = {1102},
  doi = {10.3390/rs18071102}
}
Kostenlos starten →