一种利用骨架提取和SVM分类的颗粒表征方法

耿超, 包静, 邹鹏, 王卫彬

中国公路学报 ›› 2018, Vol. 31 ›› Issue (11) : 58-65.

PDF全文下载(2310 KB)
PDF全文下载(2310 KB)
中国公路学报 ›› 2018, Vol. 31 ›› Issue (11) : 58-65.
道路工程

一种利用骨架提取和SVM分类的颗粒表征方法

  • 耿超1,2, 包静1, 邹鹏1, 王卫彬2
作者信息 +

Method for Particle Characterization by Using Skeleton Extraction and SVM Classification

  • GENG Chao1,2, BAO Jing1, ZOU Peng1, WANG Wei-bin2
Author information +
文章历史 +

摘要

集料级配是影响沥青路面抗滑和减噪性能的最主要因素，基于机器视觉技术，提出一种集料粒径高精度无损检测方法，结合骨架提取和支持向量机（SVM）算法来实现集料颗粒粒度分布的精确估计，为保证集料级配质量提供了有效手段。集料颗粒图像由数字相机获取，图像标定基于NI视觉助手Vision Assistant软件完成。颗粒骨架图像采用Skeleton-M骨架提取算法提取，针对所出现的骨架断裂情况，使用形态学膨胀和细化算法完成骨架修复；然后基于颗粒骨架图像提出颗粒粒径表征算法，基于骨架端点个数提出颗粒棱角表征方法；最后，通过提取颗粒图像特征参数，使用SVM算法对颗粒粒径分布进行精确估计。在颗粒棱角性表征方面，将所提出的颗粒骨架棱角性表征法与AIMS系统的梯度棱角法、未压实空隙率集料颗粒棱角法进行了比较。结果表明：与目前常见的粒径表征方法相比，所提出的方法可以较好地实现颗粒粒径表征和颗粒棱角性表征，所采用的基于多特征的SVM颗粒分档算法可以有效实现颗粒粒径分档，筛分档间的分档精度最高可达95%以上。

Abstract

Measuring the particle size with high accuracy and efficiency is important for ensuring the quality of a pavement construction and directly affects the long-term performance of the pavement. This paper proposed a new approach for evaluating the distribution of the particle size by combining the skeleton extraction and support vector machine (SVM) algorithms. The particle images were captured using a design image acquisition system. The skeleton images were extracted under the NI environment following the image segmentation process. Next, the skeleton repairing algorithm was designed to repair the fractured skeleton images. Finally, the distribution of particle size was estimated by employing the SVM method. The aggregate angularity was evaluated based on the final number of the skeleton images. The correlation analysis and comparison were conducted by the AIMS and uncompacted void fraction aggregate particle angular method. When compared with the particle size characterization method, the skeleton extraction method not only identifies the characteristics of the aggregate particle size but also evaluates the aggregate angularity. Because of limited characterization precision of the particle size, the nonlinear SVM with kernel rbf can distinguish the particle sieve size effectively, and the characterization precision can be estimated up to 95% accuracy.

关键词

道路工程 / 集料颗粒 / 骨架提取 / 粒径分布 / SVM

Key words

road engineering / aggregate particle / skeleton extracting / size distribution / SVM

引用本文

EndNote

Ris (Procite)

Bibtex

导出引用
耿超, 包静, 邹鹏, 王卫彬. 一种利用骨架提取和SVM分类的颗粒表征方法[J]. 中国公路学报, 2018, 31(11): 58-65
GENG Chao, BAO Jing, ZOU Peng, WANG Wei-bin. Method for Particle Characterization by Using Skeleton Extraction and SVM Classification[J]. China Journal of Highway and Transport, 2018, 31(11): 58-65
中图分类号： U414   

