Autonomous Structural Visual Inspection Using Region‐Based Deep Learning for Detecting Multiple Damage Types

By Young-Jin Cha, Wooram Choi, Gahyun Suh, Sadegh Mahmoudkhani, Oral Büyüköztürk. Comput. Aided Civ. Infrastructure Eng., 2018

1,419 citations recorded by the source corpus.

Subfields: Civil and Structural Engineering, Mechanical Engineering

View Paper: https://www.semanticscholar.org/paper/15a4e2a15f20ed77609a70fb268cbcfafa21df54

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Civil and Structural Engineering

In Mechanical Engineering

Citations in the corpus

Automatic pixel‐level multiple damage detection of concrete structure using fully convolutional network (2019, methodology): “However, the CNN method has to adopt a sliding window technique to localize the detected damage (Cha et al., 2017a; Xue & Li, 2018).”
A Fast Detection Method via Region‐Based Fully Convolutional Neural Networks for Shield Tunnel Lining Defects (2018, methodology): “Cha et al. (2017b) built a new model with region-based faster CNN (Faster R-CNN), which can be used to detect ﬁve different damage types including concrete crack, steel corrosion with two levels (medium and high), bolt corrosion, and steel delamination.”
Deep Transfer Learning for Image‐Based Structural Damage Recognition (2018, methodology): “…et al. (2016) applied VGG-F (F for “fast”) CNN architecture to collapse classiﬁcation based on collected large-scale images from reconnaissance efforts; Cha et al. (2017a, 2017b) used a deep CNN to detect concrete cracks without calculating the defect features and proposed a region-based…”
Automatic Metallic Surface Defect Detection and Recognition with Convolutional Neural Networks (2018, methodology): “[33] developed a structural damage detection method based on Faster R-CNN to detect five types of surface damages: concrete cracks, steel corrosion (medium and high levels), bolt corrosion, and steel delamination.”
Encoder–decoder network for pixel‐level road crack detection in black‐box images (2019, methodology): “Cha, Choi, Suh, Mahmoudkhani, and Büyüköztürk (2018) proposed a structural visual inspection method using Faster Region-based CNN.”
Automatic crack classification and segmentation on masonry surfaces using convolutional neural networks and transfer learning (2021, background): “These two classification techniques have been extensively used to detect cracks and other defects, and have shown promising results [11,14 – 16].”
Comparison of deep convolutional neural networks and edge detectors for image-based crack detection in concrete (2018, methodology): “DCNN can be used for crack detection in three ways: classification [42], localization [41], or segmentation.”
Advances in Computer Vision-Based Civil Infrastructure Inspection and Monitoring (2019, methodology): “[125] studied the use of Faster R-CNN, a region-based method proposed by Ren et al.”
Autonomous UAVs for Structural Health Monitoring Using Deep Learning and an Ultrasonic Beacon System with Geo‐Tagging (2018, methodology): “This CNN performance was well matched to the author’s previous results using deep CNN-based damage detection (Cha et al., 2017a).”
A systematic review of convolutional neural network-based structural condition assessment techniques (2021, methodology): “…CNN Acceleration time-histories Behrouzi and Pantoza (2018) Post-earthquake inspection DL network Tagged images of roadways and railways Kang and Cha (2018) Structural inspection where using GPS is not feasible Deep CNN with sliding window Geo-tagging of a video stream from a UAV Patterson et…”
Automatic Classification of Defective Photovoltaic Module Cells in Electroluminescence Images (2018, methodology): “Cha et al. [17] additionally investigated defect localization using the modern learning-based segmentation approaches for region proposals based on the Faster R-CNN framework which can perform in real-time.”
TDD-net: a tiny defect detection network for printed circuit boards (2019, methodology): “Y. Cha et al. [21] developed a structural damage detection method based on Faster R-CNN to detect ﬁ ve types of surface damages: concrete cracks, steel corrosion (medium and high levels), bolt corrosion, and steel delamination.”