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。

1.具体样品图像采集
<ol><li>将混凝土运输到工作场所，由泵车浇筑。</li>
	<li>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 图 1 所示。</li>
	<li>将混凝土振动设备的振动部分（插入式混凝土振动杆）插入混凝土中。连接电源，然后通过将其设置为 ON 位置来打开混凝土振动设备。</li>
	<li>当混凝土表面出现一些坍塌（由混凝土内部释放空气的振动引起，导致表面骨料下沉以填充缝隙，导致混凝土坍塌）并出现一些水泥浆时，保持相机镜头平行于混凝土表面并按 下快门键。收集 20 个振动混凝土的图像样本，如 图 2 所示。</li>
	<li>继续操作振动设备。当混凝土表面无明显塌陷时，不出现水泥浆，不产生气泡，停止振动过程，采集20张振动混凝土图像样本，如 图3所示。</li>
</ol>2. 样本图像灰度二值化
<ol><li>利用 MATLAB 软件的 imread（） 函数将 .jpg 文件读取为 1024 像素 x 1024 像素 x 3 个颜色通道的单位格式数据，表示图像的红色、绿色和蓝色通道值。</li>
	<li>接下来，应用 MATLAB 函数 rgb2gray 将图像转换为灰度，用格式 gray value = rgb2gray（jpg file name） 表示。根据公式（1）计算每个像素的灰度值，并将灰度值保存为1024 x 1024的unit8格式数据。 GR（i，j） = 0.2989R（i，j） + 0.587G（i，j） + 0.114B（i，j） （1） 其中，GR（i，j） 是像素点的灰度值，R（i，j） 是像素点的红色通道值，G（i，j） 是像素点的绿色通道值，B（i，j） 是像素点的蓝色通道值。</li>
	<li>将大于像素阈值 θ 的灰度值的二进制值更改为 1，并将小于 θ 像素的灰度值的二进制值设置为 0。</li>
	<li>获得二值灰度结果后，将结果另存为 1024 x 1024 逻辑格式数据。在本例中，θ 表示二值化阈值，对于不同振动状态的混凝土样品图像，其值分别为 50、100、150 和 200，如 图 5、 图 6 和 图 7 所示。</li>
</ol>3. 定向梯度特征值的计算
<ol><li>使用以下公式28 计算图像中每个像素的水平和垂直二进制梯度 Tp = R（x， y + 1） - R（x， y - 1）， Th = R（x+1， y） - R（x-1， y） 其中 Th 是水平二值化梯度，Tp 是垂直二值化梯度，R 是二值化逻辑格式数据，x 是二值化矩阵的行号，y 是二值化矩阵的列号。</li>
	<li>使用以下公式29 计算每个点的二进制梯度方向和大小 <img alt="Equation 1" src="/files/ftp_upload/65731/65371eq01.jpg" style="margin: auto;"> 其中 T 是二进制梯度大小，αT 是二进制梯度方向，Th 是水平二进制梯度，Tp 是垂直二进制梯度。</li>
	<li>确定图像分割块的大小，表示为 n，其中 n 的值为 [ 1,9]。沿 x 方向在 y 方向上设置每个 n 像素的分割线，根据分割线的位置有效地将图像分成 n x n 个正方形块。然后，图像中无法形成完整方形块的任何部分都将被删除。</li>
	<li>将T α二进制梯度方向（T α二进制梯度方向的值为 [ 0°， 360°]）划分为 m 个部分，得到 m 个方向梯度统计角度区间。继续计算每个块的梯度统计角度间隔的梯度统计值。<ol><li>根据块中每个像素的二进制梯度方向，将像素分类为每个方向的适当梯度统计角度区间。</li>
		<li>将每个方向的梯度统计角度间隔内像素在逆时针方向上的二进制梯度求和，得到该间隔的梯度统计值。 图 8、 图 9 和 图 10 分别描绘了块大小 n 等于 8、128 和 512 的梯度统计角度间隔方向梯度统计的结果。</li>
	</ol></li>
</ol>4. 构建定向梯度特征向量
<ol><li>将样本划分为所需的计算区域，其中每个计算区域由四个相邻的模块组成，基于步骤 3.3 中获得的模块结果。例如，考虑 16 x 16 分辨率像素和 4 x 4 的块大小，图像分为 （16 / 4-1） x （ 16 / 4-1 ） = 9 个计算区域。</li>
	<li>计算计算区域内各块的梯度统计量的角度间隔内的方向梯度统计值。随后，得到以方向梯度统计量为分量的特征向量。</li>
	<li>组合来自每个计算区域的方向梯度特征向量，以获得图像的方向梯度特征向量。</li>
</ol>5. 支持向量机培训
<ol><li>从三种振动状态中随机选择 42 个样本创建训练组，剩余 18 个样本作为测试组。</li>
	<li>利用 MATLAB 的 fitcecoc 功能进行 SVM 训练;格式是 SVM = fitcecoc （trainingFeatures， Trainingeigenvalue） 其中SVM为待训练的支持向量机，trainingFeatures为训练组图像定向梯度特征向量，Trainingeigenvalue为训练组振动状态的特征值。非振动混凝土、振动混凝土和振动混凝土样品的振动状态特征值分别为 1、2 和 3。</li>
	<li>使用 Save 函数以 .mat 格式保存经过训练的 SVM 。</li>
</ol>6. SVM识别精度的验证
<ol><li>使用 MATLAB 的预测函数，将测试组样本图像的方向梯度特征向量输入到经过训练的 SVM 中，以获得每个测试样本的振动状态特征的计算值。格式如下： testgroupcalculateseigenvalues = predict （SVM， testFeature） 其中 testgroupcalculatesegenvalues 是振动状态特征的计算值，SVM 是在步骤 5 中训练的支持向量机。testFeature 是测试组样本图像的方向梯度特征向量。</li>
	<li>通过将测试集输入到经过训练的 SVM 中来确定测试集样本识别结果。计算测试集识别结果与实际状态匹配的样本数，然后通过将正确样本数除以测试集样本总数来计算识别准确率。<ol><li>如果测试识别准确率高于 94%，则认为 SVM 识别有效。如果低于 94%，则返回步骤 1.1 并调整二值化阈值、块大小 n 和方向梯度统计区间数 m。</li>
	</ol></li>
</ol>

