Search

The health monitoring technology of transmission towers based on vibration data had become a research hotspot. At present, vibration data mainly relied on sensors installed on the tower, which was time-consuming and laborious. Nevertheless, the ROI computer vision method could achieve long-distance, multi-point, and non-contact monitoring, which offers a new possibility for the structure-safety identification of power transmission towers. However, transmission towers are generally located in the field environment, and the background is complicated, resulting in the ROI key point method for vibration data acquisition encountering various types of noise. Thus, the key point in practice was clearing the noise and reducing the impact of noise on identification accuracy. The subpixel corner method was used to detect a minor error with the research object of pixel sets. The dilation + erosion method could reduce image noise. Under white noise with a variance of 0.05, the dilation + erosion could reduce average error (Emae) and mean square error (Emse) by 27% and 23% and increase percentages of data with absolute error less than 5 mm and 10 mm in the total number of data (σ5 and σ10) by 8% and 4.3%, respectively, which was compared to median filter + sharpen. The histogram equalization method was used to balance background lighting conditions and reduce identification errors from non-uniform illumination. Emae and Emse were reduced by 92% and 99%, and σ5 and σ10 were increased by 5 and 3 times, respectively, and the identification time was cut by 62% with the histogram equalization method. Under white noise with a variance of 0.15 or lower, the three methods combined increased the numerical stability of Emae, Emse, σ5, and σ10, which indicated that the combination of the three methods could improve the anti-noise performance, robustness, and identification accuracy of the ROI computer vision method for transmission tower displacement identification. [ABSTRACT FROM AUTHOR]

The health monitoring technology of transmission towers based on vibration data had become a research hotspot. At present, vibration data mainly relied on sensors installed on the tower, which was time-consuming and laborious. Nevertheless, the ROI computer vision method could achieve long-distance, multi-point, and non-contact monitoring, which offers a new possibility for the structure-safety identification of power transmission towers. However, transmission towers are generally located in the field environment, and the background is complicated, resulting in the ROI key point method for vibration data acquisition encountering various types of noise. Thus, the key point in practice was clearing the noise and reducing the impact of noise on identification accuracy. The subpixel corner method was used to detect a minor error with the research object of pixel sets. The dilation + erosion method could reduce image noise. Under white noise with a variance of 0.05, the dilation + erosion could reduce average error (Emae) and mean square error (Emse) by 27% and 23% and increase percentages of data with absolute error less than 5 mm and 10 mm in the total number of data (σ5 and σ10) by 8% and 4.3%, respectively, which was compared to median filter + sharpen. The histogram equalization method was used to balance background lighting conditions and reduce identification errors from non-uniform illumination. Emae and Emse were reduced by 92% and 99%, and σ5 and σ10 were increased by 5 and 3 times, respectively, and the identification time was cut by 62% with the histogram equalization method. Under white noise with a variance of 0.15 or lower, the three methods combined increased the numerical stability of Emae, Emse, σ5, and σ10, which indicated that the combination of the three methods could improve the anti-noise performance, robustness, and identification accuracy of the ROI computer vision method for transmission tower displacement identification.

This paper proposed a three-dimensional (3D) pose measurement method for a non-cooperative rectangular target based on a time-of-llight (TOF) camera to solve the problem of low precision caused by large errors in extracting pixel level feature points and unstable distance measurements. Firstly, it detected the improved FAST feature points in the grayscale image. Secondly, it computed the 3D coordinates of l he extracted feature points in the camera coordinate system and the object coordinate system. Finally, it extracted the subpixel level feature points of the rectangular target and combined 30 frames dis­tance information to calculate the attitude angle. Experimental results show that, for a non-cooperative rectangular target with a length of 50 mm over the range of 1 m, the absolute errors of the Z-axis, A-axis and F-axis are 2. 65 mm, 1.28 mm and 0. 60 mm respectively. The absolute error of the attitude angle y is reduced to 0. 52°. Compared with conventional pose measu­rement based on point cloud registration, the absolute error of the attitude angle y is reduced by 48.0%. These improvements in the accuracy and stability of the 3D pose measurement of non-cooperative targets using a TOF camera are relevant to a wide range of applications. [ABSTRACT FROM AUTHOR]