基于置信区域内多级动态层表达的类贯序蒙特卡洛视觉跟踪方法

doi:10.3969/j.issn.0372-2112.2016.06.014

电子学报 ›› 2016, Vol. 44 ›› Issue (6): 1355-1361.DOI: 10.3969/j.issn.0372-2112.2016.06.014

基于置信区域内多级动态层表达的类贯序蒙特卡洛视觉跟踪方法

宋涛, 李鸥, 刘广怡

信息工程大学信息系统工程学院, 河南郑州 450002

收稿日期:2014-10-30 修回日期:2015-03-23 出版日期:2016-06-25
- 作者简介:
- 宋涛男,1983年9月出生于河南省焦作市.现为解放军信息工程大学信息系统工程学院博士研究生.主要研究方向为计算机视觉和目标跟踪技术.E-mail:taosong_1983@126.com;李鸥男,1961年出生于河南省郑州市.现为解放军信息工程大学信息系统工程学院教授、博士生导师.主要研究方向为无线通信网络、信息融合和目标跟踪技术.E-mail:zzliou@126.com
- 基金资助:
- 国家科技重大专项 (No.2014ZX03006003)

Quasi-Sequential Monte Carlo Visual Tracking Based on Multilevel Dynamic Layer Representations in Confidence Region

SONG Tao, LI Ou, LIU Guang-yi

Institute of Information System Engineering, Information Engineering University, Zhengzhou, Henan 450002, China

Received:2014-10-30 Revised:2015-03-23 Online:2016-06-25 Published:2016-06-25
- Supported by:
- National Science and Technology Major Project of the Ministry of Science and Technology (No.2014ZX03006003)

摘要/Abstract

摘要：

视觉跟踪是智能监控、机器人和视觉导航等领域的核心技术.针对现有类贯序蒙特卡洛跟踪方法复杂度高、实时性差的问题,本文提出了一种融合置信区域内多级动态层表达的跟踪方法,采用更加可靠、有效的粒子模拟状态后验概率.该方法利用检测模块得到目标可能出现的置信区域,根据真实目标尺寸给出一种粒子采样策略,每个粒子代表一级动态层表达,并为每个粒子建立双层运动模型;构建Mean-Shift分块观测模型以引入空间和外观信息,同时根据子块的匹配程度计算粒子权值、检测目标遮挡状态并提出模型更新策略.在公开视频序列上同经典粒子滤波和Mean-Shift等算法的实验对比结果证明了本文算法具有较优的跟踪准确度和实时性.

关键词: 视觉跟踪, 置信区域, 双层多级运动模型, 分块观测模型, 模型更新

Abstract:

Visual tracking is a core technology for the application domains of intelligent monitoring, robotics and vision navigation, etc.Aiming at the problem of high complexity and poor real-time performance in the existing quasi-sequential Monte Carlo tracking algorithms, this paper presents a method based on multilevel dynamic layer representations, which simulates the posteriori probability of a state using more reliable and effective particles.Then a sampling strategy is proposed in confidence areas derived from the detector, in which each particle represents a dynamic representation and has a two-layer motion model.The observation model based on parted-mean-shift is constructed for space and appearance information.Depending on the degree of matching sub-blocks, the weight of particles is calculated and a way to detect the occlusion state of an object is put forward for realtime model update.Experimental results using challenging public video sequences show better accuracy and efficiency of the proposed method, compared with the classical particle filter and mean-shift algorithms, etc.

Key words: visual tracking, confidence region, two-layer multilevel motion model, block-based observation model, model update

中图分类号:

TP319

宋涛, 李鸥, 刘广怡. 基于置信区域内多级动态层表达的类贯序蒙特卡洛视觉跟踪方法[J]. 电子学报, 2016, 44(6): 1355-1361.

SONG Tao, LI Ou, LIU Guang-yi . Quasi-Sequential Monte Carlo Visual Tracking Based on Multilevel Dynamic Layer Representations in Confidence Region[J]. Acta Electronica Sinica, 2016, 44(6): 1355-1361.

