期刊文献+

局部特征描述改进的LK跟踪注册方法 被引量:2

Improved Lucas Kanade tracking and registration method based on local descriptor
下载PDF
导出
摘要 针对KLT跟踪方法抗光照变化和抗遮挡较差的问题,提出一种使用局部特征描述改进的LK跟踪注册方法(DF-LK)。使用ORB特征点求解初始位姿,通过自适应非极大值抑制重新划分特征点,选择均匀分布的特征点作为LK方法跟踪的控制点集。相邻帧图像之间的单应性矩阵通过在DF描述后的图像上使用LK方法进行求解,跟踪的结果由向前向后错误检测进行评估,由单应性矩阵和初始位姿求解出当前帧的摄像机位姿,并叠加虚拟信息。实验结果表明,该方法在光照变化、部分遮挡和透视变化时均有较好的稳定性和鲁棒性。 To solve the problem that KL tracker is not illumination invariant and occlusion robust,an improved Lucas Kanade tracking and registration method(DF-LK)based on local descriptor was proposed.The initial camera pose was calculated using ORB keypoints,keypoints were repartitioned through adaptive non-maximal suppression and the well-distributed keypoints were chosen as the aggregation of control points tracking using LK method.The homography matrix between two successive images that described by descriptor fields was computed using LK method and the tracking result was estimated by forward-backward error detection.The current camera pose was calculated with homography matrix and initial camera pose.And virtual information was added.Experimental results show that the proposed method is robust and stable against illumination changes,partial occlusion and perspective distortion.
作者 杨靖帆 何汉武 吴悦明 YANG Jing-fan;HE Han-wu;WU Yue-ming(School of Electromechanical Engineering,Guangdong University of Technology,Guangzhou 510006,China;Department of Mechanical Engineering,Guangdong Polytechnic of Industry and Commerce,Guangzhou 510510,China)
出处 《计算机工程与设计》 北大核心 2020年第2期458-464,共7页 Computer Engineering and Design
基金 广东省科技计划基金项目(2017B010110008、2016A040403108)
关键词 增强现实 跟踪注册 局部描述子 自适应非极大值抑制 向前向后错误 augmented reality tracking and registration local descriptor adaptive non-maximal suppression forward backward error
  • 相关文献

参考文献4

二级参考文献30

  • 1史泽林,王俊卿,黄莎白.复杂场景下的变形目标跟踪[J].光电工程,2005,32(1):31-35. 被引量:4
  • 2叶 斌,徐 毓.强跟踪滤波器与卡尔曼滤波器对目标跟踪的比较[J].空军雷达学院学报,2002,16(2):17-19. 被引量:20
  • 3陈付幸,王润生.基于预检验的快速随机抽样一致性算法[J].软件学报,2005,16(8):1431-1437. 被引量:106
  • 4Ronald T. A Survey of Augmented Reality [J]. Teleoperators and Virtual Environments (S1054-7460), 1997, 4(2): 355-385.
  • 5Donggang Yu. A Useful Visualization Technique: A Literature Review for Augmented Reality and its Application, limitation & future direction [C]// Sydney, Australia: International Conference on Visual Information Communications, 2010. Germany: Springer-Verlag, 2010: 311-337.
  • 6Manfred Klopschitz. Visual tracking for augmented reality [C]// Zurich, Switzerland: IPIN 2010. USA: IEEE, 2010: 6-10.
  • 7Zdenek Kalal. Tracking-Learning-Detection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence (S0162-8828), 2012, 34(7): 1409-1422.
  • 8Zdendk Kalal. Forward-Backward Error: Automatic Detection of Tracking Failures [C]// Istanbul, Turkey: ICPR 2010. USA: IEEE, 2010: 23-26.
  • 9Zdenek Kalal. Online Learning of Robust Object Detectors during Unstable Tracking [C]//Kyoto, Japan: ICCV Workshops 2009. USA: IEEE 2009: 1417-1424.
  • 10Herbert Bay. Speeded-Up Robust Features [J]. Computer Vision and Image Understanding (S 1077-3142), 2008, 110(3): 346-359.

共引文献22

同被引文献13

引证文献2

二级引证文献3

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部