基于改进Canny算子的煤矿井下物体图像边缘检测方法研究

J4 ›› 2014, Vol. 36 ›› Issue (03): 491-496.

基于改进Canny算子的煤矿井下物体图像边缘检测方法研究

尚长春,马宏伟,安静宇

(西安科技大学工程训练中心，陕西，西安 710054)

收稿日期:2013-01-07 修回日期:2013-05-21 出版日期:2014-03-25 发布日期:2014-03-25
基金资助:
国家自然科学基金资助项目（50674075）

Image edge detection method of underground
objects based on improved Canny operator

SHANG Changchun,MA Hongwei,AN Jingyu

(Engineering Training Center,Xi’an University of Science and Technology,Xi’an 710054,China)

Received:2013-01-07 Revised:2013-05-21 Online:2014-03-25 Published:2014-03-25

摘要/Abstract

摘要：

针对传统的Canny 算子检测井下物体低强度边缘能力不足的问题，提出了一种改进的边缘检测算法。该算法从以下三个方面进行改进：（1）采用一种新的四阶偏微分方程的降噪算法对图像去噪，进一步提高降噪效果，且在降噪过程中较好地保留图像细节，使井下物体更容易被检测。（2）采用自适应阈值的方法对图像边缘进行检测，实现了双阈值的自适应提取，能够较好地提取真实边缘。特别是在低对比度图像的边缘提取上，此方法更具有优势。（3）基于模糊判决的理论，在传统的Canny算法的基础上提出了一种有效的边缘连接方法。为了验证Canny边缘检测算子的效果，分别用Prewitt 、Robert 、Sobel、传统的Canny算子对井下图像进行边缘检测实验,结果表明，该方法在最大程度抑制噪声的同时，能检测到更多的低强度边缘，为井下煤矿探测机器人图像辨识奠定了基础。

关键词: Canny算子, Otsu算法, 高斯拉普拉斯变换

Abstract:

In view of the shortage of the traditional Canny algorithm in detecting the low intensity edge capacity, the improved edge detection method is carried out from the following three aspects: (1) Using a new fourorder partial differential equations of the noise reduction algorithm for image denoising, it can further improve the noise reduction effect and better preserve image details in the noise reduction process, so that the underground objects are more easily detected. (2) Using an adaptive threshold method for the image edge detection, the method realizes the adaptive dual threshold extraction, which can effectively extract the real edge. Especially in the edge extraction of low contrast image, this method has more advantages. (3) Using the theory of fuzzy decision, an effective edge connection method is proposed based on the traditional Canny algorithm. Finally, in order to verify the effect of Canny edge detection operator, Prewitt, Robert, Sobel, and traditional Canny algorithms are used to perform the underground image edge detection test. The results show that the new method can detect more lowintensity edge and inhibit the noise at the greatest degree. It gives the foundation for the robot image recognition in coal mine.

Key words: canny operator;Otsu algorithm;Gauss Laplasse transform

尚长春,马宏伟,安静宇. 基于改进Canny算子的煤矿井下物体图像边缘检测方法研究[J]. J4, 2014, 36(03): 491-496.

SHANG Changchun,MA Hongwei,AN Jingyu. Image edge detection method of underground
objects based on improved Canny operator [J]. J4, 2014, 36(03): 491-496.

