基于最小二乘修正的随机Hough变换直线检测

doi:10.11772/j.issn.1001-9081.2015.11.3312

计算机应用 ›› 2015, Vol. 35 ›› Issue (11): 3312-3315.DOI: 10.11772/j.issn.1001-9081.2015.11.3312

基于最小二乘修正的随机Hough变换直线检测

乔寅骐, 肖健华, 黄银和, 尹奎英

南京电子技术研究所, 南京 210039

收稿日期:2015-05-28 修回日期:2015-07-26 发布日期:2015-11-13
通讯作者: 乔寅骐(1990-),男,河南郑州人,硕士研究生,主要研究方向:SAR图像处理与目标识别.
作者简介:肖健华(1960-),女,江苏南京人,研究员,博士,主要研究方向:雷达信号处理; 黄银和(1967-),男,江西九江人,研究员,主要研究方向:雷达信号处理; 尹奎英(1977-),女,山东青岛人,高级工程师,博士,主要研究方向:SAR图像解译.

Randomized Hough transform straight line detection based on least square correction

QIAO Yinqi, XIAO Jianhua, HUANG Yinhe, YIN Kuiying

Nanjing Research Institute of Electronics Technology, Nanjing Jiangsu 210039, China

Received:2015-05-28 Revised:2015-07-26 Published:2015-11-13

摘要/Abstract

摘要： 利用Hough变换进行直线检测时,由于直线在参数空间中的映射容易受到邻近目标、噪声以及本身非理想状态的干扰,算法中的投票过程较易出现无效累积,进而导致虚检、漏检及端点定位不准等问题.针对传统方法的上述缺陷,提出了一种基于 ρ-θ 域最小二乘拟合修正的随机Hough变换的直线检测方法.首先, 在随机抽样时利用像素-长度比值对抽样的有效性进行判定,剔除不在直线上的抽样点对;然后, 对邻域相关点进行 ρ-θ 域的最小二乘拟合,得到修正后的直线参数用于累加投票,投票过程中设定累加阈值,通过检测峰值点逐次检出疑似长直线;最后, 通过设定断裂阈值对每条长直线进行筛选和分段,定位出直线段的端点.仿真实验表明,所提方法在投票时有效抑制了复杂环境对局部最大值的干扰,使直线检测的准确率得到显著提升.

关键词: 直线检测, 随机Hough变换, 投票有效性, 最小二乘法, 参数空间

Abstract: When applying Hough transform to straight line detection, a straight line's mapping model can easily be interfered by the other lines, short segment noise or its own un-ideality in the parameter space, which brings invalid votings leading to problems such as fault detection, missed detection and inaccurate endpoint location. A novel method was proposed which introduced Least Square Method (LSM) performed in ρ-θ domain to Random Hough Transform (RHT) algorithm for detecting straight lines. The validity of sample was verified by pixel-length ratio before each voting in order to get rid of pseudo lines, which was followed by linear fitting based on least square method in parameter space for parameter correction. By setting an accumulation threshold, straight line candidates were picked out one by one via detecting peak point. Endpoints of straight line segments were located by setting a gap-and-scale threshold. The method is proved to have higher detecting precision than conventional Hough transform.

Key words: straight line detection, Randomized Hough Transform (RHT), validity of voting, Least Square Method (LSM), parameter space

中图分类号:

TP391.4

乔寅骐, 肖健华, 黄银和, 尹奎英. 基于最小二乘修正的随机Hough变换直线检测[J]. 计算机应用, 2015, 35(11): 3312-3315.

QIAO Yinqi, XIAO Jianhua, HUANG Yinhe, YIN Kuiying. Randomized Hough transform straight line detection based on least square correction[J]. Journal of Computer Applications, 2015, 35(11): 3312-3315.

