期刊
MEASUREMENT
卷 208, 期 -, 页码 -出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.measurement.2023.112464
关键词
Vibration displacement; Learning-based Video Motion Magnification; Tracking; Magnification factor; Complex environment; Camera resolution
A new deep learning-based vision measurement method is proposed to accurately measure micro-vibration displacements of objects under different illuminations and backgrounds. The method preprocesses the video, applies deep learning correlation techniques to zoom in on the target object and track its vibration trajectory, and converts pixel displacement to actual displacement. Experimental results demonstrate that the proposed method outperforms traditional methods, especially in complex environments, achieving exceptional accuracy.
A new deep learning-based vision measurement method is proposed to accurately measure the micro-vibration displacements of objects in different illuminations and backgrounds. The measurement method pre-process the video, then the deep learning correlation methods are used to zoom in the target object and track the vibration trajectory, and the pixel displacement is converted to actual displacement by pixel equivalents. By comparing the three sets of experiments, the proposed method has exceptional accuracy. When measuring vibration displace-ment of 0.1 mm, the Root Mean Square Error (RMSE) and Normalized Root Mean Square Error (NRMSE) are 0.0234 mm and 11.8601 %. By comparing with the Rectangle Detection Algorithm and the Template Matching Algorithm, the proposed algorithm outperforms these two traditional methods, especially for the complex en-vironments. It can be concluded that this method, as a new visual measurement method, can be adapted to a variety of complex environments and can accurately measure micro-amplitude vibrations.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据