Large-span steel structure hoisting deformation monitoring method based on unmanned aerial vehicle and machine vision

Abstract

The invention discloses a large-span steel structure hoisting process deformation monitoring method based on an unmanned aerial vehicle and a machine vision technology, and the method comprises the steps: obtaining a large-span steel structure hoisting process shot by the unmanned aerial vehicle in a segmented manner through a measurement point marking system and an image collection system; and carrying out panoramic splicing and coordinate extraction on the measuring points in the hoisting process of the large-span steel structure. The feature detection model adopts a yov5 deep learning neural network to detect and recognize mark points or feature points in the image to obtain measuring point coordinates, displacement and structural deformation during hoisting of the large-span steel structure, a coordinate conversion module in the accident early warning system converts pixel coordinates into actual coordinates through scale factors, and the actual coordinates are subjected to coordinate detection and displacement detection. And a comparison result is transmitted to the early warning module through an optical fiber network to judge whether to give an alarm or not, so that safety accident early warning in the hoisting process of the large-span steel structure is completed in real time.

Description

technical field [0001] The invention relates to the technical field of unmanned aerial vehicle image processing, in particular to the deformation monitoring technology of the unmanned aerial vehicle during the hoisting process of a large-span steel structure. Background technique [0002] With the rapid upgrading of construction industrialization, large-span steel structures have become a rookie in the construction industry. The rapid increase of large-span steel structure engineering projects, especially the use of large-span steel structures, has made the hoisting of single large-span members of steel structures and the overall hoisting of steel structures more and more widely used in steel structure construction. At the same time, hoisting construction technology is the most widely used steel structure construction technology, and more and more hoisting construction problems are increasingly prominent. Whether it is a single large-span steel structure member or an overal...

AI Technical Summary

Problems solved by technology

[0005] At present, there are still some technical problems in the UAV deformation monitoring of the long-span steel structure hoisting process: First, during the hoisting process of the long-span steel structure, due to the complicated construction process, the measuring points cannot be accessed during construction or need to be monitored. For night operations, the selection of marking points is particularly important

Second, due to the large size of the long-span steel structure, it is necessary to realize panoramic scanning for the marking points on the long-span, which has the problem of the scanning accuracy of the drone

Third, when the UAV aerial photographs the hoisting process of the large-span steel structure, due to the short shooting distance, the sampling frequency of the UAV to the marking points is inconsistent, and it is easy to collide with the hoisting structure, making route planning more difficult

Fourth, deep learning is complex and time-consuming, and it is impossible to predict safety information in real time during the hoisting process, resulting in potential safety hazards in construction

Images