AI-enhanced Algorithm for Structural Health Monitoring - An Image-based Concrete Crack Detection Method Using Convolutional Neural Networks
| dc.contributor.author | LUO, XI | |
| dc.contributor.author | GUO, JIA | |
| dc.contributor.department | Chalmers tekniska högskola / Institutionen för arkitektur och samhällsbyggnadsteknik (ACE) | sv |
| dc.contributor.examiner | Zandi, Kamyab | |
| dc.date.accessioned | 2021-08-10T13:51:03Z | |
| dc.date.available | 2021-08-10T13:51:03Z | |
| dc.date.issued | 2021 | sv |
| dc.date.submitted | 2020 | |
| dc.description.abstract | The thriving of image-based damage detection methods for structure health monitoring especially the application of UAVs for structure inspection has been a trend in the recent years. The concept of Digital Twin is to build a living digital representation for structures which requires a very fast data processing procedure. This paper proposes a CNN-based crack detection method that can recognize and extract cracks from photos of concrete structures, which can enhance the data processing for Digital Twin. The algorithm consists of two subsequent procedures, classification and segmentation, achieved by two convolutional neural networks respectively. First, full images are divided into patches and classified as positive and negative. Then, those sub-images classified as positive where cracks are visible are further processed by the image segmentation procedure to obtain the pixel level shapes of the cracks. For the classification part, the performance of transfer learning models based on pre-trained VGG16, Inception V3, MobileNet and DenseNet169 is compared with different classifier. Finally, the CNN based on MobileNet was trained with 30,000 training images and can reach 97% testing accuracy and 0.96 F1 score on testing image. For the segmentation part, different neural networks based on the elegant U-net architecture are built and tested. The models are trained with 3840 crack images and annotated ground truth and compared quantitatively and qualitatively. The model with the best performance can reach 88% sensitivity on test data set. The combination of the classification and segmentation neural networks can achieve an image-based crack detection method with high efficiency and accuracy. The algorithm can process any full image size as input. Compared with most machine learning based crack detection algorithms using sub-image classification, a relatively larger patch size is used in this paper and in this way the classification is more robust and accurate. On the other hand, the negative area in the full image will not be concerned in the segmentation procedure and this fact not only saves a lot of computational power but also significantly increases the accuracy compared to the segmentation performed on full images. | sv |
| dc.identifier.coursecode | ACEX30 | sv |
| dc.identifier.uri | https://hdl.handle.net/20.500.12380/303880 | |
| dc.language.iso | eng | sv |
| dc.setspec.uppsok | Technology | |
| dc.subject | Digital Twin, Crack Detection, Convolutional Neural Network, | sv |
| dc.subject | Computer Vision, Image Classification, Semantic Segmentation | sv |
| dc.title | AI-enhanced Algorithm for Structural Health Monitoring - An Image-based Concrete Crack Detection Method Using Convolutional Neural Networks | sv |
| dc.type.degree | Examensarbete för masterexamen | sv |
| dc.type.uppsok | H | |
| local.programme | Structural engineering and building technology (MPSEB), MSc |