基于改进SURF算法的机器人识别匹配方法
摘要:由于传统SURF匹配算法选取大量不符合预期的特征点,增加了后期匹配運算时间,导致不能满足工业级应用快速性的要求。提出一种改进的SURF算法,首先对摄像头获取的目标图像进行均值滤波处理,然后选择合理阈值、运用Canny算子对获取的目标图像进行边缘检测,再通过Hessian矩阵获取图像局部最值,并利用SURF算法对边缘图像进行匹配。仿真结果表明,该SURF算法在应用于工业机器人目标识别匹配时,既能减少匹配时间,又可以提高匹配准确度。
关键词:Canny边缘检测;SURF算法;图像匹配;目标识别
DOIDOI:10.11907/rjdk.181630
中图分类号:TP301
文献标识码:A 文章编号:1672-7800(2018)010-0014-04
英文摘要Abstract:Traditional SURF matching algorithm tends to pick a large number of feature points that do not meet expectations, which prolongs the time of matching operation later, leading to the inability to meet the requirements of rapidity in industrial applications. To solve this problem, an improved SURF algorithm was proposed in this article. Firstly, the target image acquired by the camera is subjected to mean filtering processing, then the reasonable threshold is selected to use the Canny operator to perform edge detection on the acquired target image. Furthermore the local maximum value of the image is obtained by Hessian matrix, and the edge image is matched by SURF algorithm. Experimental results show that the improved SURF algorithm can not only reduce the matching time but also improve the matching accuracy when it is applied to target recognition and matching of industrial robots.
英文关键词Key Words:Canny edge detection; SURF algorithm; image matching; target recognition
0 引言<...
== 试读已结束,如需继续阅读敬请充值会员 ==
|
本站文章均为原创投稿,仅供下载参考,付费用户可查看完整且有格式内容!
(费用标准:38元/2月,98元/2年,微信支付秒开通!) |
升级为会员即可查阅全文 。如需要查阅全文,请 免费注册 或 登录会员 |