参考文献

[1] 沙庆林.提高沥青路面使用性能和耐久性的最关键因素[J].中外公路,2005,25(1):1-5.SHA Qing-lin. The Most Critical Factor to Improve the Performance and Durability of Asphalt Pavement[J]. Journal of China & Foreign Highway, 2005, 25(1):1-5.
[2] 崔通.基于分形理论的沥青混合料级配组成分析研究[J].公路交通技术,2017,33(5):23-28.CUI Tong. Analysis of Gradation Composition of Asphalt Mixture Based on Fractal Theory[J]. Technology of Highway and Transport, 2017, 33(5):23-28.
[3] 朱洪洲,葛琦,何兆益.级配参数对沥青稳定碎石疲劳性能的影响分析[J].重庆交通大学学报:自然科学版,2018.doi:10.3969/j.issn.1674-0696.ZHU Hong-zhou, GE Qi, HE Zhao-yi.Analysis on Fatigue Performance of the Different Grading Parameters of Asphalt Stabilized Macadam[J].Journal of Chongqing Jiaotong University:Natural Science Edition, 2018. doi:10.3969/j.issn.1674-0696.
[4] 叶奋,林增龙, 宋卿卿. 基于数字图像处理的沥青混合料粗集料筛分方法[J]. 华东交通大学学报, 2015, 32(5):10-15.YE Fen, LIN Zeng-long, SONG Qing-qing. Coarse Aggregate Sieving Method of Asphalt Mixture Based on Digital Image Processing[J]. Journal of East China Jiaotong University, 2015, 32(5):10-15.
[5] 方明伟.基于集料特性及级配的沥青路面抗滑力模型研究[J].中外公路,2015,35(5):68-75.FANG Ming-wei. Development of a Model for Asphalt Pavement Skid Resistance Based on Aggregate Characteristics and Gradation[J]. Journal of China & Foreign Highway, 2015, 35(5):68-75.
[6] 邹桂莲,张肖宁,徐剑.集料特性对沥青混合料配合比设计的影响[J].公路与汽运,2010(5):70-74.ZOU Gui-lian, ZHANG Xiao-ning, XU Jian. Effect of Aggregate Characteristics on Mix Design of Asphalt Mixture[J].Highway & Automotive Applications, 2010(5):70-74.
[7] 汪海年, 郝培文, 庞立果, 等. 基于数字图像处理技术的粗集料级配特征[J]. 华南理工大学学报:自然科学版, 2007, 35(11):54-58.WANG Hai-nian, HAO Pei-wen, PANG Li-guo, et al.Investigation into Grading Characteristic of Coarse Aggregate via Digital Image Processing Technique[J]. Journal of South China University of Technology:Natural Science Edition, 2007, 35(11):54-58.
[8] 杜小婷,汪海年.基于图像分析的粗集料三维形态指标研究[J].公路,2013(8):250-254.DU Xiao-ting,WANG Hai-nian. A Study on Three-dimensional Shape Indexs of Coarse Aggregate Based on Image Analysis[J].Highway, 2013(8):250-254.
[9] 汪海年,郝培文,肖庆一,等.粗集料棱角性的图像评价方法[J].东南大学学报:自然科学版,2008,38(4):637-641.WANG Hai-nian,HAO Pei-wen,XIAO Qing-yi, et al. Digital Image Evaluation Method for Angularity of Coarse Aggregates[J]. Journal of Southeast University:Natural Science Edition, 2008, 38(4):637-641.
[10] 黄文柯,张肖宁.利用形态学多尺度算法分割粗集料粘连图像[J].哈尔滨工业大学学报,2016,48(3):125-130.HUANG Wen-ke,ZHANG Xiao-ning.Segmentation of Coarse Aggregate Adhesion Images Using Morphological Multiscale Algorithm[J].Journal of Harbin Institute of Technology, 2016, 48(3):125-130.
[11] 江杰,肖鹏,丁燕,等.沥青混合料矿料特征图像表征参数选取[J].扬州大学学报:自然科学版,2016,19(1):68-73.JIANG Jie, XIAO Peng, DING Yan, et al.Characterization Parameters Selection of Asphalt Mixture Aggregate Based on Digital Image[J].Journal of Yangzhou University:Natural Science Edition, 2016, 19(1):68-73.
