Development of a solution for collecting crack images on concrete surfaces to assess the structural health of bridges using drone

Ngo, Binh; Luong, Chieu X.; Ngo, Long; Luong, Hoang Minh

doi:10.1080/24751839.2023.2185448

Cited by 1 publication

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Smaoui et al [10] proposed a method for planning paths for autonomous scanning tasks of concrete structures based on onboard cameras, collecting and transmitting images to estimate the extent of damage caused by cracks. Ngo et al [11] used drones to collect images of cracks and defects on the surface of concrete bridges, developing an effective method for assessing the structural integrity of concrete bridges. Compared with traditional cameras that require manual photography, UAVs have the advantage of being lightweight and convenient, and they feature automatic obstacle avoidance capabilities which enable them to reach previously inaccessible areas.…”

Section: Introductionmentioning

confidence: 99%

Deep-Learning- and Unmanned Aerial Vehicle-Based Structural Crack Detection in Concrete

Jin,

Zhang,

Chen

et al. 2023

Buildings

View full text Add to dashboard Cite

Deep-learning- and unmanned aerial vehicle (UAV)-based methods facilitate structural crack detection for tall structures. However, contemporary datasets are generally established using images taken with handheld or vehicle-mounted cameras. Thus, these images might be different from those taken by UAVs in terms of resolution and lighting conditions. Considering the difficulty and complexity of establishing a crack image dataset, making full use of the current datasets can help reduce the shortage of UAV-based crack image datasets. Therefore, the performance evaluation of existing crack image datasets in training deep neural networks (DNNs) for crack detection in UAV images is essential. In this study, four DNNs were trained with different architectures based on a publicly available dataset and tested using a small UAV-based crack image dataset with 648 +pixel-wise annotated images. These DNNs were first tested using the four indices of precision, recall, mIoU, and F1, and image tests were also conducted for intuitive comparison. Moreover, a field experiment was carried out to verify the performance of the trained DNNs in detecting cracks from raw UAV structural images. The results indicate that the existing dataset can be useful to train DNNs for crack detection from UAV images; the TransUNet achieved the best performance in detecting all kinds of structural cracks.

show abstract

Section: Introductionmentioning

confidence: 99%