| 结合边缘编组的Hough变换直线提取 |
| |
| 引用本文： | 王竞雪,朱庆,王伟玺,赵丽科.结合边缘编组的Hough变换直线提取[J].遥感学报,2014,18(2):378-389. |
| |
| 作者姓名： | 王竞雪 朱庆 王伟玺 赵丽科 |
| |
| 作者单位： | 辽宁工程技术大学 测绘与地理科学学院, 辽宁 阜新 123000;西南交通大学 地球科学与环境工程学院, 四川 成都 610031;深圳市国土资源创新研究中心, 广东 深圳 518034;辽宁工程技术大学 测绘与地理科学学院, 辽宁 阜新 123000 |
| |
| 基金项目： | 国家重点基础研究发展计划（973计划）（编号：2010CB731801）；国家自然科学基金项目（编号：41101452，41201454）；武汉大学测绘遥感信息工程国家重点实验室开放基金资助（编号：11I02）；高等学校博士学科点专项科研基金资助课题（编号：20112121120003） |
| |
| 摘 要： | 针对传统Hough变换用于直线检测存在的问题进行了细致的分析和归纳总结,在此基础上,提出一种结合边缘编组的Hough变换直线提取算法。该算法首先采用基于8邻域的边缘跟踪算法对Canny算子检测得到的边缘点进行编组;然后对每一个边缘组分别进行Hough变换,单独确定Hough变换原点和参数的取值范围。Hough变换过程中,采用迭代的"投票"方式,每次确定单一峰值点并删除对应像素。实验证明,该算法原理简单,能有效解决传统Hough变换存在的精度不高、计算复杂等问题。同时该算法具有较强的鲁棒性,可以有效处理不同类型的影像数据,适用于并行处理。
|
| 关 键 词： | 直线提取 Hough变换 边缘编组 边缘跟踪 |
| 收稿时间： | 2013/5/24 0:00:00 |
| 修稿时间： | 2013/10/15 0:00:00 |
Straight line extraction algorithm by Hough transform combining edge grouping |
| |
| WANG Jingxue,ZHU Qing,WANG Weixi and ZHAO Like.Straight line extraction algorithm by Hough transform combining edge grouping[J].Journal of Remote Sensing,2014,18(2):378-389. |
| |
| Authors: | WANG Jingxue ZHU Qing WANG Weixi and ZHAO Like |
| |
| Institution: | School of Geometrics, Liaoning Technical University, Fuxin 123000, China;Faculty of Geosciences and Environmental Engineering, Southwest Jiaotong University, Chengdu 610031, China;Shenzhen Innovation Research Centre of Land and Resources, Shenzhen 518034, China;School of Geometrics, Liaoning Technical University, Fuxin 123000, China |
| |
| Abstract: | This paper analyzes and discusses the main problems of line detection and extraction by traditional Hough transform in detail. Thus, it proposes an algorithm of straight line extraction by Hough transform combining edge grouping. This algorithm first adopts an edge tracking based on eight-neighborhood to group the detected edge points by Canny operator. It then separately performs the Hough transform to each edge group obtained by grouping, and individually determines the origin of the Hough transform and the range of parameter. This algorithm uses the iterative vote scheme to determine the single peak and the corresponding points to be deleted. The experimental results prove that the proposed algorithm is simple in principle and can effectively solve problems in the traditional Hough transform, such as low precision and complex computation. The proposed algorithm has robustness, can process different content images, and is suitable for parallel processing. |
| |
| Keywords: | straight line extraction Hough transform edge grouping edge tracking |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《遥感学报》浏览原始摘要信息 |
| 点击此处可从《遥感学报》下载免费的PDF全文 |
|
