A UAV Based Concrete Crack Detection and Segmentation Using 2-Stage Convolutional Network with Transfer Learning

被引：0
作者：
Sorilla, Joses [1 ]
Chu, Timothy Scott C. [1 ]
Chua, Alvin Y. [1 ]
机构：
[1] Department of Mechanical Engineering, De La Salle University, 2401 Taft Ave. Malate, Manila
来源：
HighTech and Innovation Journal | 2024年 / 5卷 / 03期
关键词：
2-Stage CNN; Computer Vision; Crack Detection; Crack Segmentation; Transfer Learning; Unmanned Aerial Vehicles (UAV);
D O I：
10.28991/HIJ-2024-05-03-010
中图分类号：
学科分类号：
摘要：
This study explores a non-destructive testing (NDT) method for crack detection using a two-stage convolutional neural network (CNN) model, incorporating a combination of AlexNet and YOLO models through transfer learning. Crack detection is pivotal for assessing structural integrity and ensuring timely maintenance interventions. The developed model was rigorously tested in simulated environments and through physical experimentations with the use of a UAV to evaluate its effectiveness. A 2-stage model, based on AlexNet and YOLO, was developed for crack classification and segmentation. The developed model leveraged transfer learning to address limitations from traditional CNN models. A known dataset was used to evaluate the developed model, benchmarking it against other models. The classification network achieved an accuracy rate exceeding 90%, while the segmentation network successfully identified and delineated cracks in 85.71% of the images. Finally, the developed model was deployed using a UAV to perform crack detection and segmentation in a controlled environment. These results underscore the model's proficiency in both detecting and segmenting structural cracks, highlighting its potential as a reliable tool for enhancing the maintenance and safety of architectural structures. © 2024, Ital Publication. All rights reserved.
引用
收藏
页码：690 / 702
页数：12
相关论文
共 37 条
  • [11] Hamishebahar Y., Guan H., So S., Jo J., A Comprehensive Review of Deep Learning-Based Crack Detection Approaches, Applied Sciences (Switzerland), 12, 3, (2022)
  • [12] Yu S., Jia S., Xu C., Convolutional neural networks for hyperspectral image classification, Neurocomputing, 219, pp. 88-98, (2017)
  • [13] Yang F., Huo J., Cheng Z., Chen H., Shi Y., An Improved Mask R-CNN Micro-Crack Detection Model for the Surface of Metal Structural Parts, Sensors, 24, 1, (2024)
  • [14] Guo F., Liu J., Xie Q., Yu H., A two-stage framework for pixel-level pavement surface crack detection, Engineering Applications of Artificial Intelligence, 133, (2024)
  • [15] Chen Z., Wang C., Wu J., Deng C., Wang Y., Deep convolutional transfer learning-based structural damage detection with domain adaptation, Applied Intelligence, 53, 5, pp. 5085-5099, (2023)
  • [16] Brodzicki A., Piekarski M., Kucharski D., Jaworek-Korjakowska J., Gorgon M., Transfer learning methods as a new approach in computer vision tasks with small datasets, Foundations of Computing and Decision Sciences, 45, 3, pp. 179-193, (2020)
  • [17] Hammouch W., Chouiekh C., Khaissidi G., Mrabti M., Crack Detection and Classification in Moroccan Pavement Using Convolutional Neural Network, Infrastructures, 7, 11, (2022)
  • [18] Rajadurai R. S., Kang S. T., Automated vision-based crack detection on concrete surfaces using deep learning, Applied Sciences (Switzerland), 11, 11, (2021)
  • [19] Tang Y., Zhang A. A., Luo L., Wang G., Yang E., Pixel-level pavement crack segmentation with encoder-decoder network, Measurement: Journal of the International Measurement Confederation, 184, (2021)
  • [20] Ali R., Chuah J. H., Talip M. S. A., Mokhtar N., Shoaib M. A., Structural crack detection using deep convolutional neural networks, Automation in Construction, 133, (2022)
1234