Summary

基于支撑矢量机的混凝土振动状态图像识别与参数分析

Published: January 05, 2024
doi:

Summary

本文所述的协议利用定向梯度直方图技术提取了各种振动状态下混凝土图像样品的特征。它采用支持向量机进行机器学习,从而产生了一种具有最小训练样本要求和低计算机性能要求的图像识别方法。

Abstract

本文采用定向梯度直方图技术提取了不同振动状态下捕获的混凝土图像样本的特征。利用支持向量机(SVM)学习图像特征与振动状态之间的关系。机器学习结果随后用于评估混凝土振动状态的可行性。同时,分析了方向梯度直方图计算参数对识别精度的影响机理。结果验证了采用定向梯度直方图-SVM技术识别混凝土振动状态的可行性。识别准确率最初随着方向梯度的块大小或统计间隔数量的增加而增加,然后逐渐降低。识别准确率也随着二值化阈值的增加而线性降低。通过使用分辨率为1024 x 1024像素的样本图像并优化特征提取参数,可以达到100%的识别准确率。

Introduction

混凝土是建筑行业广泛使用的基本建筑材料。在泵送过程中,混凝土经常产生空隙,需要通过振动压实。振动不足可能导致混凝土表面呈蜂窝状,而过度振动会导致混凝土离体 1,2。振动操作的质量显着影响成型混凝土结构的强度 3,4,5,6 和耐久性 7,8。Cai等[9,10]将实验研究与数值分析相结合,研究了振动对骨料沉降和混凝土耐久性的影响机制。结果表明,振动时间和骨料颗粒对骨料沉降有很大影响,而骨料密度和水泥基材料的塑性粘度影响最小。振动导致骨料沉积在混凝土试样的底部。此外,随着振动时间的增加,混凝土试样底部的氯离子浓度降低,而顶部的氯离子浓度显着增加9,10

目前,混凝土振动状态的评估主要依赖于人工判断。随着建筑业通过智能化改革不断进步,机器人操作已成为未来的发展方向11,12。因此,智能振动操作的一个关键挑战是如何使机器人能够识别混凝土的振动状态。

定向梯度直方图是一种利用像素的强度梯度或边缘方向的分布作为描述符来表征图像中物体的表示和形状的技术13,14。这种方法在图像的局部网格单元上运行,在表征各种几何和光学条件下的图像变化时提供了强大的稳定性。

周等[15 提出了一种直接从拜耳模式图像中提取方向梯度特征的方法。通过将滤色器列与渐变算子进行匹配,这种方法省略了计算定向梯度的许多步骤,从而大大降低了定向渐变图像识别的计算要求。He et al.16 利用方向梯度直方图作为底层特征,采用平均聚类算法对钢轨紧固件进行分类,确定紧固件是否存在缺陷。识别结果表明,定向梯度特征直方图对紧固件缺陷具有较高的敏感性,满足铁路养护和维修的需要。在另一项研究中,Xu 等人 17 使用 Gabor 小波滤波对人脸图像特征进行了预处理,并通过二进制编码和 HOG 算法降低了特征向量的维度。该方法的平均识别准确率为92.5%。

支持向量机(SVM)18用于将向量映射到高维空间中,并建立具有合适方向的分离超平面,以最大化两个平行超平面之间的距离。这允许对支持向量进行分类 19.学者们对这种分类技术进行了改进和优化,使其在图像识别20,21,文本分类22,可靠性预测23和故障诊断24等各个领域得到应用。

Li等[25 ]开发了用于地震破坏模式识别的两阶段SVM模型,重点关注三种地震破坏模式。分析结果表明,所提出的两阶段支持向量机方法在3种失效模式下均能达到90%以上的准确率。Yang等[26 ]将优化算法与支持向量机相结合,模拟了5个超声参数与加载混凝土应力之间的关系。未优化的 SVM 的性能不尽如人意,尤其是在低应力阶段。然而,遍历由算法优化的模型会产生更好的结果,尽管计算时间很长。相比之下,粒子群优化优化的 SVM 显著缩短了计算时间,同时提供了最佳的仿真结果。Yan等[27 ]采用支持向量机技术,引入精度不敏感损失函数对高强混凝土的弹性模量进行预测,并将其预测精度与传统回归模型和神经网络模型进行比较。研究结果表明,与其他方法相比,SVM技术对弹性模量的预测误差更小。

本文收集了混凝土在各种振动状态下的图像样本,并利用定向梯度直方图技术描述了混凝土的不同状态。将定向梯度作为特征向量进行定向训练,重点关注使用定向梯度直方图-支持向量图技术识别混凝土振动状态的可行性。此外,还分析了方向梯度直方图特征提取过程中的二值化阈值、方向梯度统计块大小和方向梯度统计区间数这三个关键参数之间的影响机制,以及支持向量机的识别精度。

