首页 > 论文 > 光学学报 > 38卷 > 12期(pp:1212002--1)

基于语义目标匹配的三维跟踪注册方法

Three-Dimensional Tracking Registration Method Based on Semantic Object Matching

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

提出了一种基于语义目标匹配的三维跟踪注册方法。通过改进的单发多框检测(SSD)深度卷积神经网络对图像进行语义分割,获取场景中不同目标的像素级语义分割结果。在求取相机姿态的目标函数时,融合了图像的灰度约束与几何约束对相机的姿态进行估计。所提方法减小了特征点的缺乏或误匹配问题对三维跟踪注册算法性能的影响,且能够适应不同结构的场景。研究结果表明,该方法的误差不超过2.2 pixel,基本满足了实时性的要求。

Abstract

A three-dimensional (3D) tracking registration method is proposed based on the semantic object matching. The improved single-shot multi-box detector (SSD) deep convolution neural network is used to segment images semantically and thus the pixel level semantic segmentation results for different objects in the scene are obtained. To solve the object function of the camera pose, the camera pose is estimated by the combination of the gray and the geometric constraints of images. The proposed method not only reduces the influence of the lack or mismatch of feature points on the performance of 3D tracking registration algorithm, but also it can adapt to the scenes with different structures. The research results show that the error of this proposed method is less than 2.2 pixel, which basically satisfies the requirement of real-time.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391

DOI:10.3788/aos201838.1212002

所属栏目:仪器,测量与计量

基金项目:国家自然科学基金(61605016)

收稿日期:2018-06-22

修改稿日期:2018-07-20

网络出版日期:2018-07-25

作者单位    点击查看

安喆:长春理工大学光电工程学院, 吉林 长春 130022
徐熙平:长春理工大学光电工程学院, 吉林 长春 130022
杨进华:长春理工大学光电工程学院, 吉林 长春 130022
刘洋:长春理工大学光电工程学院, 吉林 长春 130022
闫宇轩:长春理工大学高功率半导体激光国家重点实验室, 吉林 长春 130022

联系人作者:徐熙平(xxp@cust.edu.cn); 安喆(2016200046@mails.cust.edu.cn);

【1】Rehman U, Cao S. Augmented-reality-based indoor navigation: A comparative analysis of handheld devices versus google glass[J]. IEEE Transactions on Human-Machine Systems, 2017, 47(1): 140-151.

【2】Joo-Nagata J, Abad F M, Giner J G-B, et al. Augmented reality and pedestrian navigation through its implementation in m-learning and e-learning: Evaluation of an educational program in Chile[J]. Computers & Education, 2017, 111: 1-17.

【3】Kress B, Starner T. A review of head-mounted displays (HMD) technologies and applications for consumer electronics[J]. Proceedings of SPIE, 2013, 8720: 87200A.

【4】Maisto M, Pacchierotti C, Chinello F, et al. Evaluation of wearable haptic systems for the fingers in augmented reality applications[J]. IEEE Transactions on Haptics, 2017, 10(4): 511-522.

【5】Montero A, Zarraonandia T, Diaz P, et al. Designing and implementing interactive and realistic augmented reality experiences[J]. Universal Access in the Information Society, 2017, 36(4): 1-13.

【6】Tsai C W. The applications of augmented reality for universal access in online education[J]. Universal Access in the Information Society, 2017, 35(3): 1-3.

【7】Yu H B, Ho H. System designs for augmented reality based ablation probe tracking[C]. Pacific-Rim Symposium on Image and Video Technology, 2017: 87-99.

【8】Khan D, Ullah S, Yan D M, et al. Robust tracking through the design of high quality fiducial markers: An optimization tool for AR ToolKit[J]. IEEE Access, 2018, 6: 22421-22433.

【9】Lin H C K, Su S H, Wang S T, et al. Influence of cognitive style and cooperative learning on application of augmented reality to natural science learning[J]. International Journal of Technology and Human Interaction, 2015, 11(4): 41-66.

【10】Zhang G, Chen H S, Ye Y D. A LoG operator based markerless augmented reality algorithm: LoG-PTAMM[J]. Journal of Computer-Aided Design & Computer Graphics, 2016, 28(9): 1577-1586.
张格, 陈昊升, 叶阳东. 一种基于LoG算子的无标识增强现实算法: LoG-PTAMM[J]. 计算机辅助设计与图形学学报, 2016, 28(9): 1577-1586.

【11】Ng-Thow-Hing V, Bark K, Beckwith L, et al. User-centered perspectives for automotive augmented reality[C]. IEEE International Symposium on Mixed and Augmented Reality-Arts, Media, and Humanities, 2013: 13-22.

【12】Hayashi T, Uchiyama H, Pilet J, Saito H. An augmented reality setup with an omnidirectional camera based on multiple object detection[J]. Proceedings of the 20th International Conference on Pattern Recognition, 2010: 3171-3174.

【13】Kong S H, Haouchine N, Soares R, et al. Robust augmented reality registration method for localization of solid organs′ tumors using CT-derived virtual biomechanical model and fluorescent fiducials[J]. Surgical Endoscopy & Other Interventional Techniques, 2017, 31(7): 2853-2871.

【14】Streckel B, Koch R. Lens model selection for visual tracking[C]. Joint Pattern Recognition Symposium, 2005: 41-48.

【15】Skrypnyk I, Lowe D G. Scene modelling, recognition and tracking with invariant image features[C]. Third IEEE and ACM International Symposium on Mixed and Augmented Reality, 2004: 110-119.

【16】An Z, Xu X P, Yang J H, et al. Design of augmented reality head up display system based on image semantic segmentation[J]. Acta Optica Sinica, 2018, 38(7): 0710004.
安喆, 徐熙平, 杨进华, 等. 结合图像语义分割的增强现实型平视显示系统设计与研究[J]. 光学学报, 2018, 38(7): 0710004.

【17】Geiger A, Lenz P, Urtasun R. Are we ready for autonomous driving? The KITTI vision benchmark suite[C]. IEEE Conference on Computer Vision and Pattern Recognition, 2012: 3354-3361.

【18】Zhang K. Research on a rapid fusion method for remote sensing images based on an improved atrous wavelet decompsition[D]. Zhengzhou: Henan University, 2016: 66-72.
张凯. 基于改进atrous小波分解的遥感影像快速融合方法的研究[D]. 郑州: 河南大学, 2016: 66-72.

【19】Kümmerle R, Grisetti G, Strasdat H, et al. G2o: A general framework for graph optimization[C]. IEEE International Conference on Robotics and Automation, 2011: 3607-3613.

【20】Liang C, Wang L, Liu H Y. Real-time vision SLAM algorithm based on extend Kalman filtering[J]. Computer Engineering, 2013, 39(8): 231-234, 238.
梁超, 王亮, 刘红云. 基于扩展卡尔曼滤波的实时视觉SLAM算法[J]. 计算机工程, 2013, 39(8): 231-234, 238.

【21】Park H S, Min W P, Won K H, et al. In-vehicle AR-HUD system to provide driving-safety information[J]. ETRI Journal, 2013, 35(6): 1038-1047.

【22】Liu S G. Research on interaction design of automobile HUD-based on user′s research and analysis[J]. China Packaging, 2018, 38(6): 56-58.
刘双广. 对汽车HUD的交互设计研究——基于用户的研究与分析[J]. 中国包装, 2018, 38(6): 56-58.

引用该论文

An Zhe,Xu Xiping,Yang Jinhua,Liu Yang,Yan Yuxuan. Three-Dimensional Tracking Registration Method Based on Semantic Object Matching[J]. Acta Optica Sinica, 2018, 38(12): 1212002

安喆,徐熙平,杨进华,刘洋,闫宇轩. 基于语义目标匹配的三维跟踪注册方法[J]. 光学学报, 2018, 38(12): 1212002

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF