基于Mask R-CNN的ORB去误匹配方法

张博; 韩广良

doi:10.3788/YJYXS20183308.0690

您当前的位置：

首页 >

文章列表页 >

基于Mask R-CNN的ORB去误匹配方法

图像处理 | 更新时间：2020-07-06

- 基于Mask R-CNN的ORB去误匹配方法
- ORB removal mis-matching method based on Mask R-CNN
- 液晶与显示 2018年33卷第8期页码：690-696
- 作者机构：
  
  1.中国科学院长春光学精密机械与物理研究所, 长春 130033
  2.中国科学院大学, 北京 100049
- 作者简介：
  
  [ "张博(1991-), 男, 吉林辽源人, 硕士研究生, 2014年于吉林大学获得学士学位, 主要从事机器视觉方面的研究。E-mail:1220792913@qq.com" ]
  [ "韩广良(1968-), 男, 山东嘉祥人, 博士, 研究员, 现为中科院长春光机所图像室主任, 主要从事目标识别、目标跟踪、机器视觉方面的研究。E-mail:hangl@ciomp.ac.cn" ]
- 基金信息：
  
  国家自然科学基金(61602432);National Natural Science Foundation of China(61602432)
- DOI：10.3788/YJYXS20183308.0690
  中图分类号： TP394.1;TH691.9
- 收稿日期：2018-03-09，
  
  录用日期：2018-6-6，
  
  纸质出版日期：2018-08-05
- 稿件说明：
移动端阅览
张博, 韩广良. 基于Mask R-CNN的ORB去误匹配方法[J]. 液晶与显示, 2018,33(8):690-696.

Bo ZHANG, Guang-liang HAN. ORB removal mis-matching method based on Mask R-CNN[J]. Chinese journal of liquid crystals and displays, 2018, 33(8): 690-696.
张博, 韩广良. 基于Mask R-CNN的ORB去误匹配方法[J]. 液晶与显示, 2018,33(8):690-696. DOI： 10.3788/YJYXS20183308.0690.

Bo ZHANG, Guang-liang HAN. ORB removal mis-matching method based on Mask R-CNN[J]. Chinese journal of liquid crystals and displays, 2018, 33(8): 690-696. DOI： 10.3788/YJYXS20183308.0690.

摘要

为了提高多目标图像的ORB匹配的正确率，提出一种基于Mask R-CNN的图像ORB去除误匹配方法，该算法首先通过Faster R-CNN方法对图像进行识别，运用区域推荐网络得到矩形框标注的感兴趣区域和类别标签，该步骤可以得到感兴趣区域的预测类别和坐标信息，并且通过全卷积网络卷积层进行像素级别校正，得到像素级别的目标所属类别，然后进行目标分割。最后在原有ORB特征点匹配基础上，剔除两幅图像中相同目标分割区域以外的误匹配点。为了验证该方法的有效性，对传统ORB匹配与基于本文方法的ORB匹配进行了仿真实验。改进后的算法，使得在多目标环境下的目标的匹配精度提高了约18.6%，结果表明，本文算法较传统的ORB匹配算法的精度有一定提高。

Abstract

This paper presents an elimination image ORB mis-matching method based on Mask R-CNN in order to improve the accuracy of multi-target image matching ORB. First of all

the algorithm identifies the image by faster R-CNN method

and it uses Region Proposal Network to obtain the interest area and category labels which are marked by rectangular box. We can get the forecast category and coordinate information of the interest area by this step. And then we correct the pixel level by the convolution layer of the Fully Convolutional Networks

and get the category of target belonging to the pixel level and segment target. Finally

the mis-matching points outside the same target segmentation area are eliminated in the two images on the basis of the original ORB matching. At the same time

some simulation experiments which use the traditional ORB matching method and the ORB matching based on this paper is carried out to verify the effectiveness of this method. The results show that the algorithm is much more accurate than that of the traditional ORB matching algorithm. The improved algorithm makes the matching accuracy in the multi-target environment be increased by 18.6%.

关键词

Keywords

references

RUBLEE E, RABAUD V, KONOLIGE K, et al . ORB: an efficient alternative to SIFT or SURF[C]// Proceedings of 2011 International Conference on Computer Vision . Barcelona, Spain: IEEE, 2011: 2564-2571.

ROSTEN E, DRUMMOND T. Machine learning for high-speed corner detection[C]// Proceedings of the 9 th European Conference on Computer Vision . Graz, Austria: Springer, 2006: 430-443.

CALONDER M, LEPETIT V, STRECHA C, et al . BRIEF: binary robust independent elementary features[C]// Proceedings of the 11 th European Conference on Computer Vision . Heraklion, Crete, Greece: Springer, 2010: 778-792.

FISCHLER M A, BOLLES R C. Random sample consensus:a paradigm for model fitting with applications to image analysis and automated cartography[J]. Communications of the ACM, 1981, 24(6):381-395.

SMITH S M, BRADY J M. SUSAN-a new approach to low level image processing[J]. International Journal of Computer Vision, 1997, 23(1):45-78.

张二磊, 马骏, 王晓田.一种改进的SURF彩色遥感图像配准算法[J].液晶与显示, 2017, 32(2):144-152.

ZHANG E L, MA J, WANG X T. Improved SURF algorithm for color remote sensing image registration[J]. Chinese Journal of Liquid Crystals and Displays, 2017, 32(2):144-152. (in Chinese)

杨梦铎, 李凡长, 张莉.李群机器学习十年研究进展[J].计算机学报, 2015, 38(7):1337-1356.

YANG M D, LI F C, ZHANG L. Advances in the study of lie group machine learning in recent ten years[J]. Chinese Journal of Computers, 2015, 38(7):1337-1356. (in Chinese)

HE K M, GKIOXARI G, DOLLÁR P, et al . Mask R-CNN[C]// Proceedings of 2017 IEEE International Conference on Computer Vision . Venice, Italy: IEEE, 2017: 2980-2988.

吴晓波, 安文斗, 杨钢.图像测量系统中的误差分析及提高测量精度的途径[J].光学精密工程, 1997, 5(1):133-141.

WU X B, AN W D, YANG G. Error analysing and approaches of improving measureing precision in image measuring system[J]. Optics and Precision Engineering, 1997, 5(1):133-141. (in Chinese)

GIRSHICK R. Fast R-CNN[C]// Proceedings of 2015 IEEE International Conference on Computer Vision . Santiago, Chile: IEEE, 2015: 1440-1448.

GEIGER A, LENZ P, STILLER C, et al. Vision meets robotics:the KITTI dataset[J]. The International Journal of Robotics Research, 2013, 32(11):1231-1237.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据