Suppr超能文献

在移动隧道扫描系统中使用无参考图像质量评估优化基于深度学习的裂缝检测

Optimizing Deep Learning-Based Crack Detection Using No-Reference Image Quality Assessment in a Mobile Tunnel Scanning System.

作者信息

Lee Chulhee, Kim Donggyou, Kim Dongku

机构信息

Department of Geotechnical Engineering Research, Korea Institute of Civil Engineering and Building Technology (KICT), Goyang-Si 10223, Gyeonggi-Do, Republic of Korea.

出版信息

Sensors (Basel). 2025 Sep 2;25(17):5437. doi: 10.3390/s25175437.

Abstract

The mobile tunnel scanning system (MTSS) enables efficient tunnel inspection; however, motion blur (MB) generated at high travel speeds remains a major factor undermining the reliability of deep-learning-based crack detection. This study focuses on investigating how horizontally oriented MB in MTSS imagery affects the crack-detection performance of convolutional neural networks (CNNs) and proposes a data-centric quality-assurance framework that leverages no-reference image quality assessment (NR-IQA) to optimize model performance. By intentionally applying MB to both public and real-world MTSS datasets, we analyzed performance changes in ResNet-, VGG-, and AlexNet-based models and established the correlations between four NR-IQA metrics (BRISQUE, NIQE, PIQE, and CPBD) and performance (F1 score). As the MB intensity increased, the F1 score of ResNet34 dropped from 89.43% to 4.45%, confirming the decisive influence of image quality. PIQE and CPBD exhibited strong correlations with F1 (-0.87 and +0.82, respectively), emerging as the most suitable indicators for horizontal MB. Using thresholds of PIQE ≤ 20 and CPBD ≥ 0.8 to filter low-quality images improved the AlexNet F1 score by 1.46%, validating the effectiveness of the proposed methodology. The proposed framework objectively assesses MTSS data quality and optimizes deep learning performance, enhancing the reliability of intelligent infrastructure maintenance systems.

摘要

移动隧道扫描系统(MTSS)能够实现高效的隧道检测;然而,在高行驶速度下产生的运动模糊(MB)仍然是削弱基于深度学习的裂缝检测可靠性的主要因素。本研究着重探讨MTSS图像中水平方向的运动模糊如何影响卷积神经网络(CNN)的裂缝检测性能,并提出一种以数据为中心的质量保证框架,该框架利用无参考图像质量评估(NR-IQA)来优化模型性能。通过有意地将运动模糊应用于公共和真实世界的MTSS数据集,我们分析了基于ResNet、VGG和AlexNet的模型的性能变化,并建立了四个NR-IQA指标(BRISQUE、NIQE、PIQE和CPBD)与性能(F1分数)之间的相关性。随着运动模糊强度的增加,ResNet34的F1分数从89.43%降至4.45%,证实了图像质量的决定性影响。PIQE和CPBD与F1表现出很强的相关性(分别为-0.87和+0.82),成为水平运动模糊最合适的指标。使用PIQE≤20和CPBD≥0.8的阈值来过滤低质量图像,AlexNet的F1分数提高了1.46%,验证了所提出方法的有效性。所提出的框架客观地评估MTSS数据质量并优化深度学习性能,提高了智能基础设施维护系统的可靠性。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e919/12431290/6502cf1ab302/sensors-25-05437-g001.jpg

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验