陈然;杨仕教;朱忠华;郑建礼;张紫晗;胡光球;
CHEN Ran;YANG Shi-jiao;ZHU Zhong-hua;ZHENG Jian-li;ZHANG Zi-han;HU Guang-qiu;School of Resources Environment and Safety Engineering, University of South China;Guangdong Xiyuan Blasting Technology Co., Ltd;

• 1:南华大学资源环境与安全工程学院
• 2:广东锡源爆破科技股份有限公司

摘要(Abstract)：

为改进爆破块度图像分割中容易存在的过分割、噪声、"黑洞"现象等问题,提出了双门限阈值分割技术,开展了多种类型的爆破岩块图像分割实验和小型爆堆的手工测量实验,实验结果表明,双门限阈值法与灰度阈值法、适应性阈值法、Otsu大津法等常用的分割方法相比,对爆破岩堆的图像分割效果更优,能够解决岩石表面噪声问题;与手工测量相比,双门限阈值技术对爆堆图像分割的平均相对误差为12.0%,误差主要因岩块的边缘棱角效应所致,这种效应使得分割结果偏大。双门限阈值分割技术能较好地应用于爆破块度图像识别。
In order to improve the problems of over segmentation, noise and "black hole" that are easy existing in image segmentation of blasting rock mass, the double threshold segmentation technology is proposed, and many kinds of experiments on image segmentation of blasting rock mass and manual measurement of small blasting piles are carried out. The experimental results show that the double threshold method compare with the commonly used segmentation methods such as gray threshold method, adaptive threshold method, Otsu method, etc is more effective in image segmentation of blasting rock pile, and it can solve the problem of rock surface noise; compared with the manual measurement, the average relative error of the double threshold technology in image segmentation of blasting rock pile is 12.0%.The error is mainly caused by the edge angular effect of rock block, which makes the segmentation result larger. The double threshold segmentation technology can be applied to the image recognition of blasting fragmentation.

关键词(KeyWords)： 爆破块度;图像分割;双门限阈值;误差;爆堆
blasting block;image segmentation;double threshold;error;rock pile

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金资助项目(50974076);; 广东锡源爆破科技股份有限公司资助项目

作者(Authors): 陈然;杨仕教;朱忠华;郑建礼;张紫晗;胡光球;
CHEN Ran;YANG Shi-jiao;ZHU Zhong-hua;ZHENG Jian-li;ZHANG Zi-han;HU Guang-qiu;School of Resources Environment and Safety Engineering, University of South China;Guangdong Xiyuan Blasting Technology Co., Ltd;

参考文献(References)：

• [1] 武仁杰,李海波,于崇,等.基于统计分级判别的爆破块度预测模型[J].岩石力学与工程学报,2018,37(1):141-147.WU R J,LI H B,YU C,et al.Prediction model of blasting fragmentation based on statistical classification[J].Journal of Rock Mechanics and Engineering,2018,37 (1):141-147.
• [2] 孙臣良,题正义,高波.基于图像处理的爆堆块度分布自动测试系统[J].辽宁工程技术大学学报,2002(4):449-451.SUN C L,TI Z Y,GAO B.Automatic test system of explosive fragmentation distribution based on image processing[J].Journal of Liaoning University of Engineering and Technology,2002 (4):449-451.
• [3] 璩世杰,刘际飞,许文耀.爆堆矿岩块度分布的计算机图像自动处理系统[J].金属矿山,2013(6):1-4,37.QU S J,LIU J F,XU W Y.Automatic computer image processing system for the distribution of rock block size in blaster heap[J].Metal Mine,2013 (6):1-4 ,37.
• [4] 叶平坤.基于图像处理的矿岩粒度检测的研究[D].郑州:郑州大学,2018.YE P K.Research on particle size detection of ore and rock based on image processing[D].Zhengzhou:Zhengzhou University,2018.
• [5] 荆永滨,王公忠,毕林,等.基于块体形状分类的爆堆块度三维几何参数估算[J].爆破,2018,35(1):35-41.JING Y B,WANG G Z,BI L,et al.Estimation of three-dimensional geometric parameters of blasting block size based on block shape classification[J].Blasting,2018,35 (1):35-41.
• [6] PASCAL A,OLAF C,ANDREAS G,et al.Semi-automatic segmentation of petrographic thin section images using a “seeded-region growing algorithm” with an application to characterize wheathered subarkose sandstone[J].Computers and Geosciences,2015,83:89-99.
• [7] 王桂芹,王正勇,罗代升.基于FCM和标记分水岭的粘连岩石颗粒图像分割[J].四川大学学报(自然科学版),2012,49(2):356-360.WANG G Q,WANG Z Y,LUO D S.Image segmentation of conglutinated rock particles based on FCM and marker watershed[J].Journal of Sichuan University (Natural science edition),2012,49 (2):356-360.
• [8] WANG L F,PAN C H.Robust level set image segmentation via a local currentropy-based K-means clustering[J].Pattern Recognition,2014,47(5):1 917-1 925.
• [9] JIANG X L,WANG Q,HE B,et al.Robust level set image segmentation algorithm using local correntropy-based fuzzy c-means clustering with spatial constraints[J].Neurocomputing,2016,207:22-35.
• [10] XU W Y,CHEN N,SU Q,et al.Shadow detection and removal in apple image segmentation under natural light conditions using an ultrametric contour map[J].Biosystems Engineering,2019,184:142-154.
• [11] IRYNA T,ROBERT A S.A parametric study of segmentation thresholds for X-ray CT porosity characterisation in composite materials[J].Composites Part A:Applied Science and Manufacturing,2019,123:10-24.
• [12] 杨仕教,彭贯军,朱忠华,等.基于ImagePy工具的岩块图像二值化分割研究[J].爆破,2018,35(4):129-135.YANG S J,PENG G J,ZHU Z H,et al.Binary segmentation of rock block image based on imagepy tool[J].Blasting,2018,35 (4):129-135.
• [13] BUSHRA M,NAZEER M,MUHAMMAD S.Adaptive hysteresis thresholding segmentation technique for localizing the breast masses in the curve stitching domain[J].International Journal of Medical Informatics,2019,126:26-34.
• [14] 史秀志,黄丹,盛惠娟,等.矿岩爆破图像二值化分割技术的研究与选择[J].爆破,2014,31(1):47-50,113.SHI X Z,HUANG D,SHENG H J,et al.Research and selection of binary segmentation technology of mine rock blasting image[J].Blasting,2014,31 (1):47-50 ,113.
• [15] 王丽丽,徐岚俊,魏舒,等.基于Sauvola与Otsu算法的秸秆覆盖率图像检测方法[J].农业工程,2017,7(4):29-35.WANG L L,XU L J,WEI S,et al.Image detection method of straw coverage based on Sauvola and Otsu algorithm[J].Agricultural Engineering,2017,7 (4):29-35.
• [16] 题正义.爆堆块度分布的自动与分形测试系统研究[D].阜新:辽宁工程技术大学,2002.TI Z Y.Study on the automatic and fractal measurement system of fragmentation distribution of explosive piles[D].Fuxing:Liaoning University of Engineering and Technology,2002.
• [17] 彭贯军.基于机器视觉对爆堆岩块图像处理识别的研究[D].衡阳:南华大学,2019.PENG G J.Study on image processing and recognition of rock burst based on machine vision[D].Hengyang:Nanhua University,2019.