ABSTRACT
Aiming at the low efficiency of the traditional detection methods of buried depth and inclination rate of concrete poles, a method of measuring concrete poles based on binocular vision was proposed. Firstly, an improved DeeplabV3+ semantic segmentation algorithm is proposed. Based on the original model structure, the backbone feature extraction network is modified, the feature fusion method is optimized, and the improved CBAM attention mechanism is added to reduce the model complexity and improved the accuracy of concrete pole area segmentation. Secondly, the sub-pixel edge extraction algorithm based on local area effect is used to determine the edge of the concrete pole in the image segmentation area, and the least squares method is used to fit the edge to determine the precise feature points. Finally, the coordinate transformation of binocular vision is used to calculate the depth and inclination of the concrete pole. Experiments show that the method has a buried depth measurement error of less than 10 cm, an error rate of less than 5%, and an inclination measurement error of less than 0.3°, which provides an automated concrete pole buried depth and inclination rate measurement solution
- Oraegbune O M, Ataguba O C, Haruna C A. 2017. FAILURE, CAUSES AND IMPACTS OF REINFORCED ELECTRIC CONCRETE POLES IN SOME AREAS OF ADAMAWA STATE, NIGERIA. Nigeria Journal of Engineering Science and Technology Research, 3(2): 33-56.Google Scholar
- Xu H B, Sun Q, Qi J J and Wang Y. 2021. Research on Anti-overturning Performance of Concrete Pole Based on ABAQUS. Science Technology and Industry ,21(07):301-305.Google Scholar
- Zhang H B. 2009. The Application of Portable Laser Ranger in Distance Measurement of Overhead Power Lines. Sci-Tech Information Development & Economy, 19(35):189-190.Google Scholar
- Lu Z M, Gong H, Jin Q H, Hu Q W and Li J Y. 2022. Tilt Rate Measurement of Power Tower Based on UAV LiDAR Point Cloud. Journal of Applied Sciences, 40(03):389-399.Google Scholar
- Chen G H, Ge M Y, Huang B Y, Liang H X and Li X K. 2022. Power tower tilt detection method based on binocular vision. Journal of Beijing Jiaotong University, 46(02):128-137.Google Scholar
- Chen L C, Zhu Y, PAPANDREOU G, Schroff F and Adam H. 2018. Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. The European conference on computer vision. Munich, 801-818.Google Scholar
- Sandler M, Howard A, Zhu M, 2018. MobileNetV2: Inverted residuals and linear bottlenecks. The IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, 4510-4520.Google ScholarCross Ref
- Woo S, Park J, Lee J Y, 2018. Cbam: convolutional block attention module. The European Conference on Computer Vision. Munich, 3-19.Google ScholarDigital Library
- Wang Q, Wu B, Zhu P, 2020. ECA-Net: efficient channel attention for deep convolutional neural networks. The IEEE Conference on Computer Vision and Pattern Recognition. Seattle, 13-19.Google ScholarCross Ref
- Javad A, Lee H, Kim B and Han Y. 2021, Vibration measurement of a rotating cylindrical structure using subpixel-based edge detection and edge tracking. Mechanical Systems and Signal Processing, 166:108437.Google ScholarCross Ref
Recommendations
Research on Key Technique of Weed Locating Based on Binocular Vision System
ISCSCT '08: Proceedings of the 2008 International Symposium on Computer Science and Computational Technology - Volume 02There are two aspects for locating precision of weed recognition system based on binocular vision. One is extraction of the feature points, and the other is distortion of camera lens used for image collecting. Some improvement has been made for these ...
Method of Binocular Rotation Angle Measurement Based on Machine Vision
IMCCC '14: Proceedings of the 2014 Fourth International Conference on Instrumentation and Measurement, Computer, Communication and ControlSince the current angle measurement had the disadvantage of high energy and cost and it is hard to integrate, a new rotation angle measurement based on machine vision was proposed. A binocular rotation angle measurement algorithm was established based ...
A New Method of Depth Measurement with Binocular Vision Based on SURF
IWCSE '09: Proceedings of the 2009 Second International Workshop on Computer Science and Engineering - Volume 01Binocular measurement system has a wide range of applications and becomes a hot research direction in recent years. Traditional feature extraction and matching methods limit its accuracy and robustness. In this paper, we propose a new method of ...
Comments