A low-altitude near-real-time building earthquake damage assessment method

Abstract

The invention provides a low-altitude near-real-time building earthquake damage assessment method. The evaluation method includes relevant data preparation, building image segmentation, and earthquake damage assessment based on CNN model. This assessment method is expected to provide a reference for rapid assessment and emergency rescue of regional building earthquake damage. With the continuous application of this image segmentation method in actual earthquakes, more and more building damage images will be obtained, thereby significantly expanding the image library used to train the CNN classifier, and ultimately improving the prediction accuracy and reliability of the CNN classifier.

Description

technical field [0001] The invention relates to the technical field of civil engineering and earthquake engineering, in particular to a building earthquake damage assessment method. Background technique [0002] After the earthquake, in order to assist decision-making and emergency rescue, it is necessary to conduct a rapid assessment of the earthquake damage of the entire region. The current manual assessment method usually requires a lot of time, manpower and material resources, and cannot assess the earthquake damage of a large-scale building in a relatively short period of time, so the efficiency is low. However, the method based on high-altitude remote sensing can only observe the damage of ground buildings from a higher perspective, and cannot reliably grasp the damage on building facades, and its accuracy is low. Therefore, it is urgent to develop a low-altitude rapid building earthquake damage assessment method. Contents of the invention [0003] The purpose of t...

AI Technical Summary

Problems solved by technology

The current manual assessment method usually takes a lot of time, manpower and material resources, and cannot assess the earthquake damage of a large-scale building in a short period of time, and the efficiency is low

However, the method based on high-altitude remote sensing can only observe the damage of ground buildings from a higher perspective, and cannot reliably grasp the damage on building facades, and its accuracy is low.

Images