边缘检测是岩石裂隙图像识别领域的一个重要方向。针对经典Canny算法在边缘检测精度方面的不足,提出一种基于改进Canny算子的岩石裂隙识别算法,采用双边滤波代替原始高斯滤波对图像进行平滑去噪;采用4方向的3×3 Sobel算子代替原始2×2模板计算图像梯度;采用Otsu算法自适应确认Canny高低阈值。选取单一型、偏Y型与T型岩石裂隙图像进行仿真实验,从边缘像素统计与算法执行效率两个方面对其进行评价。结果表明:与经典Canny算法、Sobel算子相比,改进Canny算法C/A值分别降低80.9%~90.3%、54.4%~76.7%,C/B值分别降低67.3%~82.6%、43.7%~76.0%;改进Canny算法边缘点连接程度好,伪边缘抑制性强,在边缘检测精度与整体功能性方面均取得了较大进步,但执行效率有待进一步提高。改进Canny算法为岩石裂隙识别方面的研究提供了新思路。
Edge detection is an important direction in the field of rock fracture image recognition. Aiming at the shortcomings of classical Canny algorithm in edge detection accuracy, a rock fracture recognition algorithm based on improved Canny operator is proposed. Bilateral filtering is used instead of original Gaussian filtering to smooth and denoise the image. The 3 × 3 Sobel operator in 4 directions is used to replace the original 2 × 2 template to calculate the image gradient. Otsu algorithm is used to adaptively confirm Canny high and low thresholds. The single type, Y-shaped and T-type rock fracture images are selected for simulation experiments, and evaluated from two aspects of edge pixel statistics and algorithm execution efficiency. The results show that compared with the classical Canny algorithm and Sobel operator, the C/A value of the improved Canny algorithm is reduced by 80.9%~90.3% and 54.4%~76.7% respectively. The C/B value decreased by 67.3%~82.6% and 43.7%~76.0%, respectively. The connection degree of edge points is good, and the pseudo-edge suppression is strong. Great progress has been made in edge detection accuracy and overall functionality, but the execution efficiency needs to be further improved. The improved Canny algorithm provides a new idea for the study of rock fracture identification.
[1] 许海亮,任合欢,宋义敏.带裂纹花岗岩试件三点弯变形演化及破裂机制[J].地下空间与工程学报,2022,18(4):1199-1207,1218.
[2] 陈云娟,朱维申,王知深,等.裂隙岩体表征单元体的确定及工程应用[J].地下空间与工程学报,2016,12(1):25-29.
[3] 杨东辉,赵毅鑫,滕腾,等.砂岩破裂失稳声发射临界特征与Kaiser点识别研究[J].应用基础与工程科学学报,2021,29(1):218-230.
[4] 王军祥,曾相森,徐晨晖,等.基于图像处理技术的岩体裂隙定量识别方法研究[J].地下空间与工程学报,2022,18(2):446-457.
[5] Huang M L,Liu Y L,Yang Y M.Edge detection of ore and rock on the surface of explosion pile based on improved Canny operator[J].Alexandria Engineering Journal,2022,61(12):10769-10777.
[6] 张庆贺,陈晨,袁亮,等.基于DIC和YOLO算法的复杂裂隙岩石破坏过程动态裂隙早期智能识别[J].煤炭学报,2022,47(3):1208-1219.
[7] Canny J.A computational approach to edge detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1986,8(6):679-698.
[8] 赵芳,周旺辉,陈岳涛,等.改进的Canny算子在裂缝检测中的应用[J].电子测量技术,2018,41(20):107-111.
[9] Talab A M A,Huang Z,Xi F,et al.Detection crack in image using Otsu method and multiple filtering in image processing techniques[J].Optik - International Journal for Light and Electron Optics,2016,127(3):1030-1033.
[10] 黄昊,刘强,郭立钱,等.基于Canny算子和形态学的洞室岩体裂隙边缘检测[J].计算机应用与软件,2012,29(3):262-264.
[11] 郭强,车爱兰,黄醒春,等.用摄影测量方法研究岩体破碎区域分布规律[J].地下空间与工程学报,2012,8(2):318-322.
[12] 瞿中,林丽丹,郭阳.形态学与区域延伸相结合的图像裂缝检测算法研究[J].计算机科学,2014,41(11):297-300.
[13] 王顺阳,贺易航,韩博.基于Canny优化算法物理模拟实验覆岩裂隙场自动识别研究[J].能源与环保,2022,44(11):313-318.
[14] 邓兆鹏,曹茂永,LAXMISHA Rai.基于改进的区域生长和Hough变换的钻孔图像水平裂隙识别[J].科学技术与工程,2019,19(31):239-245.
[15] 谢配红,谭海英.基于图像识别技术对出露危岩体裂隙发育规律统计分析[J].煤炭技术,2021,40(7):66-67.
[16] 许杰颖,谢雄耀,周应新,等.山岭隧道结构裂缝特征自动化提取算法研究[J].地下空间与工程学报,2019,15(增1):219-224.
[17] 唐建新,刘庆,代张音,等.注浆裂隙砂质泥岩力学特性和破坏模式研究[J].地下空间与工程学报,2021,17(4):1028-1037.
[18] 汤双臣,冯鹏,赵家琛.含交叉裂隙岩石试样单轴力学特性与破坏机理[J].地下空间与工程学报,2021,17(5):1376-1383,1407.
[19] 熊俊豪,刘宝臣,刘磊,等.基于摄影法的红黏土裂隙试验研究[J].地下空间与工程学报,2020,16(2):381-387.
[20] 骆赵刚,许冲,杨振北,等.土体裂隙的量测表征及开裂试验研究[J].地下空间与工程学报,2021,17(1):126-134.
[21] Ramnarayan R,Saklani N,Verma V.A review on edge detection technique “Canny edge detection”[J].International Journal of Computer Applications,2019,178(10):28-30.
[22] 杜绪伟,陈东,马兆昆,等.基于Canny算子的改进图像边缘检测算法[J].计算机与数字工程,2022,50(2):410-413,457.
[23] Zhao L J,Zhu R S.Research on image contour edge analysis based on Canny edge detector[J].Academic Journal of Computing & Information Science,2022,5(1):70-75.
[24] 李俊山,马颖,赵方舟,等.改进的Canny图像边缘检测算法[J].光子学报,2011,40(增1):50-54.
[25] Hu T Y,Qi Z F,Qin Y F,et al.Detecting technology of current generator blade shape based on improved canny algorithm[J].IOP Conference Series:Materials Science and Engineering,2018,452(3):032026.
[26] 李静,陈桂芬,丁小奇.基于改进Canny算法的图像边缘检测方法研究[J].计算机仿真,2021,38(4):371-375.
[27] 林卉,赵长胜,舒宁.基于Canny算子的边缘检测及评价[J].黑龙江工程学院学报,2003(2):3-6,16.
