A Vision-Based Displacement Measurement System for Foundation Pit

被引:46
作者
Mi, Chao [1 ,2 ]
Liu, Yi [3 ]
Zhang, Yujie [3 ]
Wang, Jiaqi [3 ]
Feng, Yufei [2 ]
Zhang, Zhiwei [2 ]
机构
[1] Shanghai Maritime Univ, Container Supply Chain Technol Engn Res Ctr, Minist Educ, Shanghai 201306, Peoples R China
[2] Shanghai SMU Vis Smart Technol Co Ltd, Shanghai 201306, Peoples R China
[3] Shanghai Maritime Univ, Logist Engn Coll, Shanghai 201306, Peoples R China
关键词
Displacement measurement; foundation pit; two-stage perspective n point (PNP); vision-based measurement; CONVOLUTIONAL NETWORKS; IMAGE REGISTRATION; POSE ESTIMATION; CAMERA; CLASSIFICATION; ROBUST;
D O I
10.1109/TIM.2023.3311069
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
The early displacement monitoring of excavation pits is currently a primary method to prevent pit collapse accidents. However, conventional pit displacement monitoring mainly relies on regular manual measurement or automated professional instrument measurement, which results in high cost, complex operation and deployment, nonreal-time measurement, and nonintuitive data collection. Consequently, this article proposes a method for the visual measurement of 3-D displacement of pits based on a two-stage perspective $n$ -point (PNP) algorithm. Initially, markers are installed on the reference points with known 3-D spatial coordinates and on each displacement measurement point of the excavation pit. All markers are scanned sequentially by panning the camera and zooming the lens, ensuring at least two adjacent markers enter the frame and are captured in each shot. Second, the improved histogram of oriented gradients (HOG) combined with support vector machine (SVM) rapid algorithm is utilized to perform quick detection and coarse positioning of each marker in the aforementioned photographs. Third, the subpixel algorithm and image morphology are combined. Based on the coarse positioning, the pixel coordinate values of the markers in the images are calculated. Finally, the two-stage PNP algorithm is applied in a cyclical fashion: by using the known 3-D spatial coordinates and its pixel coordinates of the previous marker to solve for the current camera's 3-D spatial coordinates and pose, the 3-D spatial coordinates of the next marker can be derived using the current camera's 3-D spatial coordinates and pose and the pixel coordinates of the next marker. This cycle continues until the 3-D spatial coordinates of all markers are fully resolved, thereby achieving accurate measurement of the 3-D displacement of the pit. Experimental results show that the accuracy of the proposed method is nearly as high as the measurement accuracy of manual total stations, meeting the requirements for daily 3-D displacement measurement of excavation pits. Meanwhile, this method offers the advantages of low cost, simple deployment and operation, and a high degree of automation.
引用
收藏
页数:15
相关论文
共 41 条
[1]   How to localize humanoids with a single camera? [J].
Alcantarilla, Pablo F. ;
Stasse, Olivier ;
Druon, Sebastien ;
Bergasa, Luis M. ;
Dellaert, Frank .
AUTONOMOUS ROBOTS, 2013, 34 (1-2) :47-71
[2]   Linear pose estimation from points or lines [J].
Ansar, A ;
Daniilidis, K .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2003, 25 (05) :578-589
[3]   CNN and HOG based comparison study for complete occlusion handling in human tracking [J].
Aslan, Muhammet Fatih ;
Durdu, Akif ;
Sabanci, Kadir ;
Mutluer, Meryem Afife .
MEASUREMENT, 2020, 158
[4]   Studies on Three-Dimensional (3D) Accuracy Optimization and Repeatability of UAV in Complex Pit-Rim Landforms As Assisted by Oblique Imaging and RTK Positioning [J].
Bi, Rui ;
Gan, Shu ;
Yuan, Xiping ;
Li, Raobo ;
Gao, Sha ;
Luo, Weidong ;
Hu, Lin .
SENSORS, 2021, 21 (23)
[5]   YOLACT Real-time Instance Segmentation [J].
Bolya, Daniel ;
Zhou, Chong ;
Xiao, Fanyi ;
Lee, Yong Jae .
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, :9156-9165
[6]   Globally-Optimal Inlier Set Maximisation for Camera Pose and Correspondence Estimation [J].
Campbell, Dylan ;
Petersson, Lars ;
Kneip, Laurent ;
Li, Hongdong .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2020, 42 (02) :328-342
[7]   An Edge Traffic Flow Detection Scheme Based on Deep Learning in an Intelligent Transportation System [J].
Chen, Chen ;
Liu, Bin ;
Wan, Shaohua ;
Qiao, Peng ;
Pei, Qingqi .
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2021, 22 (03) :1840-1852
[8]   Where are my quadrats? Positional accuracy in fieldwork [J].
Dodd, Mike .
METHODS IN ECOLOGY AND EVOLUTION, 2011, 2 (06) :576-584
[9]   A Vision-Based Sensor for Noncontact Structural Displacement Measurement [J].
Feng, Dongming ;
Feng, Maria Q. ;
Ozer, Ekin ;
Fukuda, Yoshio .
SENSORS, 2015, 15 (07) :16557-16575
[10]   Two-dimensional displacement optical fiber sensor based on macro-bending effect [J].
Ghaffar, Abdul ;
Hou, Yu-Long ;
Liu, Wen-Yi ;
Dharejo, Fayaz Ali ;
Zhang, Hui-Xin ;
Jia, Pinggang ;
Hu Yanyun ;
Liu, Jia ;
Zhang Yunjun ;
Nasir, Zafar .
OPTICS AND LASER TECHNOLOGY, 2019, 120