参考文献

[1] Xue J,Zheng N,Geng J.Tracking multiple visual targets via particle-based belief propagation[J].IEEE Transactions on SMC,Part B,2008,38(1):196-209.
[2] Matej K,Stanislav K.A two-stage dynamic model for visual tracking[J].IEEE Transactions on SMC,Part B,2010,40(6):1505-1520.
[3] Han H,Ding Y S,Hao K R.An evolutionary particle filter with immune genetic algorithm for intelligent video target tracking[J].Computer & Mathematics with Applications,2011,62(7):2685-2695.
[4] Chang C,Ansari R.Kernel particle filter for visual tracking[J].IEEE Signal Processing Letters,2005,12:242-245.
[5] Comaniciu D,Meer P.Mean shift:A robust approach toward feature space analysis[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(5):603-619.
[6] Comaniciu D,Ramesh V,Meer P.Kernel-based object tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(5):564-577.
[7] Cong D T,Septier F,Garnier C,et al.Robust visual tracking via MCMC-based particle filter[A].IEEE International Conference on Acoustics,Speech and Signal Processing[C].Kyoto:IEEE Press,2012.1493-1496.
[8] Brown J A,Capson D W,Member S.A framework for 3D model-based visual tracking using a GPU-accelerated particle filter[J].IEEE Transactions on Visualization and Computer Graphics,2012,18(1):68-80.
[9] Anderson C,Bert P,Vander W.Change detection and tracking using pyramids transformation techniques[A].Proceedings of SPIE Conference on Intelligent Robots and Computer Vision[C].Cambridge MA:Elsevier Press,1985.72-78.
[10] Wang L F,Yan H P,Wu H Y.Forward-backward mean-shift for visual tracking with local-background-weighted histogram[J].IEEE Transactions on Intelligent Transportation Systems,2013,14(3):1480-1489.
[11] Zhou L,Huang K,Tan T.Foreground object detection using top-down information based on EM framework[J].IEEE Transactions on Image Processing,2012,21(9):4204-4217.
[12] Gay-Bellile V,Bartoli A,Sayd P.Direct estimation of non-rigid registrations with image-based self-occlusion reasoning[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(1):87-104.
[13] Isard M,Blake A.Condensation-conditional density propagation for visual tracking[J].International Journal of Computer Vision,1998,29(1):5-28.
[14] Zhang X,Hu W,Bao H.Robust head tracking based on multiple cues fusion in the kernel-Bayesian framework[J].IEEE Transactions on Circuits and Systems for Video Technology,2013,23(7):1197-1208.

基于置信区域内多级动态层表达的类贯序蒙特卡洛视觉跟踪方法

Quasi-Sequential Monte Carlo Visual Tracking Based on Multilevel Dynamic Layer Representations in Confidence Region

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 14

编辑推荐

Metrics

[1]	仇祝令, 查宇飞, 吴敏, 王青. 基于注意力学习的正则化相关滤波跟踪算法[J]. 电子学报, 2020, 48(9): 1762-1768.
[2]	蒲磊, 冯新喜, 侯志强, 余旺盛. 基于二阶池化网络的鲁棒视觉跟踪算法[J]. 电子学报, 2020, 48(8): 1472-1478.
[3]	金泽芬芬, 侯志强, 余旺盛, 王鑫, 寇人可. 基于量子遗传算法的视觉目标跟踪[J]. 电子学报, 2020, 48(8): 1493-1501.
[4]	蒲磊, 冯新喜, 侯志强, 查宇飞, 余旺盛. 基于深度空间正则化的相关滤波跟踪算法[J]. 电子学报, 2020, 48(10): 2025-2032.
[5]	范舜奕, 管桦, 侯志强, 余旺盛, 戴铂. 基于多表观特征子模型更新的鲁棒视觉跟踪[J]. 电子学报, 2018, 46(2): 440-446.
[6]	孙巧, 张胜修, 张正新, 曹立佳, 李小锋. 基于加权重叠率的单目标视觉跟踪评价指标[J]. 电子学报, 2017, 45(3): 753-761.
[7]	宋涛, 李鸥, 刘广怡, 崔弘亮. 基于改进协作目标外观模型的在线视觉跟踪[J]. 电子学报, 2017, 45(2): 384-393.
[8]	余旺盛, 李卫华, 侯志强. 分层结构直方图及其应用[J]. 电子学报, 2017, 45(11): 2617-2624.
[9]	薛模根, 朱虹, 袁广林. 在线鲁棒判别式字典学习视觉跟踪[J]. 电子学报, 2016, 44(4): 838-845.
[10]	袁广林, 薛模根. 基于主分量寻踪的鲁棒视觉跟踪[J]. 电子学报, 2015, 43(3): 417-423.
[11]	余旺盛, 田孝华, 侯志强, 查宇飞. 基于局部分块学习的在线视觉跟踪[J]. 电子学报, 2015, 43(1): 74-78.
[12]	余旺盛, 田孝华, 侯志强, 黄安奇, 刘翔. 基于关键区域特征匹配的视觉跟踪算法[J]. 电子学报, 2014, 42(11): 2150-2156.
[13]	余旺盛, 侯志强, 田孝华. 基于旋转不变直方图的快速匹配穷搜索[J]. 电子学报, 2012, 40(11): 2177-2182.
[14]	李宏友;汪同庆;叶俊勇;蒋昀. 基于3D OGHM的视频运动目标检测算法[J]. 电子学报, 2008, 36(3): 604-608.