Slope monitoring method based on machine vision in foggy weather

doi:10.13474/j.cnki.11-2246.2022.0177.

Abstract

Abstract: In order to solve the problem that the presence of fog will reduce the image quality and affect the monitoring effect in the process of slope monitoring by machine vision, so a slope monitoring method combining dark channel prior(DCP) is proposed. Firstly, by calculating the FADE value of the real-time image, which determines whether the collected image needs to be defogged. For images that need to be defogged, DCP algorithm is used for defogging processing to restore the texture details. Then, the scale-invariant feature transform(SIFT) algorithm is used to match the feature points of the image after fog removal, and the random sample consensus(RANSAC) algorithm is used to screen the excellent matching point pairs, and the transformation matrix between the template and the image is obtained. Then, the affine transformation is used to obtain the template coordinates and the slope displacement. The experimental results show that the proposed method performs well in fog images of different concentrations, and overcomes the problem that visual monitoring is difficult to apply in fog environment effectively.

Key words: DCP, machine vision, slope monitoring, displacement extract, SIFT

CLC Number:

P208

SHI Mengjie, TAO Tingye, GAO Fei, LI Jiangyang, CHEN Hao. Slope monitoring method based on machine vision in foggy weather[J]. Bulletin of Surveying and Mapping, 2022, 0(6): 88-92.

References

[1] LI Qing, MIN Gaochen, CHEN Peng, et al. Computer vision-based techniques and path planning strategy in a slope monitoring system using unmanned aerial vehicle[J]. International Journal of Advanced Robotic Systems, 2020, 17(2):1-14.
[2] 岳聪,王利,王智伟,等.基于S-变换的GNSS滑坡变形监测数据信息提取与抑噪[J].大地测量与地球动力学, 2020, 40(4):335-339.
[3] 王军飞,肖慎轲,刘东烈,等.地基合成孔径雷达的边坡形变监测应用研究[J].测绘科学,2021,46(5):58-65.
[4] GLENN N F, STREUTKER D R, CHADWICK D J, et al. Analysis of LiDAR-derived topographic information for characterizing and differentiating landslide morphology and activity[J].Geomorphology,2006,73(1/2):131-148.
[5] ABELLÁN A,OPPIKOFER T,JABOYEDOFF M,et al. Terrestrial laser scanning of rock slope instabilities[J]. Earth Surface Processes and Landforms, 2014, 39(1):80-97.
[6] HE Leping, TAN Jie, HU Qijun, et al. Non-contact measurement of the surface displacement of a slope based on a smart binocular vision system[J]. Sensors, 2018, 18(9):2890.
[7] LI Boyi, PENG Xiulian, WANG Zhangyang, et al. AOD-net:all-in-one dehazing network[C]//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice:IEEE, 2017:4780-4788.
[8] HE Kaiming, SUN Jian, TANG Xiaoou. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12):2341-2353.
[9] CAI Bolun, XU Xiangmin, JIA Kui, et al. DehazeNet:an end-to-end system for single image haze removal[J]. IEEE Transactions on Image Processing, 2016, 25(11):5187-5198
[10] CHOI L K, YOU J, BOVIK A C. Referenceless prediction of perceptual fog density and perceptual image defogging[J]. IEEE Transactions on Image Processing, 2015, 24(11):3888-3901.
[11] 周杰,解琨,付超,等.结合SIFT特征点和泊松融合的无人机遥感影像拼接技术[J].测绘通报, 2021(1):94-98.
[12] 喜文飞,赵子龙,王绍君,等.一种改进的无人机影像拼接粗差剔除算法[J].测绘通报,2021(2):36-39.
[13] 寇大磊,钱敏,权冀川,等.基于多尺度卷积网络的快速图像去雾算法[J].计算机工程与应用, 2020,56(20), 191-198.
[14] TANG Ketan,YANG Jianchao,WANG Jue. Investigating haze-relevant features in a learning framework for image dehazing[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus:IEEE, 2014:2995-3002.
[15] ZHU Qingsong, MAI Jiaming, SHAO Ling. A fast single image haze removal algorithm using color attenuation prior[J]. IEEE Transactions on Image Processing, 2015, 24(11):3522-3533.