Proceedings of the 2019 International Conference on Robotics, Intelligent Control and Artificial Intelligence · 2019 · 28 citations · 10 references
ComputingCivil EngineeringComputer ScienceComputer VisionMachine LearningWater Resources EngineeringCrack AssessmentDam EngineeringDam GeologyDeep LearningCrack DetectionCrack Feature ExtractionCracksDam ConstructionDeep Learning DetectionMulti-scale Feature RepresentationStorage CapacitySurface Crack Inspection
According to the statistics of the First National Water Census Bulletin in 2013[1], the number of water conservancy projects in China has exceeded 98,000, and 756 are under construction, with a total storage capacity of more than 930 billion cubic meter, ranking first in the world. While these water conservancy projects bring enormous economic and social benefits to China, they are affected by geology, hydrology, meteorology and other factors, and their buildings such as tunnels are prone to various defects. However, the current methods for detecting cracks on the dam surface are still dominated by humans. This process is not only inefficient, costly, but often incomplete. YOLOv2 lacks the capture of small defects, YOLOv3 uses three scale feature maps for prediction, and enhances the detection of small cracks. This paper aims to propose a new application scenario for applying YOLOv3 to crack detection in floodgate dam surface and share its effects.
10
Road crack detection using deep convolutional neural network
Lei Zhang, Fan Yang, Yimin D. Zhang et al. · 2016 · 1.5K citations
Leif Saager, Eric M. Maiese, Lori D. Bash et al. · Journal of Clinical Anesthesia · 2018 · 107 citations