A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Research on intelligent recognition method of tunnel lining cracks based on small objective recognition algorithm
With the rapid development of today’s highways, the number of tunnels is also increasing. Cracks, as one of the most common and serious diseases detected in tunnels, are an important parameter indicator to evaluate the apparent structural quality of tunnel linings. When the crack length or width exceeds the allowable range, it can affect the bearing capacity of the reinforced concrete structure and even lead to instability and sudden collapse of the lining, posing a great threat to human life and property. For this reason, image acquisition of tunnels is needed regularly to analyze the disease. At present, the rapid detection means of highway tunnels is still in the exploration stage, and the technical bottlenecks common to only a few products at home and abroad limit the promotion and application of the system. For the existing tunnel lining acquisition images exist in poor picture quality, disease is not prominent and manual labeling disease inefficiency and other problems, innovation based on image processing, deep learning and other methods to develop a small target recognition algorithm for tunnel lining cracks, and build a tunnel crack intelligent identification system to achieve intelligent identification detection of crack disease on highway tunnel scenes. The use of tunnel crack intelligent identification system can significantly reduce the detection time of crack disease and human detection cost investment, at the same time, can also effectively avoid the manual detection of fatigue situation prone to misidentification, omission identification and other problems, play an irreplaceable role in the protection of highway tunnel safe operation, timely detection of highway initial disease, reducion of maintenance costs and other aspects, has significant economic and social benefits.
Research on intelligent recognition method of tunnel lining cracks based on small objective recognition algorithm
With the rapid development of today’s highways, the number of tunnels is also increasing. Cracks, as one of the most common and serious diseases detected in tunnels, are an important parameter indicator to evaluate the apparent structural quality of tunnel linings. When the crack length or width exceeds the allowable range, it can affect the bearing capacity of the reinforced concrete structure and even lead to instability and sudden collapse of the lining, posing a great threat to human life and property. For this reason, image acquisition of tunnels is needed regularly to analyze the disease. At present, the rapid detection means of highway tunnels is still in the exploration stage, and the technical bottlenecks common to only a few products at home and abroad limit the promotion and application of the system. For the existing tunnel lining acquisition images exist in poor picture quality, disease is not prominent and manual labeling disease inefficiency and other problems, innovation based on image processing, deep learning and other methods to develop a small target recognition algorithm for tunnel lining cracks, and build a tunnel crack intelligent identification system to achieve intelligent identification detection of crack disease on highway tunnel scenes. The use of tunnel crack intelligent identification system can significantly reduce the detection time of crack disease and human detection cost investment, at the same time, can also effectively avoid the manual detection of fatigue situation prone to misidentification, omission identification and other problems, play an irreplaceable role in the protection of highway tunnel safe operation, timely detection of highway initial disease, reducion of maintenance costs and other aspects, has significant economic and social benefits.
Research on intelligent recognition method of tunnel lining cracks based on small objective recognition algorithm
Meng, Ying (author) / Wu, Hongtao (author) / Niu, Bingqing (author)
2024-07-15
875237 byte
Conference paper
Electronic Resource
English
Microbial self-repairing method for tunnel lining concrete cracks
| European Patent Office | 2020
Efficient Crack Detection Method for Tunnel Lining Surface Cracks Based on Infrared Images
| Online Contents | 2016