CNN-based segmentation frameworks for structural component and earthquake damage determinations using UAV images

Saida, Taisei; Rashid, Muhammad; Nemoto, Yudai; Tsukamoto, Shota; Asai, Takahiro; Nishio, Mayuko

doi:10.1007/s11803-023-2174-z

Cited by 3 publications

(1 citation statement)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Liang [20] proposed a convolutional neural network (CNN) for object detection and a principled manner of such selection based on Bayesian optimization to conduct component-level bridge column detection and observed promising results. Resorting to semantic segmentation networks, Saida et al [21] proposed a feature pyramid network (FPN) to achieve component identification for building images. Experimental results indicated that FPN was capable of remarkably learning semantic information and obtained high-precision segmentation results.…”

Section: Introductionmentioning

confidence: 99%

Component Identification and Depth Estimation for Structural Images Based on Multi-Scale Task Interaction Network

Ye,

Yu,

Liu

et al. 2024

Buildings

View full text Add to dashboard Cite

Component identification and depth estimation are important for detecting the integrity of post-disaster structures. However, traditional manual methods might be time-consuming, labor-intensive, and influenced by subjective judgments of inspectors. Deep-learning-based image visual inspection is a new approach to overcome these problems, but repeated modeling is required for different inspection tasks, which limits inspection accuracy and practical deployment efficiency. In this study, it is observed that the matched ratios of pixel pairs between component identification and depth estimation reach a high value, which indicates the dual tasks are highly related. Therefore, the Multi-Scale Task Interaction Network (MTI-Net) is proposed for structural images to simultaneously accomplish both tasks for accurate and efficient structural inspection. It propagates distilled task information from lower to higher scales. Then, it aggregates the refined task features from all scales to produce the final per-task predictions. Experiments show that MTI-Net delivers the full potential of multi-task learning, with a smaller memory footprint and higher efficiency compared to single-task learning. For the evaluation metrics of model performance, the mean Intersection over Union (mIoU) of component identification improves by 2.30, and root mean square error (RMSE) drops by 0.36 m with the aid of the multi-task strategy. The multi-task deep learning framework has great potential value in engineering applications.

show abstract

Section: Introductionmentioning

confidence: 99%

Component Identification and Depth Estimation for Structural Images Based on Multi-Scale Task Interaction Network

Ye,

Yu,

Liu

et al. 2024

Buildings

View full text Add to dashboard Cite

show abstract

Intelligent crack identification method for high‐rise buildings aided by synthetic environments

Yao,

Jiang,

Wang

et al. 2024

Structural Design Tall Build

View full text Add to dashboard Cite

SummaryCracks can develop in high‐rise buildings because of long‐term environmental changes and extreme loading events such as strong winds or earthquakes. Although deep learning‐based identification methods can efficiently identify cracks, the accuracy of crack identification in high‐rise buildings needs to be improved due to the lack of crack datasets specifically related to high‐rise structures. Moreover, the number of available images of cracks in high‐rise is limited. To this end, this paper establishes an intelligent crack identification method based on a photorealistic synthetic modeling technique. First, a computer graphics (CG) model of a high‐rise building with assumed damage is constructed. Subsequently, the CG model is utilized to generate a dataset that includes photorealistic images of the high‐rise building as well as corresponding labels for various components and types of damage. The generated dataset is then used to train a DeepLabv3 + neural network for structural component and damage identification, followed by validation by employing images of both synthetic and full‐scale high‐rise buildings. The trained network can accurately identify different components in images of the full‐scale, high‐rise building and identify cracks that are intentionally synthesized in those images. The results show that the synthetic dataset generated by the CG model not only allows for fast and efficient labeling for the purpose of neural network training but also outperforms methods that do not consider any application‐specific context in crack identification.

show abstract

Propeller-Type Wall-Climbing Robot for Visual and Hammering Inspection of Concrete Surfaces

Nishimura,

Mochiyama,

Yamaguchi

2024

IEEE Access

View full text Add to dashboard Cite

Periodic inspections are necessary to maintain concrete infrastructures. As efficient and lowcost inspection methods, visual inspection robots to detect cracks and hammering inspection robots to detect internal defects have been developed. However, these robots can generally perform only a single task. To realize multiple tasks by a robot, multiple measurement sensors need to be installed considering the stability of the robot on the wall and measurement performance. Parameters such as weight and size must be designed to ensure the stability of the robot on the wall. We propose a propeller-type wall-climbing robot that can capture images and perform hammering simultaneously while moving on the wall. The static model of robot was established by considering parameters such as the direction of the propeller's thrust force, weight, and placement of the measurement sensors. This model increases the payload for sensor installation and enables movement on dusty concrete walls with a low friction coefficient. The image captured by the inspection robot is used for crack detection and width estimation. We confirmed that the hammering sounds generated by the robot showed different frequency characteristics on clear and defective areas. The developed inspection robot showed the ability to collect adequate data for concrete health monitoring.

show abstract

CNN-based segmentation frameworks for structural component and earthquake damage determinations using UAV images

Cited by 3 publications

References 24 publications

Component Identification and Depth Estimation for Structural Images Based on Multi-Scale Task Interaction Network

Component Identification and Depth Estimation for Structural Images Based on Multi-Scale Task Interaction Network

Intelligent crack identification method for high‐rise buildings aided by synthetic environments

Propeller-Type Wall-Climbing Robot for Visual and Hammering Inspection of Concrete Surfaces

Contact Info

Product

Resources

About