Monocular Vision-based Displacement Measurement System Robust to Angle and Distance Using Homography
نویسندگان
چکیده
Displacement of a civil structure contains important information about structural behavior that helps confirm safety and serviceability. Displacement measurement by conventional devices such as LVDT is still challenging due to issues in the cost-effectiveness and accessibility to measurement locations. This paper presents a monocular vision-based displacement measurement system (VDMS) that is cost-effective and convenient installation. The proposed system is composed of a low-cost aftermarket camera, a specially-designed marker, and a laptop computer. The motion of the marker attached to the structure is captured by the video camera, that is subsequently converted to the time history of a dynamic displacement response using planar homography. Planar homography is a transformation matrix mapping any two planes in the three dimensional space, and it can map an image plane into the real marker’s plane which may be at an angle with respect to the camera axis. The system was validated by a lab-scale test using a shaking table. Experimental results show proposed system has a good agreement with LDV regardless of camera positions.
منابع مشابه
Visual map - less navigation based on homographies 1
We introduce a method for autonomous robot navigation based on homographies computed between current image and images taken in a previous teaching phase with a monocular vision system. The features used to estimate the homography are vertical lines automatically extracted and matched. From homography, the underlying motion correction between the reference path and the current robot location is ...
متن کاملParticular Forms of Homography Matrices
This paper deals with monocular video sequences without calibration to recover a maximum of information on displacement and projection parameters. In this paper, we propose a new way to deal with the huge number of particular cases of homographic relations and validate this approach with some experiments showing that if several models are correct, the model with less parameters gives the best e...
متن کاملCamera Pose Estimation in Unknown Environments using a Sequence of Wide-Baseline Monocular Images
In this paper, a feature-based technique for the camera pose estimation in a sequence of wide-baseline images has been proposed. Camera pose estimation is an important issue in many computer vision and robotics applications, such as, augmented reality and visual SLAM. The proposed method can track captured images taken by hand-held camera in room-sized workspaces with maximum scene depth of 3-4...
متن کاملView Synthesis from Image and Video for Object Recognition Applications
Title of Dissertation: View Synthesis from Image and Video for Object Recognition Applications Zhanfeng Yue, Doctor of Philosophy, 2007 Dissertation directed by: Professor Rama Chellappa Department of Electrical and Computer Engineering Object recognition is one of the most important and successful applications in computer vision community. The varying appearances of the test object due to diff...
متن کاملVisual map-less navigation based on homographies
We introduce a method for autonomous robot navigation based on homographies computed between current image and images taken in a previous teaching phase with a monocular vision system. The features used to estimate the homography are vertical lines automatically extracted and matched. From homography, the underlying motion correction between the reference path and the current robot location is ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2015