Defect Detection of Subway Tunnels Using Advanced U-Net Network

Wang, An; Togo, Ren; Ogawa, Takahiro; Haseyama, Miki

doi:10.3390/s22062330

Cited by 15 publications

(7 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various image segmentation algorithms have been developed, but more recently, the success of deep learning models in various vision applications has led to a large number of studies on the development of image segmentation methods using deep learning architectures. U-Net is a convolution neural network [27] originally proposed for medical imaging segmentation, but various research has shown its potential for other segmentation tasks as well [28][29][30]. The U-Net network is fast, can segment a 512 × 512 image without the need for multiple runs and allows for learning with very few labelled images.…”

Section: Unet Model-based Extraction Of Contours Of the Garments' Shapementioning

confidence: 99%

An Intelligent Solution for Automatic Garment Measurement Using Image Recognition Technologies

Paulauskaitė-Tarasevičienė

Noreika

Purtokas

et al. 2022

Applied Sciences

View full text Add to dashboard Cite

Global digitization trends and the application of high technology in the garment market are still too slow to integrate, despite the increasing demand for automated solutions. The main challenge is related to the extraction of garment information-general clothing descriptions and automatic dimensional extraction. In this paper, we propose the garment measurement solution based on image processing technologies, which is divided into two phases, garment segmentation and key points extraction. UNet as a backbone network has been used for mask retrieval. Separate algorithms have been developed to identify both general and specific garment key points from which the dimensions of the garment can be calculated by determining the distances between them. Using this approach, we have resulted in an average 1.27 cm measurement error for the prediction of the basic measurements of blazers, 0.747 cm for dresses and 1.012 cm for skirts.

show abstract

Section: Unet Model-based Extraction Of Contours Of the Garments' Shapementioning

confidence: 99%

An Intelligent Solution for Automatic Garment Measurement Using Image Recognition Technologies

Paulauskaitė-Tarasevičienė

Noreika

Purtokas

et al. 2022

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…This is achieved through the extraction of image edge information, 2 the integration of deep learning technology, 3 the enhancement of deep feature fusion algorithms, 4 and the proposal of novel network architectures. 5 Various methods, such as linear array cameras and computer vision, 6 ultrasonic detection, 7 infrared characterization, 8 and others, have been proposed for the safety inspection of track and train structures. These methods have the potential to enhance the level of intelligent safety detection and enable early detection and warning of certain safety hazards.…”

Section: Introductionmentioning

confidence: 99%

“…To address conspicuous abnormal conditions, such as track cracks, foreign objects on subway sleepers, and train bearing defects, scholars frequently employ image processing technology to enable detection. This is achieved through the extraction of image edge information, 2 the integration of deep learning technology, 3 the enhancement of deep feature fusion algorithms, 4 and the proposal of novel network architectures 5 . Various methods, such as linear array cameras and computer vision, 6 ultrasonic detection, 7 infrared characterization, 8 and others, have been proposed for the safety inspection of track and train structures.…”

Section: Introductionmentioning

confidence: 99%

Invisible track bed defect classification method based on distributed optical fiber sensing system and FFT Attention Transformer model

Chen,

Lin,

et al. 2024

Opt. Eng.

View full text Add to dashboard Cite

An invisible track bed defect classification method based on distributed optical fiber sensing data acquisition and an attention Transformer model mechanism under the frequency domain is proposed. The vibration sensing data contain structural safety information of vehicles, rails, track beds, etc., covering the entire time period and entire track area of subway operation. To classify the invisible track bed defect rapidly and accurately, the original vibration signals are first reduced by downsampling and envelope signal extraction. According to the regular characteristics of different types of signals, an fast Fourier transform (FFT) Attention Transformer (FFT-Attn-Transformer) sequence feature extraction architecture with a high recognition accuracy is proposed for model training.The results demonstrate that the accuracy, precision, recall rate, and F 1-score are all above 98% using the proposed model, and the recognition accuracy of the defect test area is 99.47%, which has extremely high stability and accuracy, providing an innovative and feasible idea for the lack of effective monitoring scheme for invisible track bed defects.

show abstract

“…Three optimization methods of data augmentation, transfer learning, and cascade strategy were further used to improve model accuracy. Wang et al 24 introduced atrous spatial pyramid pooling and inception modules into U-Net architecture to improve the segmentation performance in subway tunnel.…”

Section: Introductionmentioning

confidence: 99%

Efficient segmentation of water leakage in shield tunnel lining with convolutional neural network

Wang

Han

et al. 2023

Structural Health Monitoring

View full text Add to dashboard Cite

Water leakage is a critical factor reflecting the structural safety of shield tunnels. Computer vision provides new opportunities to overcome the shortcomings of manual visual inspection and realize automatic detection of water leakage regions. In this study, we propose a leakage segmentation model with an encoder–decoder structure. The encoder adopts multi-branch convolutional attention for feature fusion, and the decoder adopts a lightweight design that only contains multi-layer perceptron. Standard convolution in multi-branch is decomposed to two depth-wise strip convolutions to realize lightweight design and extract strip-like features. Extensive ablation and comparative studies were conducted to test model performance. Test results show that our model achieves robust detection of water leakage under strong noise background, reaching an intersection over union of 90.75% with performance-computation trade-off. Consequently, the proposed method can be an effective alternative to the current visual inspection technologies, and provide a nearly automated inspection platform for shield tunnels.

show abstract

Defect Detection of Subway Tunnels Using Advanced U-Net Network

Cited by 15 publications

References 57 publications

An Intelligent Solution for Automatic Garment Measurement Using Image Recognition Technologies

An Intelligent Solution for Automatic Garment Measurement Using Image Recognition Technologies

Invisible track bed defect classification method based on distributed optical fiber sensing system and FFT Attention Transformer model

Efficient segmentation of water leakage in shield tunnel lining with convolutional neural network

Contact Info

Product

Resources

About