Intelligent image recognition of particle size and gradation of earth-rock
-
摘要: 土石料的级配直接影响着土石坝的质量与防渗，为解决传统人工筛分和目测超粒径剔除的低效率与随机性。采用基于MaskRCNN算法的图像识别技术，从标准球体的图像识别入手，研究了不同组别粒径下识别球体数量与真实数量间的关系，提出了将颗粒平面识别向空间体积扩展的椭球计算方法，建立了基于指数函数的图像识别与级配之间的转换方法。采用该方法应用于碎石料和砂石料的粒径与级配识别中，相关系数均提升10%以上，级配曲线所反映的Cu，Cc准确度最高提升35.26%。该研究为土石料级配的图像识别提供了新方法。Abstract: The gradation of soil and stone materials directly affects the quality and anti-seepage of earth-rock dams. In order to solve the low efficiency and randomness of the traditional manual screening and the visual removal of oversized particles, the image recognition technology based on the MaskRCNN algorithm is used to start with the image recognition of standard spheres, and the relationship between the number of recognized spheres and the real number under different groups of particle sizes is studied. The ellipsoid calculation method that extends particle plane recognition to space volume is proposed, and the transformation method between the image recognition and the gradation based on the exponential function is established. By applying this method to the identification of particle size and the gradation of crushed stone and gravel, the correlation coefficient increases by more than 10%, and the accuracy of Cu and Cc reflected by the gradation curve is up to 35.26%. This stud may provide a new method for the image recognition of soil and stone gradation.
-
Keywords:
- earth-rock /
- gradation /
- image recognition /
- particle profile /
- spatial conversion
-
-
![]()
图 2 土石颗粒识别近似转换
Figure 2. Approximate transformation for identification of soil-rock particle
![]()
图 5 试验识别与设计级配在各粒径下倍数关系
Figure 5. Relationship between test identification and design gradation under each particle size
![]()
图 6 空间修正后识别试验级配曲线对比
Figure 6. Comparison of gradation curves of identification tests after spatial correction
-
[1] 杨玉生, 赵剑明, 王龙, 等. 级配特征对筑坝砂砾料填筑标准的影响[J]. 水利学报, 2019, 50(11): 1374-1383. doi: 10.13243/j.cnki.slxb.20190547 YANG Yusheng, ZHAO Jianming, WANG Long, et al. Influence of gradation characteristics on filling standard of sand gravel material for dam construction[J]. Journal of Hydraulic Engineering, 2019, 50(11): 1374-1383. (in Chinese) doi: 10.13243/j.cnki.slxb.20190547
[2] 汤洪洁, 杨正权. 高土石坝筑坝材料特性的认识与思考[J]. 水利规划与设计, 2019(1): 125-129. doi: 10.3969/j.issn.1672-2469.2019.01.035 TANG Hongjie, YANG Zhengquan. Understanding and thinking on the characteristics of dam materials for high earth-rock dams[J]. Water Resources Planning and Design, 2019(1): 125-129. (in Chinese) doi: 10.3969/j.issn.1672-2469.2019.01.035
[3] 朱晟, 钟春欣, 郑希镭, 等. 堆石体的填筑标准与级配优化研究[J]. 岩土工程学报, 2018, 40(1): 108-115. doi: 10.11779/CJGE201801010 ZHU Sheng, ZHONG Chunxin, ZHENG Xilei, et al. Filling standards and gradation optimization of rockfill materials[J]. Chinese Journal of Geotechnical Engineering, 2018, 40(1): 108-115. (in Chinese) doi: 10.11779/CJGE201801010
[4] ZHANG S L, WU G J, YANG X G, et al. Digital image-based identification method for the determination of the particle size distribution of dam granularmateria[J]. KSCE Journal of Civil Engineering, 2018, 22(8): 2820-2833. doi: 10.1007/s12205-017-0304-8
[5] 张国英, 邱波, 刘冠洲, 等. 基于图像的原矿碎石粒度检测与分析系统[J]. 冶金自动化, 2012, 36(3): 47-50. https://www.cnki.com.cn/Article/CJFDTOTAL-YJZH201203018.htm ZHANG Guoying, QIU Bo, LIU Guanzhou, et al. Image-based volume modeling and particle size analysis system of crushed ore[J]. Metallurgical Industry Automation, 2012, 36(3): 47-50 (in Chinese https://www.cnki.com.cn/Article/CJFDTOTAL-YJZH201203018.htm
[6] HAN D, ZHU J H, LI L L. et al. Verification andapplication of two-dimensional slice identificationmethod in three-dimensional mesostructure under different aggregate gradations and packing algorithms[J]. Construction and Building Materials, 2016, 102(1): 843-851.
[7] 雷雨萌, 陈祖煜, 于沭, 等. 基于深度阈值卷积模型的土石料级配智能检测方法研究[J]. 水利学报, 2021, 52(3): 369-380. doi: 10.13243/j.cnki.slxb.20200499 LEI Yumeng, CHEN Zuyu, YU Shu, et al. Intelligent detection of gradation for earth-rockfill materials base on Deep Otsu Convolutional Neural Network[J]. Journal of Hydraulic Engineering, 2021, 52(3): 369-380. (in Chinese) doi: 10.13243/j.cnki.slxb.20200499
[8] LEE J R J, SMITH M L, SMITH L N. New approach to the three-dimensional quantification of angularity using image analysis of the size and form of coarse aggregates[J]. Engineering Geology, 2007, 91(2): 254-264.
[9] SEZGIN M, SANKUR B. Survey over image thresholding techniques and quantitative performance evaluation[J]. Journal of Electronic Imaging, 2004, 13(1): 146-168. doi: 10.1117/1.1631315
[10] 黄鹏, 郑淇, 梁超. 图像分割方法综述[J]. 武汉大学学报(理学版), 2020, 66(6): 519-531. doi: 10.14188/j.1671-8836.2019.0002 HUANG Peng, ZHENG Qi, LIANG Chao. Overview of image segmentation methods[J]. Journal of Wuhan University (Natural Science Edition), 2020, 66(6): 519-531. (in Chinese) doi: 10.14188/j.1671-8836.2019.0002
-
期刊类型引用(0)
其他类型引用(1)
下载:
计量
- 文章访问数: 249
- HTML全文浏览量: 51
- PDF下载量: 86
- 被引次数: 1
