Panoramic image CNN based tunnel disease automatic identification device

Abstract

The invention discloses a panoramic image CNN based tunnel disease automatic identification device. According to the device, firstly, a panoramic image of a tunnel inner wall is quickly acquired with a panoramic vision sensor; then the panoramic image is processed mainly by panorama unrolling, image preprocessing, binarization processing and the like to extract suspected disease region; and finally, the disease is subjected to automatic detection and classification identification by adopting a convolutional neural network. According to the scheme, the structure of the detection device in extracting a tunnel inner wall panoramic image is greatly simplified, and various tunnel disease characteristics can be automatically extracted, detected and identified by the end-to-end convolutional neural network, and an effective technical support is provided to tunnel maintenance and completion acceptance.

Description

technical field [0001] The present invention relates to the application of omni-directional visual sensor, pattern recognition, artificial intelligence, applied mathematics, digital image processing and computer vision technology in the detection of tunnel damage, in particular to a tunnel fault automatic identification device based on panoramic image CNN. Background technique [0002] In order to solve the pressure brought by the population flow and the relative concentration of employment points on traffic and the environment, and to meet the needs of the national environment and situation changes, various tunnels and underground projects (such as urban subways, road tunnels, railway tunnels, underwater tunnels, etc.) Tunnels, municipal pipelines, underground energy caverns, etc.) have become an inevitable trend. [0003] As of 2014, there were 12,404 highway tunnels across the country with a length of 10.7567 million meters. Among them, there are 626 extra-long tunnels, ...

AI Technical Summary

Problems solved by technology

[0013] Aiming at the shortcomings of the current tunnel lining disease detection process, such as the difficulty of quickly and conveniently obtaining the panoramic image of the inner wall of the tunnel and the difficulty of automatically detecting and identifying various diseases, the present invention provides a tunnel disease automatic identification device based on panoramic image CNN, which can be used on the detection device Effectively improve the automation and intelligence level of visual recognition of tunnel diseases, ensure real-time detection and recognition capabilities on the basis of better detection and recognition accuracy, and better solve the contradiction between the complexity and generalization of tunnel inner wall recognition. universality

Images