Protocol

1.具体样品图像采集 将混凝土运输到工作场所,由泵车浇筑。 要拍摄图像,请通过向右移动电源键开关并将其转到 ON 位置来打开拍摄设备。将相机的模式旋钮调整到绿色自动模式,确保相机镜头与混凝土表面平行,然后按 下快门键。捕获 20 个非振动混凝土的图像样本,将它们保存为采集分辨率为 1024 x 1024 像素的.jpg格式,如 ?…

Representative Results

该协议旨在分析方向梯度特征的三向量计算参数如何影响支持向量机识别混凝土振动状态的精度。方向梯度特征向量的主要计算参数包括方向梯度统计块大小、方向梯度统计角度区间数和二进制格雷阈值。本节使用三个主要计算参数作为变量来设计测试。测试参数级别详见 表 1。对分辨率为 1024 x 1024 像素的混凝土图像样本共进行了 100 次测试。与 表1 中描述的参数相对应…

Discussion

本文利用支持向量机(SVM)学习各种混凝土振动状态样本的图像特征。基于机器学习结果,提出了一种基于图像识别的具体振动状态识别方法。为了提高识别精度,控制图像分割、图像二值化和定向梯度特征值提取这三个关键步骤的参数至关重要。根据测试结果,采用较小的二值化阈值对具体样品图像进行预处理,并利用128 pixels x 128 pixel的图像分割块大小。统计角度区间的方向梯度数设置为 12。…

Divulgations

The authors have nothing to disclose.

Acknowledgements

我们衷心感谢武汉城建集团2023年度科研专项(NO.7)对这项工作的资助。

Materials

camera SONY A6000 The sensor size is 23.5×15.6mm, the maximum acquisition resolution is 1440 * 1080, and the effective pixel is 24.3 million.
concrete Wuhan Construction Changxin Technology Development Co., Ltd. C30 pumping concrete According to the standard of ' concrete strength test and evaluation standard ' ( GB / T 50107-2010 ), the standard value of cubic compressive strength is 30 MPa pumping concrete.
Matlab MathWorks Matlab R2017a MATLAB's programming interface provides development tools for improving code quality maintainability and maximizing performance.
It provides tools for building applications using custom graphical interfaces.
It provides tools for combining MATLAB-based algorithms with external applications and languages
Processor  Intel 12th Gen Intel(R) Core (TM) i7-12700H @ 2.30GHz 64-bit Win11 processor 

