Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
July 7, 2026Scientific ReportsOpen Access

Detection of underground objects from GPR data using a lightweight YOLO-based approach

View Full Paper
Ask AI
Bookmark
Share

Authors

MAMuhammed Mücahit ARVASSoftware Research and Development ConsultingAÇAhmet ÇınarFırat University

Discussion

Loading...

Member takes

Overview

Randomized trial demonstrates improved detection accuracy in GPR data, suggesting effective real-time use.

Key Points

  • This research aims to enhance underground object detection in noisy GPR data using a lightweight YOLOv8n-based framework.
  • Developed a YOLOv8n-based framework incorporating GhostConv and C3Ghost modules.
  • Trained and tested on four GPR datasets from the Roboflow platform.
  • Evaluated performance using F1-score and mean Average Precision across various IoU thresholds.
  • Achieved a 5.7% improvement in mean Average Precision on the Integrated Dataset.
  • Showed a 5.9% increase in F1 scores compared to previous methods.
  • Demonstrated reduced processing time while enhancing detection accuracy.

Cite This Study

ARVAS et al. (2026) studied this question.

synapsesocial.com/papers/6a4c9711331bc25c9e5f436fhttps://doi.org/10.1038/s41598-026-59135-0
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Comparative Evaluation of YOLO Architectures for Automated Detection of Buried Manhole Covers in GPR Radargrams2026
  2. 2Ground penetrating radar signal recognition and localization method based on improved Yolov82025
  3. 3Addressing Data Scarcity in GPR Road Defect Detection: A Novel Framework Combining Stable Diffusion and Efficient GCP-YOLO2026
  4. 4A Feature-Enhanced Deep Learning Network for GPR Hyperbolic Target Detection in B-Scan Profiles2026
  5. 5End-to-End Model Enabled GPR Hyperbolic Keypoint Detection for Automatic Localization of Underground Targets2025 · 7 citations