Directional Gradient Histogram and SVM for Identifying Concrete Vibration States

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

作者没有什么可透露的。

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。...

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。

<table border="1" fo:keep-together.within-page="1" fo:keep-with-next.within-page="always">
	<tbody>
		<tr>
			<td>camera</td>
			<td>SONY</td>
			<td>A6000</td>
			<td>The sensor size is 23.5x15.6mm, the maximum acquisition resolution is 1440 * 1080, and the effective pixel is 24.3 million.</td>
		</tr>
		<tr>
			<td>concrete</td>
			<td>Wuhan Construction Changxin Technology Development Co., Ltd.</td>
			<td>C30 pumping concrete</td>
			<td>According to the standard of &#39; concrete strength test and evaluation standard &#39; ( GB / T 50107-2010 ), the standard value of cubic compressive strength is 30 MPa pumping concrete.</td>
		</tr>
		<tr>
			<td>Matlab</td>
			<td>MathWorks</td>
			<td>Matlab R2017a</td>
			<td>MATLAB&#39;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</td>
		</tr>
		<tr>
			<td>Processor&#160;</td>
			<td>Intel</td>
			<td>12th Gen Intel(R) Core (TM) i7-12700H @ 2.30GHz</td>
			<td>64-bit Win11 processor&#160;</td>
		</tr>
	</tbody>
</table>

image recognition and parameter analysis of concrete vibration state based on support vector machine