参考文献

[1] DONG J, YANG X, YU Q. Fast line segment detection based on edge connection[J]. Acta Optica Sinica, 2013, 33(3):213-220. (董晶, 杨夏, 于起峰. 基于边缘连接的快速直线段检测算法[J]. 光学学报, 2013, 33(3):213-220.)
[2] AI R, SHI Z, ZHANG C. Line segment detection in low-SNR infrared image[J]. Infrared and Laser Engineering, 2013, 42(1):278-284.(艾锐, 史泽林, 张程硕. 低信噪比红外图像直线段检测算法[J]. 红外与激光工程, 2013, 42(1):278-284.)
[3] WOODFORD O J, PHAM M T, MAKI A, et al.Demisting the Hough transform for 3D shape recognition and registration[J]. International Journal of Computer Vision, 2014, 106(3):332-341.
[4] YAO A, GALL J, van GOOL L. A Hough transform-based voting framework for action recognition[C]// Proceedings of the 2010 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2010:2061-2068.
[5] WANG Y, CHEN W, ZHANG M, et al.Method for estimating building heights via registering catadioptric omnidirectional image and remote sensing image[J]. Journal of Computer Applications, 2011, 31(9):2477-2480. (王媛媛, 陈旺, 张茂军,等. 折反射全向图像与遥感图像配准的建筑物高度提取算法[J]. 计算机应用, 2011, 31(9):2477-2480.)
[6] XU L, OJA E, KULTANEN P. A new curve detection method: Randomized Hough Transform (RHT)[J]. Pattern Recognition Letters, 1990, 11(5): 331-338.
[7] KIRYATI N, ELDAR Y, BRUCKSTEIN A M. A probabilistic Hough transform[J]. Pattern recognition, 1991, 24(4): 303-316.
[8] MAO J, MA L, GUO A, et al.Uncertainty measurement-based random Hough transform line detection in noisy condition [J].Computer Applications and Software, 2009, 26(11): 26-29. (毛俊勇, 马莉, 郭安哲, 等. 噪声环境下基于不确定性度量的随机HT直线检测[J]. 计算机应用与软件, 2009, 26(11): 26-29.)
[9] JI J, CHEN G, SUN L. A novel Hough transform method for line detection by enhancing accumulator array[J]. Pattern Recognition Letters, 2011, 32(11): 1503-1510.
[10] WANG J, ZHU Q, WANG W, et al.Straight line extraction algorithm by Hough transform combining edge grouping [J]. Journal of Remote Sensing, 2014, 18(2): 378-389. (王竞雪, 朱庆, 王伟玺,等.结合边缘编组的Hough变换直线提取[J].遥感学报, 2014, 18(2): 378-389.)
[11] LEE D, PARK Y. Discrete Hough transform using line segment representation for line detection[J]. Optical Engineering, 2011, 50(8): 087004.
[12] CHUNG K L, HUANG Y H, TSAI S R. Orientation-based discrete Hough transform for line detection with low computational complexity[J]. Applied Mathematics and Computation, 2014, 237(7): 430-437.

[1]	张齐林, 李方伟, 王明月. 基于时间反演的到达时间定位[J]. 计算机应用, 2021, 41(3): 820-824.
[2]	石昌友, 王美丽, 刘欣然, 黄慧丽, 周德强, 邓干然. 基于机器视觉的不同类型甘蔗茎节识别[J]. 计算机应用, 2019, 39(4): 1208-1213.
[3]	王波, 刘德亮. 基于迭代自适应方法的近场源二维参数联合估计[J]. 计算机应用, 2019, 39(2): 523-527.
[4]	李元, 吴昊俣, 张成, 冯立伟. 基于改进偏最小二乘法的多模态过程故障检测方法[J]. 计算机应用, 2018, 38(12): 3601-3606.
[5]	曹俊丽, 李居峰. 基于莱特准则的椭圆拟合优化算法[J]. 计算机应用, 2017, 37(1): 273-277.
[6]	赵小乐, 吴亚东, 田金沙, 张红英. 统一最小二乘规则的单幅图像超分辨算法[J]. 计算机应用, 2016, 36(3): 800-805.
[7]	李晓雯, 元向辉, 周春翔. 基于惯导角度量测的轨道平面最佳线形参数估计算法[J]. 计算机应用, 2016, 36(12): 3499-3504.
[8]	王越, 范先星, 刘金城, 庞振营. 结构化道路上应用区域划分的车道线识别[J]. 计算机应用, 2015, 35(9): 2687-2691.
[9]	付辉, 吴斌, 韩东轩, 黄阳强. 基于大气物理模型的快速视觉优化去雾算法[J]. 计算机应用, 2015, 35(11): 3316-3320.
[10]	郑凤飞, 黄文培, 贾明正. 基于Spark的矩阵分解推荐算法[J]. 计算机应用, 2015, 35(10): 2781-2783.
[11]	王刚石守东林宜丙. 基于图像检测的双绞线绕距测量方法[J]. 计算机应用, 2014, 34(10): 3014-3019.
[12]	刘旭巫玲陈念年范勇段晶晶任新宇夏菁菁. 基于光栅投影序列图像融合的倾斜校正算法[J]. 计算机应用, 2013, 33(11): 3209-3212.
[13]	尚丽苏品刚周燕. 基于改进的快速稀疏编码的图像特征提取[J]. 计算机应用, 2013, 33(03): 656-659.
[14]	孙劲光周玉成孟祥福李扬. 基于三维肤色模型的人脸检测预处理方法[J]. 计算机应用, 2012, 32(04): 1126-1129.
[15]	范怡傅继武. 基于中点提取的椭圆检测算法[J]. 计算机应用, 2011, 31(10): 2705-2707.

基于最小二乘修正的随机Hough变换直线检测

Randomized Hough transform straight line detection based on least square correction

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics