基于邻近目标置信度评估的视觉目标跟踪与定位

doi:10.16182/j.issn1004731x.joss.19-VR0514

系统仿真学报 ›› 2020, Vol. 32 ›› Issue (7): 1294-1300.doi: 10.16182/j.issn1004731x.joss.19-VR0514

基于邻近目标置信度评估的视觉目标跟踪与定位

柳有权^{1, *}, 裴雪¹, 李婉¹, 刘正雄²

1. 长安大学信息工程学院,陕西西安 710064;
2. 西北工业大学航天学院,陕西西安 710072

收稿日期:2019-09-09 修回日期:2019-12-16 出版日期:2020-07-25 发布日期:2020-07-15
作者简介:柳有权(1976-),男,湖北秭归,博士,教授,硕导,研究方向为计算机图形学、虚拟现实技术;裴雪(1992-),女,河南新乡,硕士生,研究方向为计算机图形学、虚拟现实技术。

Visual Tracking and Localization Based on Confidence Evaluation of Adjacent Targets

Liu Youquan^{1, *}, Pei Xue¹, Li Wan¹, Liu Zhengxiong²

1. School of information Engineering, Chang'an University, Xi'an 710064, China;
2. School of Astronautics, Northwestern Polytechnical University, Xi'an 710072, China;

Received:2019-09-09 Revised:2019-12-16 Online:2020-07-25 Published:2020-07-15

摘要/Abstract

摘要： 针对视觉目标跟踪与定位中,目标因为无特征或被严重遮挡导致无法定位的问题,设计了一种基于邻近目标置信度评估的视觉目标跟踪与定位算法。在跟踪过程中,通过检测提取邻近目标的标记特征,然后结合每个特征标记的汉明距离和相对其他标记的归一化结果以及每个标记发生的概率,得到每个标记最终置信度,选择置信度最大的邻近标记来确定目标位置。实验结果表明,该算法在对目标存在遮挡或目标没有特征的情况可以大大提高跟踪的鲁棒性和准确性。

关键词: 目标跟踪与定位, 邻近标记, 置信度评估, 汉明距离

Abstract: In visual target tracking and localization, the target could not be located due to the lack of features or the severe occlusion. Aiming at this, an algorithm based on confidence evaluation of neighboring targets is designed. In the tracking process, by detecting and extracting the marker features of neighboring targets, and combining the Hamming distance of each feature marker and the normalized result with respect to other markers as well as the probability of occurrence of each marker, the final confidence of each marker is obtained. The marker with the maximum confidence is to used determine the target location. Experimental results show that the algorithm can greatly improve the robustness and accuracy of tracking during occlusion or target features missing.

Key words: target tracking and localization, proximity marking, confidence evaluation, Hamming distance

中图分类号:

TP391.4

柳有权, 裴雪, 李婉, 刘正雄. 基于邻近目标置信度评估的视觉目标跟踪与定位[J]. 系统仿真学报, 2020, 32(7): 1294-1300.

Liu Youquan, Pei Xue, Li Wan, Liu Zhengxiong. Visual Tracking and Localization Based on Confidence Evaluation of Adjacent Targets[J]. Journal of System Simulation, 2020, 32(7): 1294-1300.

参考文献 16

[1]	黄凯奇, 陈晓棠, 康运锋, 等. 智能视频监控技术综述[J]. 计算机学报, 2015, 38(6): 1093-1118.Huang Kaiqi, Chen Xiaotang, Kang Yunfeng, et al.Overview of Intelligent Video Surveillance Technology[J]. Chinese Journal of Computers, 2015, 38(6): 1093-1118.
[2]	Ali A, Jalil A, Niu J, et al.Visual object tracking-classical and contemporary approaches[J]. Frontiers of Computer Science (S2095-2228), 2016, 10(1): 167-188.
[3]	Blanco-Pons S, Carrión-Ruiz B, Lerma J L, et al.Design and implementation of an augmented reality application for rock art visualization in Cova dels Cavalls (Spain)[J]. Journal of Cultural Heritage (S1296-2074), 2019, 39: 177-185.
[4]	Han C.The Calibration of Kinect Camera Based on ARtoolkit[C]. Proceedings of 2017 2nd International Conference on Mechatronics, Control and Automation Engineering (MCAE2017). Pennsylvania: DEStech Publications, 2017: 169-175.
[5]	Khan D, Ullah S, Rabbi I.Factors affecting the design and tracking of ARToolKit markers[J]. Computer Standards and Interfaces (S0920-5489), 2015, 2: 56-66.
[6]	Fiala M.ARTag, a fiducial marker system using digital techniques[C]. Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR, 2005)- Volume 2. Washington, DC, USA: IEEE Computer Society, 2005: 590-596.
[7]	Byeon M, Lee M, Kim K, et al.Variational Inference for 3-D Localization and Tracking of Multiple Targets Using Multiple Cameras[J]. IEEE Transactions on Neural Networks and Learning Systems (S2168-2388), 2019, 30: 3260-3274.
[8]	姜明新, 王洪玉. 基于置信度评估的在线目标跟踪算法[J]. 大连理工大学学报, 2013, 53(5): 755-759.Jiang Mingxin, Wang Hongyu.Online Target Tracking Algorithm Based on Confidence Evaluation[J]. Journal of Dalian University of Technology, 2013, 53(5): 755-759.
[9]	Olson E.AprilTag: A robust and flexible visual fiducial system[C]. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA). New York: IEEE Press, 2011: 3400-3407.
[10]	Wagner D, Reitmayr G, Mulloni A, et al.Pose tracking from natural features on mobile phones[C]. Proceedings of the 7th IEEE and ACM International Symposium on Mixed and Augmented Reality (ISMAR 08). Washington, DC, USA: IEEE Computer Society, 2008: 125-134.
[11]	金绍港. 基于嵌套二维码的车载旋翼无人机自主跟踪与降落技术研究[D]. 北京: 国防科学技术大学, 2016.Jin Shaogang.Autonomous Tracking and Landing Technology of Vehicle Rotor UAV Based on Nested Two-dimensional Code[D]. Beijing: National University of Defense Technology, 2016.
[12]	Babu R V, Pérez P, Bouthemy P.Robust tracking with motion estimation and local Kernel-based color modeling[J]. Image and Vision Computing (S0262-8856), 2006, 25(8): 1205-1216.
[13]	杨亦乐, 高玮玮, 马晓峰, 等. 基于深度学习的行人数量统计方法[J]. 软件, 2019, 40(11): 119-122, 151.Yang Yile, Gao Weiwei, Ma Xiaofeng, et al.Pedestrian statistics method based on deep learning[J]. Software, 2019, 40(11): 119-122, 151.
[14]	韩健. 基于内容的图像索引研究[D]. 南京: 东南大学, 2018.Han Jian.Research on Content-Based Image Indexing[D]. Nanjing: Southeast University, 2018.
[15]	Krogius M, Haggenmi A, Olson E.Flexible Layouts for Fiducial Tags[C]. Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). New York: IEEE Press, 2019.
[16]	Wang J, Olson E.Apriltag 2: Efficient and robust fiducialdetection[C]. 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). New York: IEEE Press, 2016: 4193-4198.

基于邻近目标置信度评估的视觉目标跟踪与定位

Visual Tracking and Localization Based on Confidence Evaluation of Adjacent Targets

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献 16

相关文章 1

编辑推荐

Metrics

本文评价