[12] 沙爱民,王超凡,孙朝云.一种基于图像的沥青混合料矿料级配检测方法[J].长安大学学报:自然科学版,2010,30(5):1-5.SHA Ai-min, WANG Chao-fan, SUN Chao-yun.An Image-based Mineral Gradation Measurement Method of Asphalt Mixture[J]. Journal of Chang'an University:Natural Science Edition, 2010, 30(5):1-5.
[13] 段跃华,张肖宁.基于CT断层扫描图像的混凝土粗集料三维虚拟筛分[J].吉林大学学报:工学版,2012,42(4):918-923.DUAN Yue-hua,ZHANG Xiao-ning.3-dimensional Virtual Sieve Analysis of Coarse Aggregate of Concrete Based on CT Scan Image[J].Journal of Jilin University:Engineering and Technology Edition, 2012, 42(4):918-923.
[14] 孙朝云,沙爱民,姚秋玲,等.沥青混合料自动检测系统研究[J].仪器仪表学报, 2006,27,(4):353-357,366.SUN Chao-yun, SHA Ai-min, YAO Qiu-ling, et al. Research on the Automatic Measurement System of the Asphalt Mixture[J]. Chinese Journal of Scientific Instrument, 2006, 27(4):353-357, 366.
[15] 李伟,沙爱民,孙朝云,等.基于光电成像的矿质混合料级配在线检测技术[J].中国公路学报,2013,26(1):38-43.LI Wei,SHA Ai-min,SUN Chao-yun,et al.Mineral Mixture Gradation Online Detection Technology Based on Optoelectronics Imaging[J]. China Journal of Highway and Transport, 2013, 26(1):38-43.
[16] CHEN K, ZANIEWSKI J, ZHAO P, et al. 2D Image Based Sieving for Particle Aggregate Gradation[J]. Journal of Electronics, 2008, 25(2):277-282.
[17] 刘汉烨, 李伟, 侯云飞, 等.基于三维数据的集料级配组成分析方法[J]. 北京工业大学学报, 2017, 43(10):1521-1528.LIU Han-ye, LI Wei, HOU Yun-fei, et al. Aggregate Grading Composition Analysis Method Based on 3D Data[J]. Journal of Beijing University of Technology, 2017, 43(10):1521-1528.
[18] GIRDNER K K, KEMENY J M, SRIKANT A, et al. The Split System for Analyzing the Size Distribution of Fragmented Rock[J]. Measurement of Blast Fragmentation, 1996(1):101-108.
[19] MORA C F, KWAN A K H, CHAN H C. Particle Size Distribution Analysis of Coarse Aggregate Using Digital Image Processing[J]. Cement and Concrete Research, 1998, 28(6):921-932.
[20] WANG W. Image Analysis of Particles By Modified Ferret Method-best-fit Rectangle[J]. Powder Technology, 2006, 165(1):1-10.
[21] PIRARD E, VERGARA N, CHAPEAU V. Direct Estimation of Sieve Size Distributions from 2-D Image Analysis of Sand Particles[J]. Proceedings PARTEC, 2004, 2004:1-4.
[22] HAMZELOO E, MASSINAEI M, MEHRSHAD N. Estimation of Particle Size Distribution on an Industrial Conveyor Belt Using Image Analysis and Neural Networks[J]. Powder Technology, 2014, 261:185-190.
[23] ANDERSSON T, THURLEY M J, CARLSON J E. A Machine Vision System for Estimation of Size Distributions by Weight of Limestone Particles[J]. Minerals Engineering, 2012, 25(1):38-46.
[24] BAGHERI G H, BONADONNA C, MANZELLA I, et al. On the Characterization of Size and Shape of Irregular Particles[J]. Powder Technology, 2015, 270:141-153.
[25] SYVITSKI J P M. Principles, Methods and Application of Particle Size Analysis[M]. Cambridge:Cambridge University Press, 2007.

基金

国家自然科学基金项目（51408045）；中央高校基本科研业务费专项资金项目（310824171005）
PDF全文下载(2310 KB)

Accesses

Citation

Detail
段落导航
相关文章
版权所有 © 《中国公路学报》编辑部
地址：陕西省西安市南二环路中段长安大学内　
邮编：710064　
电话：029-82334387　
E-mail：zgglxb@163.com
技术支持：北京玛格泰克科技发展有限公司

/

〈 〉