Development of an Autonomous Road Surface Damage Inspection Program Using Deep Convolutional Neural Network

Thuyet, Dang Quoc; Jomoto, Masakazu; HIRAKAWA, Kazunari; SWE, Yin Lei LEI

doi:10.2208/journalofjsce.10.1_235

Cited by 1 publication

(1 citation statement)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Maeda et al (2018) developed a road damage detection system using smartphone images in Japan. Thuyet et al (2022) built an autonomous road inspection system using deep learning and data obtained utilizing a laser crack measurement system (LCMS) to detect cracks and patches. Other studies such as Goncalves and Givigi (2016) and Hong et al (2020) developed methods to detect and measure crack defects in civil infrastructure from simple image data containing a few objects.…”

Section: Datasets Simple Segmentation and Deep Learningmentioning

confidence: 99%

Probabilistic Management of Pavement Defects With Image Processing Techniques

Obunguta,

Matsushima,

Susaki

2024

Journal of Civil Engineering and Management

View full text Add to dashboard Cite

Pavement management has traditionally relied on human-based decisions. In many countries, however, the pavement stock has recently increased, while the number of management experts has declined, posing the challenge of how to efficiently manage the larger stock with fewer resources. Compared to efficient computer-based techniques, human-based methods are more prone to errors that compromise analysis and decisions. This research built a robust probabilistic pavement management model with a safety metric output using inputs from image processing tested against the judgment of experts. The developed model optimized road pavement safety. The study explored image processing techniques considering the trade-off between processing cost and output accuracy, with annotation precision and intersection over union (IoU) set objectively. The empirical applicability of the model is shown for selected roads in Japan.

show abstract

Section: Datasets Simple Segmentation and Deep Learningmentioning

confidence: 99%