This approach improves detection accuracy in complex environments with reduced computational complexity, indicating better performance.
To address the issue of insufficient detection accuracy in complex environments due to scarce effective samples in underground pipeline detection using Ground Penetrating Radar (GPR), this paper presents a low complexity and high accuracy underground pipeline detection method. Validated on a dataset of 786 pipeline images, the method adopts MobileNetV4(MNv4) as the backbone network to reduce computational complexity and optimizes the loss function to handle imbalanced sample distribution. Experimental results demonstrate that it achieves superior performance in AP50, recall rate, and GFLOPs compared to conventional approaches, with reduced computational overhead , maintaining high accuracy and robustness in complex environments to provide reliable technical support for practical detection.
No takes yet. Share an insight, caveat, or question.
Zhou et al. (2025) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: