[1]杨克超,李林.基于计算机视觉和视频插帧的结构振动测试与模态识别[J].福建理工大学学报,2024,22(01):22-29.[doi:10.3969/j.issn.2097-3853.2024.01.004]
　YANG Kechao,LI Lin.Structural vibration testing and mode identification based on computer vision and video frame interpolation[J].Journal of Fujian University of Technology;,2024,22(01):22-29.[doi:10.3969/j.issn.2097-3853.2024.01.004]
点击复制

基于计算机视觉和视频插帧的结构振动测试与模态识别()
分享到：

《福建理工大学学报》[ISSN:2097-3853/CN:35-1351/Z]

卷:
第22卷
期数:
2024年01期
页码:
22-29
栏目:
出版日期:
2024-02-25

文章信息/Info

Title:
Structural vibration testing and mode identification based on computer vision and video frame interpolation
作者:
杨克超; 李林
福建农林大学
Author(s):
YANG Kechao;  LI Lin
College of Transportation and Civil Engineering, Fujian Agriculture and Forestry University
关键词:
结构振动测试; 模态识别; 计算机视觉; 视频插帧; 注意力机制
Keywords:
structural vibration testing;  modal recognition;  computer vision;  video frame interpolation;  attention mechanism
分类号:
TU317；O329
DOI:
10.3969/j.issn.2097-3853.2024.01.004
文献标志码:
A
摘要:
结构振动测试和模态参数识别是基于结构动态特性进行结构健康监测(SHM)的基本方法。为克服传统接触式测试的不便,引入了非接触式计算机视觉方法,其中以智能手机为数据采集装置的方法受到越来越多的关注。然而智能手机相机往往因为性能受限无法满足需求,从而导致测量结果精度下降。为此,提出一种改进的视频插帧算法EQVI?T 与改进的边缘检测算法,通过提高原始视频的帧率和提出的特征点追踪方法共同提升计算精度。为验证这一方法的有效性,将其应用于试验室模型的位移响应监测和模态参数识别,并进行了定量和定性评估。结果表明,所提方法在提高测量精度和准确性方面具有显著优势,展示了其在结构振动测试中的潜在应用价值。
Abstract:
Structural vibration testing and modal parameter identification are the two basic methods for structural health monitoring (SHM) based on the dynamic properties of structures. Non-contact computer vision methods have been introduced to overcome the inconvenience of conventional contact testing, with increasing interest in methods that use smartphones as data acquisition devices. However, smartphone cameras often fail to meet the requirements due to performance limitations, which leads to a decrease in the accuracy of measurement results. To this end, an improved video frame interpolation algorithm, EQVI-T, was proposed along with an improved edge detection algorithm, which jointly improves the accuracy of the computation by increasing the frame rate of the original video and the proposed feature point tracking method. To validate the effectiveness of this method, it was applied to the monitoring of displacement response and identification of modal parameters of a test chamber model, and quantitative and qualitative evaluations were performed. Experimental results show that the proposed method has significant advantages in improving measurement accuracy and precision, demonstrating its potential application in structural vibration testing.

参考文献/References:

［1］ 叶肖伟，董传智. 基于计算机视觉的结构位移监测综述［J］. 中国公路学报，2019，32（11）：21-39.［2］ XU L，GUO J J，JIANG J J. Time–frequency analysis of a suspension bridge based on GPS［J］. Journal of Sound and Vibration，2002，254（1）：105-116.［3］ GARG P，MOREU F，OZDAGLI A，et al. Noncontact dynamic displacement measurement of structures using a moving laser Doppler vibrometer［J］. Journal of Bridge Engineering，2019，24（9）：04019089.［4］ JAVED A，LEE H，KIM B，et al. Vibration measurement of a rotating cylindrical structure using subpixel-based edge detection and edge tracking［J］. Mechanical Systems and Signal Processing，2022，166：108437.［5］ ZHU J S，LU Z Y，ZHANG C. A marker-free method for structural dynamic displacement measurement based on optical flow［J］. Structure and Infrastructure Engineering，2022，18（1）：84-96.［6］ LIU T，LEI Y，MAO Y B. Computer vision-based structural displacement monitoring and modal identification with subpixel localization refinement［J］. Advances in Civil Engineering，2022，2022：5444101. ［7］ CHEN T C，ZHOU Z. An improved vision method for robust monitoring of multi-point dynamic displacements with smartphones in an interference environment［J］. Sensors，2020，20（20）：5929［8］ SONG L M，WU W F，GUO J R，et al. Survey on camera calibration technique［C］∥2013 5th International Conference on Intelligent Human-Machine Systems and Cybernetics. Hangzhou， IEEE，2013：389-392. ［9］ JIANG H Z，SUN D Q，JAMPANI V，et al. Super SloMo：high quality estimation of multiple intermediate frames for video interpolation［C］∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City，IEEE，2018：9000-9008.［10］ LEE H，KIM T，CHUNG T Y，et al. AdaCoF：adaptive collaboration of flows for video frame interpolation［C］∥2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Seattle，IEEE，2020：5316-5325.［11］ NIKLAUS S，MAI L，LIU F. Video frame interpolation via adaptive separable convolution［C］∥2017 IEEE International Conference on Computer Vision （ICCV）. Venice. IEEE，2017：261-270.［12］ LIU Y H，XIE L B，LI S Y，et al. Enhanced quadratic video interpolation［C］∥Computer Vision – ECCV 2020 Workshops：Glasgow，Proceedings，Part IV. ACM，2020：41–56.［13］ WANG X T，CHAN K C K，YU K，et al. EDVR：video restoration with enhanced deformable convolutional networks［C］∥2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops （CVPRW）. Long Beach，IEEE，2019：DOI:10.1109/CVPRW.2019.D0247.［14］ TRUJILLO-PINO A，KRISSIAN K，ALEMN-FLORES M，et al. Accurate subpixel edge location based on partial area effect［J］. Image and Vision Computing，2013，31（1）：72-90. ［15］ HUANG Z W，ZHANG T Y，HENG W，et al. Real-time intermediate flow estimation for video frame interpolation［C］∥AVIDAN S，BROSTOW G，CISS M，et al. European Conference on Computer Vision. Cham：Springer，2022：624-642. ［16］ DONG J，OTA K，DONG M X. Video frame interpolation：a comprehensive survey［J］. ACM Transactions on Multimedia Computing，Communications，and Applications, 2023, 19(2s): 1-31.［17］李俊燕. 基于自由衰减响应信号的工程结构时变模态阻尼识别［D］. 哈尔滨：哈尔滨工业大学，2022.

更新日期/Last Update: 2024-02-25