Figure 2 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
The internal cracks of concrete are very important in the safety evaluation of structures, but there is a lack of fine characterization methods at present. Borehole cameras are a piece of in situ borehole detection technology which can measure the structural elements of a borehole wall with high precision. In this paper, borehole camera technology...
Contexts in source publication
Context 1
... optical probe is the most critical component of the system, mainly including a data-processing module, electronic compass, LED light source, glass window, camera, and conical mirror, as shown in Figure 2a. The optical probe has three sizes, with diameters of 31 mm, 51 mm, and 73 mm, respectively, and corresponding lengths of 471 mm, 462 mm, and 587 mm, respectively. ...
Context 2
... optical probe is the most critical component of the system, mainly including a data-processing module, electronic compass, LED light source, glass window, camera, and conical mirror, as shown in Figure 2a. The optical probe has three sizes, with diameters of 31 mm, 51 mm, and 73 mm, respectively, and corresponding lengths of 471 mm, 462 mm, and 587 mm, respectively. ...
Context 3
... control box superimposes the video data, orientation data and depth data in real time to ensure that the depth and orientation of each frame of the image are determined. Figure 2a shows the measurement process. As the optical probe moves in the borehole, the video image, orientation information, and depth information of the borehole wall structure are collected and saved. ...
Context 4
... the conical mirror technology reflects the panoramic strip image, the image must be restored to a form convenient for viewing through a certain algorithm. As shown in Figure 2b, the borehole wall image collected by the borehole camera system is shown. The first picture is the plan expansion of the borehole wall along the due north direction, and the other four are borehole histograms from different perspectives. ...
Context 5
... control box superimposes the video data, orientation data and depth data in real time to ensure that the depth and orientation of each frame of the image are determined. Figure 2a shows the measurement process. As the optical probe moves in the borehole, the video image, orientation information, and depth information of the borehole wall structure are collected and saved. ...
Context 6
... the conical mirror technology reflects the panoramic strip image, the image must be restored to a form convenient for viewing through a certain algorithm. As shown in Figure 2b, the borehole wall image collected by the borehole camera system is shown. The first picture is the plan expansion of the borehole wall along the due north direction, and the other four are borehole histograms from different perspectives. ...
Citations
In recent years, the trend of applying intelligent technologies at all stages of construction has become increasingly popular. Particular attention is paid to computer vision methods for detecting various aspects in monitoring the structural state of materials, products and structures. This paper considers the solution of a scientific problem in the area of construction flaw detection using the computer vision method. The convolutional neural network (CNN) U-Net to segment violations of the microstructure of the hardened cement paste that occurred after the application of the load is shown. The developed algorithm makes it possible to segment cracks and calculate their areas, which is necessary for the subsequent evaluation of the state of concrete by a process engineer. The proposed intelligent models, which are based on the U-Net CNN, allow segmentation of areas containing a defect with an accuracy level required for the researcher of 60%. It has been established that model 1 is able to detect both significant damage and small cracks. At the same time, model 2 demonstrates slightly better indicators of segmentation quality. The relationship between the formulation, the proportion of defects in the form of cracks in the microstructure of hardened cement paste samples and their compressive strength has been established. The use of crack segmentation in the microstructure of a hardened cement paste using a convolutional neural network makes it possible to automate the process of crack detection and calculation of their proportion in the studied samples of cement composites and can be used to assess the state of concrete.
