基于梯度的区域生长和距离直方图的快速圆检测方法

针对基于Hough 变换类圆检测算法所需设置参数较多和基于距离直方图的算法计算量大等问题，提出了一种基于梯度的区域生长和距离直方图的快速圆检测方法(GHC)。该算法通过利用梯度模值和方向进行区域生长的方法得到若干圆弧线段支撑区域；选取弧线段上的三个坐标点求解该圆弧段对应的圆心和半径并求解出正方形适应区域；将每条圆弧线段上的所有点向其适应区域内各坐标点进行投影并统计距离的累加值；综合全图距离直方图，精确地求解出图像中包含各圆的圆心和半径并进行完整度校验。通过实验表明，相比基于距离直方图的圆检测算法(HBCD)和随机Hough变换算法(RHT)，该法对不同尺寸、完整度的单圆或多圆均有良好的检测效果，具有较强的稳健性和较小的空间、时间复杂度。

Abstract

The most existing circle detectors based on Hough transform need to tune many parameters while the methods based on histogram are complex in computation and resource, thus a fast circle detector based on regiongrowing of gradient and histogram of Euclidean distance is presented to solve the above problems. The pixels′ gradient module and direction are computed in the first step and region-growing method is implemented to generate arc support regions. Three coordinates of each arc support region (ASR) are then selected to solve the center and radius of its corresponding circle and determine a square fitting area (SFA). Afterward, the Euclidean distances between every coordinates on each ASR and each coordinate of its ASR’s corresponding SFA are computed and recorded in a three dimensional accumulator. A histogram is used to count the frequency of the distances that participate in the accumulator and the parameters of each circle are acquired. A verification strategy of circular integrity is used to test the detection results. Compared with the histogram based circle detection (HBCD) and random Hough transform (RHT), experimental results indicate that the proposed algorithm is able to detect partial circles, multiple centers or circles in partial occlusion. This method has features of high speed, low consumption, wide range of application and strong anti-interference performance．

参考文献

[1] 丁伟利, 李勇, 王文锋, 等. 基于轮廓特征理解的城市道路图像深度估计[J]. 光学学报, 2014, 34(7): 0715001.

Ding Weili, Li Yong, Wang Wenfeng, et al.. Depth estimation of urban road image based on contour understanding [J]. Acta Optica Sinica, 2014, 34(7): 0715001.

[2] 赵连军, 刘恩海, 张文明, 等. 利用全局信息提取靶标特征的方法[J]. 光学学报, 2014, 34(4): 0415002.

Zhao Lianjun, Liu Enhai, Zhang Wenming, et al.. Feature extraction of target based on global information [J]. Acta Optica Sinica, 2014, 34(4): 0415002.

[3] 杨娜, 陈后金, 李志林, 等. 复杂背景图像中圆检测的新算法[J]. 北京交通大学学报, 2010, 34(2): 67-70.

Yang Na, Chen Houjin, Li Zhilin, et al.. A new algorithm of the circle detection in a complex background image [J]. Journal of Beijing Jiaotong University, 2010, 34(2): 67-70.

[4] 敖磊, 谭久彬, 崔继文, 等. 一种快速高精度激光CCD 自准直仪圆目标中心的定位方法[J]. 光学学报, 2007, 27(2): 253-258.

Ao Lei, Tan Jiubin, Cui Jiwen, et al.. Fast and precise center location for circle target of CCD laser autocollimator [J]. Acta Optica Sinica, 2007, 27(2): 253-258.

[5] Xu L, OJA E． Randomized Hough transform (RHT): basic mechanisms, algorithms, and computational complexities [J]. CVGIP: Image Understanding, 1993 , 57(2): 131-154.

[6] 陈传虎, 邹德旋, 刘海宽. 应用统计距离实现虹膜定位[J]. 光学精密工程, 2012, 20(11): 2516-2522.

Chen Chuanhu, Zou Dexuan, Liu Haikuan. Iris location algorithm by counting distances [J]． Optics and Precision Engineering, 2012, 20(11): 2516-2522.

[7] 商飞, 王丰贵, 田地, 等. 一种基于圆内接直角三角形的圆检测方法[J]. 光学学报, 2008, 28(4): 739-743.

Shang Fei, Wang Fenggui, Tian Di, et al.. A method for circle detection based on right triangles inscribed in a circle [J]. Acta Optica Sinica, 2008, 28(4): 739-743.

[8] V Patraucean, P Gurdjos, R G Von Gioi. A Parameterless Line Aegment and Elliptical Arc Detector with Enhanced Ellipse Fitting [M]// Andrew Fitzgibbon, Svetlana Lazebnik, Pietro Perona, et al.. Computer Vision-ECCV 2012. Berlin: Springer, 2012. 572-585.

[9] R G Von Gioi, J Jakubowicz, J M Morel, et al.. LSD: A fast line segment detector with a false detection control [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(4): 722-732.

[10] A Desolneux, L Moisan, J M Morel. From Gestalt Theory to Image Analysis: a Probabilistic Approach [M]. Berlin: Springer, 2007.

[11] S Basalamah. Histogram based circle detection [J]. International Journal of Computer Science and Network Security, 2012, 12(8): 40-43.

[12] A Desolneux, L Moisan, J M Morel. Meaningful alignments [J]. International Journal of Computer Vision, 2000, 40(1): 7-23.

[13] A Desolneux, L Moisan, J M Morel. Computational gestalts and perception thresholds [J]. Journal of Physiology-Paris, 2003, 97(2): 311-324.

[14] 覃勋辉, 马戎, 付维平, 等. 一种基于梯度的直线段检测算法[J]. 光子学报, 2012, 41(2): 205-209.

Qin Xunhui, Ma Rong, Fu Weiping, et al.. A line segments detection algorithm based on grad [J]. Acta Photonica Sinica, 2012, 41(2): 205-209.

[15] A Desolneux, S Ladjal, L Moisan, et al.. Dequantizing image orientation [J]. IEEE Trans Transactions Image Processing, 2002, 11(10): 1129-1140.

[16] K L Chung, Y H Huang, J P Wang, et al.. Fast randomized algorithm for center-detection [J]. Pattern Recognition, 2010, 43(8): 2659-2665.

蔡佳, 黄攀峰, 张彬. 基于梯度的区域生长和距离直方图的快速圆检测方法[J]. 光学学报, 2015, 35(3): 0315001. Cai Jia, Huang Panfeng, Zhang Bin. Fast Circle Detector Based on Region-Growing of Gradient and Histogram of Euclidean Distance[J]. Acta Optica Sinica, 2015, 35(3): 0315001.

基于梯度的区域生长和距离直方图的快速圆检测方法

关于本站 Cookie 的使用提示

全站搜索

基于梯度的区域生长和距离直方图的快速圆检测方法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索