运动模型引导的自适应核相关目标跟踪方法

doi:10.12263/DZXB.20200433

电子学报 ›› 2021, Vol. 49 ›› Issue (3): 550-558.DOI: 10.12263/DZXB.20200433

运动模型引导的自适应核相关目标跟踪方法

陈丹, 姚伯羽

西安理工大学自动化与信息工程学院, 陕西西安 710048

收稿日期:2020-05-08 修回日期:2020-08-01 出版日期:2021-03-25
- 作者简介:
- 陈丹女,1975年生于陕西汉中.博士,硕导.现为西安理工大学自动化与信息工程学院副教授.主要研究方向为现代信号处理,机器人目标识别与跟踪.E-mail:chdh@xaut.edu.cn;姚伯羽 男,1994年生于陕西西安.现为西安理工大学自动化与信息工程学院硕士研究生.主要研究方向为计算机视觉.E-mail:423058934@qq.com
- 基金资助:
- 国家自然科学基金 (No.61671375）; 榆林市科技计划项目 (No.2019-146）; 西安理工大学研究生竞赛培育项目 (No.252051834）

Adaptive Response Kernel Correlation Target Tracking Method Guided by Motion Model

CHEN Dan, YAO Bo-yu

School of automation and Information Engineering, Xi'an University of Technology, Xi'an, Shaanxi 710048, China

Received:2020-05-08 Revised:2020-08-01 Online:2021-03-25 Published:2021-03-25
- Supported by:
- National Natural Science Foundation of China (No.61671375); Yulin Science and Technology Project of Shaanxi Province (No.2019-146); Cultivation Program for Postgraduate Competition of Xi’an University of Technology (No.252051834)

摘要/Abstract

摘要： 针对小型移动机器人对人体目标快速运动或遮挡导致的跟踪准确率降低甚至跟踪失败问题，通过建立足部运动模型预测双脚位置信息，获得核相关滤波（KCF，Kernel Correlation Filter）目标检测区域，再结合输出响应峰值邻域相关检测，提出了运动模型引导的自适应核相关滤波算法.对实际拍摄的七组不同情况下的视频进行了足部目标跟踪实验，结果表明运动模型引导的自适应响应KCF算法平均跟踪准确率最高，且在短时间遮挡情况下的算法跟踪准确率也达到86%，明显高于自适应响应KCF、BACF （Background Aware Correlation Filters）以及SAMF （Scale Adaptive kernel correlation filters with Multiple Features）三种跟踪算法.最后在ROS （Robot Operating System）下将所提算法应用于Turtlebot机器人目标跟踪测试，成功克服了遮挡情况对足部跟踪带来的影响，验证了所提算法具有较强的鲁棒性和实时性.

关键词: 目标跟踪, 运动模型, 核相关滤波, 自适应输出响应, 遮挡检测, 机器人操作系统

Abstract: Aiming at the problem of low tracking accuracy and even tracking failure caused by fast motion or occlusion of human targets by small mobile robots, a foot motion model was established to predict the position information of feet, and the target detection region of kernel correlation filter (KCF) was obtained. In this paper, a motion model guided adaptive kernel correlation filtering algorithm is proposed by combining with the output response peak neighborhood correlation detection. Foot tracking experiments were carried out on seven groups of videos under different scenarios. The results show that the average tracking accuracy of the adaptive response KCF algorithm guided by the motion model is the highest, and the tracking precision rate of the algorithm reaches 86% in the case of short-term occlusion, which is significantly higher than that of the adaptive response KCF, BACF and SAMF algorithm. Finally, the proposed algorithm is applied to the target tracking test of a Turtlebot robot under the ROS (Robot Operating System), which successfully overcomes the influence of occlusion on feet tracking, and verifies that the proposed algorithm has strong robustness and real-time performance.

Key words: target tracking, motion model, kernel correlation filter, adaptive response, occlusion detection, ROS

中图分类号:

TP391

陈丹, 姚伯羽. 运动模型引导的自适应核相关目标跟踪方法[J]. 电子学报, 2021, 49(3): 550-558.

CHEN Dan, YAO Bo-yu . Adaptive Response Kernel Correlation Target Tracking Method Guided by Motion Model[J]. Acta Electronica Sinica, 2021, 49(3): 550-558.

参考文献

[1] Bolme D S,Beveridge J R,Draper A B.Visual object tracking using adaptive correlation filters[A].Twenty-third IEEE Conference on Computer Vision & Pattern Recognition[C].Los Alamitos:IEEE Computer Society Press,2010.2554-2560.
[2] Henriques J F,Caseiro R,Martins P.High-speed tracking with kernelized correlation filters[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2014,37(3):583-596.
[3] Wu Y,Lim J,Yang M H.Object tracking benchmark[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2015,37(9):1834-1848.
[4] Kumara R,Maria A.Object tracking with adaptive motion modeling of particle filter and support vector machines[A].2015 IEEE International Conference on Image Processing[C].Los Alamitos:IEEE Computer Society Press,2015.353-360.
[5] Wang X P,Zhao Q J,Tan H K.Self-tuning visual tracking based on multiple motion models[A].2016 35th Chinese Control Conference[C].Los Alamitos:IEEE Computer Society Press,2016.3990-3994.
[6] Wang Y,Wang H J,Li C.Methods of target motion estimation for AUV target tracking[A].2016 IEEE International Conference on Mechatronics and Automation[C].Los Alamitos:IEEE Computer Society Press,2016.2139-2144.
[7] 陈婧,孙玉娟,周万军.融合运动模型与联合置信度量的改进核相关跟踪算法[J].红外技术,2018,40(11):1106-1111. Chen J,Sun Y J,Zhou W J.An improved kernelized correlation tracking algorithm based on a joint confidence measurement and motion model[J].Infrared Technology,2018,40(11):1106-1111.(in Chinese)
[8] 廖家才,曹立波,夏家豪.基于核相关滤波和运动模型的多目标轨迹跟踪[J].汽车工程,2019,41(10):1179-1188. Liao J C,Cao L B,Xia J H.Multi-target trajectory racking based on kernelized correlation filtering and motion model[J].Automotive Engineering,2019,41(10):1179-1188.(in Chinese)
[9] 程熙.基于深度图像的室内移动机器人行人跟随[D].长沙:湖南大学,2018. Chen X.Pedestrian following method for indoor mobile robot based on depth image[D].Changsha:Hunan University,2018.(in Chinese)
[10] Li Y,Ding S,Zhai Q.Human feet tracking guided by locomotion model[A].2015 International Conference on Robotics & Automation[C].Los Alamitos:IEEE Computer Society Press,2015.2424-2429.
[11] 闫培亮.基于相关滤波的目标跟踪算法研究[D].西安:西安电子科技大学,2019. Yan P L.Research on Object Tracking Algorithm Based on Correlation Filtering[D].Xi'an:Xidian University,2019.(in Chinese)
[12] Kiani G H,Sim T,Lucey S.Correlation filters with limited boundaries[A].IEEE Conference on Computer Vision and Pattern Recognition[C].Los Alamitos:IEEE Computer Society Press,2015.4630-4638.
[13] 刘海峰,孙成,梁星亮.自适应特征融合与抗遮挡的相关滤波跟踪算法[J/OL].激光与光电子学进展,http://kns.cnki.net/kcms/detail/31.1690.TN.20191217.1448.026.html,2019-12-11. Liu H F,Sun C,Liang X L.Correlation filter tracking algorithm with adaptive feature fusion and anti-occlusion[J/OL].Laser & Optoelectronics Progress,http://kns.cnki.net/kcms/detail/31.1690.TN.20191217.1448.026.html,2019-12-11.(in Chinese)
[14] Galoogahi H K,Fagg A,Lucey S.Learning background-aware correlation filter for visual tracking[A].2017 International Conference on Computer Vision[C].Los Alamitos:IEEE Computer Society Press,2017.1144-1152.
[15] Li Y,Zhu J.A scale adaptive kernel correlation filter tracker with feature integration[A].European Conference on Computer Vision[C].Heidelberg:Springer Press,2015.254-265.
[16] Lentin Joseph.Mastering ROS for Robotics Programming[M].Birmingham:Packt Publishing,2015.

运动模型引导的自适应核相关目标跟踪方法

Adaptive Response Kernel Correlation Target Tracking Method Guided by Motion Model

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	李豪, 袁广林, 秦晓燕, 琚长瑞, 朱虹. 基于空间加权对数似然比相关滤波与Deep Snake的目标轮廓跟踪[J]. 电子学报, 2023, 51(1): 105-116.
[2]	陈震, 倪晶晶, 张聪炫, 葛利跃, 王梓歌. 基于金字塔块匹配的双目场景流估计[J]. 电子学报, 2022, 50(9): 2164-2171.
[3]	谢青松, 刘晓庆, 安志勇, 李博. 基于前景优化的视觉目标跟踪算法[J]. 电子学报, 2022, 50(7): 1558-1566.
[4]	侯利明, 连峰, 谭顺成, 徐从安. 闪烁噪声统计特性未知情况下的鲁棒广义标签多伯努利滤波器[J]. 电子学报, 2021, 49(7): 1346-1353.
[5]	罗大鹏, 杜国庆, 曾志鹏, 魏龙生, 高常鑫, 陈应, 肖菲, 罗琛. 基于少量样本学习的多目标检测跟踪方法[J]. 电子学报, 2021, 49(1): 183-191.
[6]	马少雄, 邱实, 唐颖, 张晓. 基于工地场景的深度学习目标跟踪算法[J]. 电子学报, 2020, 48(9): 1665-1671.
[7]	田增山, 廉颖慧, 周牧, 李泽, 金悦. 基于Wi-Fi多维参数特征的无源目标跟踪技术[J]. 电子学报, 2020, 48(8): 1572-1579.
[8]	陈辉, 贺忠良, 邓东明, 李国财. 高斯混合多伯努利滤波器基于柯西施瓦兹散度的传感器控制方法[J]. 电子学报, 2020, 48(4): 706-716.
[9]	叶瑾, 许枫, 杨娟, 王佳维. 一种基于多传感器的复合量测IMM-EKF数据融合算法[J]. 电子学报, 2020, 48(12): 2326-2330.
[10]	王树亮, 毕大平, 阮怀林, 杜明洋, 潘继飞. 基于信息熵准则的认知雷达机动目标跟踪算法[J]. 电子学报, 2019, 47(6): 1277-1284.
[11]	陈辉, 贺忠良, 连峰, 黎慧波. 基于高斯混合多目标滤波器的传感器控制策略[J]. 电子学报, 2019, 47(3): 521-530.
[12]	李姝怡, 程婷. 基于量测转换IMM的多普勒雷达机动目标跟踪[J]. 电子学报, 2019, 47(3): 538-544.
[13]	张浩为, 谢军伟, 葛佳昂, 宗彬锋, 路文龙. 基于波形调度的机动目标跟踪算法[J]. 电子学报, 2019, 47(3): 560-567.
[14]	戴忠华, 周穗华, 张宏欣, 单珊. 初值自适应的磁性目标跟踪方法[J]. 电子学报, 2019, 47(12): 2457-2464.
[15]	查宇飞, 吴敏, 库涛, 陈兵, 张园强. 基于位置敏感模型的深度跟踪算法研究[J]. 电子学报, 2019, 47(10): 2076-2082.