参考文献

［1］Jiang Aihua, Xing Jishou. Image edge processing technology［J］. Science Technology and Engineering,2005,5(5):299230.(in Chinese)
［2］Zhang Zheng, Wang Yanping. Digital image processing and machine vision［M］. Beijing:People’s Posts and Telecommunications Press, 2010.(in Chinese)
［3］Zhang Chunxue, Chen Xiuhong. Noise image edge detection method based on zero crossing［J］. Computer Engineering & Science, 2010,32(9):4042.(in Chinese)
［4］Szeliski R. Computer vision algorithm and application［M］. Ai Haizhou, Xing Junliang, Translation. Beijing:Tsinghua University Press, 2012.(in Chinese)
［5］Zhao Cuifang,Shi Caicheng.Gray image compression based on quadtree and partial differential equation［J］.Optical Technique, 2007,33(6):848850.(in Chinese)
［6］Xue Lixia,Li Tao.Adaptive Canny edge detection algorithm［J］.Application Research of Computer, 2010,27(9):35893590.(in Chinese)
［7］Tang Lulu, Zhang Qican. An improved algorithm for Canny edge detection with adaptive threshold［J］. Optoelectronic Engineering, 2011,38(5):128131.(in Chinese)
［8］Mo Shaoqing, Liu Zhengguang. An unsupervised threshold selection method for edge detection based on the image selfinformation［J］.Journal of Optoelectronics · Laser, 2011,22(8):12471249.(in Chinese)
［9］Liang Guangming, Sun Jixiang, Ma Qi.An application of Otsu algorithm on Canny operator［J］. Journal of National University of Defense Technology, 2003,25(5):3740.(in Chinese)
［10］Yang Shaoqing, Jia Chuanying.Image edge connect based on fuzzy logic［J］.Optical Technique, 2002,28(2):108109.(in Chinese)
［11］de Jong H. Modeling and simulation of genetic regulatory systems:A literature review［J］. Computtational, 2002, 9(1):67103.
［12］Destrempes F, Mignotte M. Astatistical model for contours in images［J］. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2004, 26(5):626638.
［13］Bao P, Zhang L. Canny edge detection enhancement by scale multiplication［J］. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2005, 27(9):1485 1490.
附中文参考文献：
［1］蒋爱花,邢济收.图像边缘处理技术［J］.科学技术与工程，2005,5(5):299230.
［2］张铮,王艳平.数字图像处理与机器视觉［M］.北京:人民邮电出版社,2010.
［3］张春雪,陈秀宏.基于零交叉的噪声图像边缘检测［J］.计算机工程与科学,2010,32(9):4042.
［4］Szeliski R. 计算机视觉算法与应用［M］.艾海舟,兴军亮,译.北京:清华大学出版社,2012.
［5］赵翠芳,史彩成.基于四叉树和偏微分方程的灰度图像压缩［J］.光学技术,2007,33(6):848850.
［6］薛丽霞,李涛.一种自适应的 Canny 边缘检测算法［J］.计算机应用研究,2010,27(9):35893590.
［7］唐路路,张启灿.一种自适应阈值的Canny边缘检测算法［J］.光电工程,2011,38(5):128131.
［8］磨少清,刘正光.基于图像自身信息的图像边缘检测阈值自动设定方法［J］.光电子·激光,2011,22(8)：12471249.
［9］梁光明,孙即祥,马琦.Otsu算法在Canny算子中的应用［J］.国防科技大学学报,2003,25(5):3740.
［10］杨绍清,贾传荧.基于模糊判决的图像边缘连接［J］.光学技术,2002,28(2):108109.

[1]	郭晋秀, 张月芳, 邓红霞, 李海芳. 融合分区与Canny泛函的水平集对猴脑提取的研究[J]. 计算机工程与科学, 2020, 42(12): 2193-2198.
[2]	陈树，丁保阔. 一种基于改进视觉背景提取算法的前景检测[J]. 计算机工程与科学, 2018, 40(04): 673-680.
[3]	黄山1,李众1，黄蒙蒙2. 利用数据场和欧氏距离的图像边缘提取[J]. 计算机工程与科学, 2016, 38(11): 2297-2302.
[4]	何俊,房灵芝,蔡建峰,何忠文. 基于ASM和肤色模型的疲劳驾驶检测[J]. 计算机工程与科学, 2016, 38(07): 1447-1453.
[5]	方建军1，杜明芳1,2 ，庞睿1. 基于小波分析和概率Hough变换的书脊视觉识别[J]. J4, 2014, 36(01): 126-131.
[6]	张小红，张媛. 基于纹理特征的H.264/AVC帧内预测模式快速选择算法[J]. J4, 2013, 35(4): 81-86.
[7]	秦筱楲[1] 丁明跃[2]. 基于图像分析的后视镜失真率自动检测方法[J]. J4, 2005, 27(7): 57-59.