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。

Concrete is a fundamental building material extensively used in the construction industry. During pumping, the concrete frequently develops voids that require compaction through vibration. Inadequate vibration may result in a honeycombed concrete surface, while excessive vibration can lead to concrete segregation1,2. The quality of vibration operation significantly impacts the strength3,4,5,6 and durability of the formed concrete structures7,8. Cai et al.9,10 conducted a study that combined experimental research with numerical analysis to investigate the influence mechanism of vibration on aggregate settlement and concrete durability. The findings revealed that vibration time and aggregate particles exert a substantial impact on aggregate settlement, while aggregate density and the plastic viscosity of the cement-based material have minimal effects. Vibration causes aggregate deposition at the bottom of the concrete specimens. Moreover, as the vibration time increases, the chloride ion concentration decreases at the bottom of the concrete specimens while significantly increasing at the top9,10.
Currently, the assessment of concrete vibration state relies predominantly on manual judgment. As the construction industry continues to progress through intelligent reforms, robot operations have emerged as the future direction11,12. Consequently, a crucial challenge in intelligent vibration operations is how to enable robots to identify the vibration state of concrete.
The histogram of the oriented gradient is a technique that utilizes the intensity gradient of pixels or the distribution of edge directions as a descriptor to characterize the representation and shape of objects in images13,14. This approach operates on the local grid cells of the image, providing robust stability in characterizing image changes under various geometric and optical conditions.
Zhou et al.15 proposed a method for directly extracting directional gradient features from Bayer mode images. This approach omits numerous steps in calculating the directional gradient by matching the color filter column with the gradient operator, thereby significantly reducing the computational requirements for directional gradient image recognition. He et al.16 utilized the directional gradient histogram as the underlying feature and employed the mean clustering algorithm to classify rail fasteners and determine whether the fasteners are defective. The recognition results indicated that the histogram of the oriented gradient feature exhibited high sensitivity to fastener defects, meeting the needs of railway maintenance and repair. In another study, Xu et al.17 preprocessed face image features using Gabor wavelet filtering and reduced the dimension of feature vectors through binary coding and the HOG algorithm. The average recognition accuracy of the method is 92.5%.
The support vector machine (SVM)18 is used to map the vector into a high-dimensional space and establishes a separating hyperplane with a suitable direction to maximize the distance between two parallel hyperplanes. This allows for the classification of support vectors19. Scholars have improved and optimized this classification technology, leading to its application in various fields such as image recognition20,21, text classification22, reliability prediction23, and fault diagnosis24.
Li et al.25 developed a two-stage SVM model for seismic failure pattern recognition, focusing on three seismic failure modes. The analysis results indicate that the proposed two-stage SVM method can achieve more than 90% accuracy for the three failure modes. Yang et al.26 integrated an optimization algorithm with the SVM to simulate the relationship between the five ultrasonic parameters and the stress of the loaded concrete. The performance of an unoptimized SVM is unsatisfactory, particularly in the low-stress stage. However, traversing the model optimized by the algorithm yields improved results, albeit with lengthy computation times. In comparison, the particle swarm optimization optimized SVM significantly reduces the calculation time while delivering optimal simulation results. Yan et al.27 employed SVM technology and introduced a precision-insensitive loss function to predict the elastic modulus of high-strength concrete, comparing its prediction accuracy against the traditional regression model and neural network model. The research findings demonstrate that the SVM technology produces a smaller prediction error for elastic modulus compared to other methods.
This paper collects image samples of concrete under various vibration states and describes the concrete&#39;s different states using the directional gradient histogram technique. The directional gradient is employed as a feature vector for training the SVM, and the study focuses on the viability of using the directional gradient histogram-SVM technology to identify the vibration state of concrete. Additionally, the paper analyzes the influence mechanism between three key parameters-binarization threshold, directional gradient statistical block size, and directional gradient statistical interval number-in the feature extraction process of the directional gradient histogram and the recognition accuracy of the SVM.

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines 

基于支撑矢量机的混凝土振动状态图像识别与参数分析

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...

Watch this Scientific Journal Video about Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines at JoVE.com

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。

In this paper, the directional gradient histogram technology is employed to extract the features of concrete image samples captured under different ...

本文描述的协议利用定向梯度直方图技术提取了各种振动单元下混凝土图像样本的特征。它采用支持向量机进行机器学习，从而产生具有最小训练样本要求和低计算机性能要求的成像识别方法。这种方法大大减少了所需的样本数量，并降低了计算机性能要求。使用相当于 2.3 GHz 中央处理器的笔记本电脑，识别过程只需 50 秒即可完成支持的向量机的列车空间微分。使用 128 个项目和 128 个项目以下大小的图像分割。统计角度反转的方向向量数设置为 12。在224分辨率的图像处理过程中，机器学习结果的识别效果最佳。

image-recognition-parameter-analysis-concrete-vibration-state-based

Research

Education

JoVE Core

JoVE Journal

Civil Engineering

Engineering

Unit 1

Image Recognition and Parameter Analysis of Concrete Vibration State Based on Support Vector Machine

Mixing, Placing and Curing Concrete 

SCIENTISTS IN ACTION

535 次观看.  Wuhan University. 本文描述的协议利用定向梯度直方图技术提取了各种振动单元下混凝土图像样本的特征。它采用支持向量机进行机器学习，从而产生具有最小训练样本要求和低计算机性能要求的成像识别方法。这种方法大大减少了所需的样本数量，并降低了计算机性能要求。使用相当于 2.3 GHz 中央处理器的笔记本电脑，识别过程只需 50 秒即可完成支持的向量机的列车空间微分。使用 12...