References

  1. Jiang, L., Tian, Z., Wang, K., Sun, X. Estimating the segregation of concrete under vibration based on electrical method. Concrete. 1, 41-44 (2023).
  2. Ren, B., Ye, Z., Wang, D., Wu, B., Tan, Y. Evaluation of segregation degree of hardening concrete using improved Mask R-CNN. Journal of Hydroelectric Engineering. 41 (5), 93-102 (2022).
  3. Hu, J., Qin, M., Wang, H., Liu, K. Study on the influence of vibration frequency on the performance of concrete. Highway. 65 (12), 111-114 (2020).
  4. Bian, C., et al. Experimental study on characterization of evaluation indexes for vibration compaction of fresh concrete. Journal of Hydroelectric Engineering. 39 (2), 67-80 (2020).
  5. Liu, Z., Zhou, M., Bai, J., Mou, S. Influence of vibration time on the strength and homogeneity of rubber concrete. Industrial Construction. 42, 509-512 (2012).
  6. Cheng, Y., Gou, Z., Wang, Y. Testing Investigation on Effects of Mixing, Vibrating and Curing on Strength of High-Performance Concrete. Journal of Northeastern University (Natural Science). 31 (12), 1790-1793 (2010).
  7. Zhao, Y., Chen, S., Liu, Z. Influence mechanism of high-frequency vibration on concrete antifreeze and application in construction of tunnels in cold regions. Industrial Construction. 44 (5), 101-105 (2014).
  8. Quan, L., Tian, B., Li, S., He, Z., He, K. Evolution characteristics of flexural fatigue performance of dense concrete consolidated with high frequency vibration applied in airport pavement. Journal of Traffic and Transportation Engineering. 20 (2), 34-45 (2020).
  9. Cai, Y., et al. Influence of coarse aggregate settlement induced by vibration on long-term chloride transport in concrete: a numerical study. Materials and Structures. 55 (9), 1-18 (2022).
  10. Cai, Y., Liu, Q. F., Yu, L., Meng, Z., Avija, B. An experimental and numerical investigation of coarse aggregate settlement in fresh concrete under vibration. Cement and Concrete Composites. 122 (7), 104153 (2021).
  11. Wang, X., et al. Development and application of concrete vibrating robot system for high arch dam. Journal of Hydraulic Engineering. 53 (6), 631-654 (2022).
  12. Chen, C., Li, X., Qiu, Z., Yao, W., Zhu, H. Research Progress of Construction Robots. Journal of Architecture and Civil Engineering. 39 (4), 58-70 (2022).
  13. Shen, H., Zhang, W., Liu, J., Qiu, K. Development and Prospect of Construction Robots for High Rise Buildings. Construction Technology. 46 (8), 105-108 (2017).
  14. Dalal, N., Triggs, B. Histograms of Oriented Gradients for Human Detection. IEEE Computer Society Conference on Computer Vision & Pattern Recognition. , (2005).
  15. Zhou, W., et al. Gradient-based Feature Extraction From Raw Bayer Pattern Images. IEEE Transactions on Image Processing. (99), 1 (2021).
  16. He, B., et al. Railway Fastener Defects Detection under Various Illumination Conditions using Fuzzy C-Means Part Model. Transportation Research Record. 2675 (4), 271-280 (2021).
  17. Xu, X., Quan, C., Ren, F. Facial expression recognition based on Gabor Wavelet transform and Histogram of Oriented Gradients. IEEE International Conference on Mechatronics & Automation. , (2015).
  18. Cortes, C., Vapnik, V. N. Support Vector Networks. Machine Learning. 20 (3), 273-297 (1995).
  19. Burges, C. A Tutorial on Support Vector Machines for Pattern Recognition. Data Mining and Knowledge Discovery. 2 (2), 121-167 (1998).
  20. Yang, C., et al. Identification of Pleurotus Ostreatus From Different Producing Areas Based on Mid-Infrared Spectroscopy and Machine Learning. Spectroscopy and Spectral Analysis. 43 (2), 577-582 (2023).
  21. Chaabane, S. B., et al. Face recognition based on statistical features and SVM classifier). Multimedia Tools and Applications. 81 (6), 8767-8784 (2022).
  22. Saleh, M. R., et al. Experiments with SVM to classify opinions in different domains. Expert Systems with Applications. 38 (12), 14799-14804 (2011).
  23. Zhang, Y., Liu, Y., Wang, J. Reliability Prediction of Coal Mine Water Disasters Emergency Rescue System Based on Improved SVM. Journal of Zhengzhou University (Engineering Science). 36 (3), 115-119 (2015).
  24. Cao, Y., Song, D., Hu, X., Sun, Y. Fault Diagnosis of Railway Point Machine Based on Improved Time-Domain Multiscale Dispersion Entropy and Support Vector Machine. Acta Electronica Sinica. 51 (1), 117-127 (2023).
  25. Li, Q., Yuze, C., Yu, B., Ning, C. Two-stage support vector machine method for failure mode classification of reinforced concrete columns. Engineering Mechanics. 39 (2), 148-158 (2022).
  26. Yang, Y., Zhang, W., Yu, H., Chai, W., Liu, D. Analysis on the relationships between ultrasonic parameters and the stress state in loaded concrete based on improved support vector machines). Journal of Vibration and Shock. 42 (2), 175-224 (2023).
  27. Yan, K., Shi, C. Prediction of elastic modulus of normal and high strength concrete by support vector machine. Construction & Building Materials. 24 (8), 1479-1485 (2010).
  28. Hussein, I. J., et al. Fully-automatic identification of gynaecological abnormality using a new adaptive frequency filter and histogram of oriented gradients (HOG). Expert Systems. 39 (3), 12789 (2022).
  29. Chandrakala, M., Devi, P. D. Two-stage classifier for face recognition using HOG features. Materials Today: Proceedings. 47, 5771-5775 (2021).
  30. Long, C., Yichi, Z., Zhangkai, L., Dandan, D. Low-Light Image Enhancement Based on RAW Domain Image. Journal of Computer-Aided Design & Computer Graphics. 35 (2), 303-311 (2023).
  31. Wang, X., et al. Development and application of concrete vibrating robot system for high arch dam. Journal of Hydraulic Engineering. 53 (6), 631-654 (2022).
check_url/fr/65731?article_type=t

Play Video

Citer Cet Article
Wang, S., Wang, A., Fu, X., Wu, K., Lu, T. Image Recognition and Parameter Analysis of Concrete Vibration State Based on Support Vector Machine. J. Vis. Exp. (203), e65731, doi:10.3791/65731 (2024).

View Video