基于卡尔曼滤波的多目标跟踪方法

doi:10.11896/j.issn.1002-137X.2018.08.045

摘要/Abstract

摘要： 针对视频多目标跟踪中由于目标间的遮挡、交错或目标漂移而导致跟踪失败的情况,提出一种基于卡尔曼滤波以及空间颜色直方图的遮挡预测跟踪算法。利用空间颜色直方图对目标进行建模,可以对不同目标进行区分进而在目标之间出现交错或目标漂移时仍能跟踪到目标。通过卡尔曼滤波算法可以预测目标的状态,对预测位置之间存在交错的目标进行遮挡标记,以便在下一帧中仍然可以跟踪到被遮挡的目标。采用2D MOT 2015数据集进行实验,跟踪的平均精度达到了34.1%。实验结果表明,所提方法对多目标跟踪的效果有所提高。

关键词: 多目标跟踪, 卡尔曼滤波, 空间颜色直方图, 遮挡预测

Abstract: Aiming at the tracking failure caused by occlusion between objects,interleaving or target drift in multi-object tracking,this paper proposed an occlusion prediction tracking algorithm based on Kalman filter and spatiograms.By combining the color histogram and the distribution of color in space,spatiograms can be used to distinguish different objects,so that the object can still be tracked when interleaving or occlusion between objects occurs.The state of the object can be predicted by the Kalman filtering algorithm.The occlusion mark is usedfor the object which overlaps with other objects,so that the occluded object which is undetected can be tracked in the next frame.The 2D MOT 2015 data set was used for experiment.The average accuracy of tracking achieves 34.1%.Experimental results show that the algorithm can improve the performance of multi-object tracking.

Key words: Kalman filter, Multi-object tracking, Occlusion prediction, Spatial color histogram

中图分类号:

TP391.41

赵广辉, 卓松, 徐晓龙. 基于卡尔曼滤波的多目标跟踪方法[J]. 计算机科学, 2018, 45(8): 253-257. https://doi.org/10.11896/j.issn.1002-137X.2018.08.045

ZHAO Guang-hui, ZHUO Song, XU Xiao-long. Multi-object Tracking Algorithm Based on Kalman Filter[J]. Computer Science, 2018, 45(8): 253-257. https://doi.org/10.11896/j.issn.1002-137X.2018.08.045

参考文献

[1]REN S,HE K,GIRSHICK R,et al.Faster R-CNN:towards realtime object detection with region proposal networks[C]∥International Conference on Neural Information Processing Systems.MIT Press,2015:91-99.
[2]HE K,ZHANG X,REN S,et al.Deep Residual Learning for Ima-ge Recognition[C]∥Computer Vision and Pattern Recognition.IEEE,2016:770-778.
[3]HOFMANN M,WOLF D,RIGOLL G.Hypergraphs for JointMulti-view Reconstruction and Multi-object Tracking[C]∥Computer Vision and Pattern Recognition.IEEE,2013:3650-3657.
[4]DICLE C,CAMPS O I,SZNAIER M.The Way They Move:Tracking Multiple Targets with Similar Appearance[C]∥IEEE International Conference on Computer Vision.IEEE,2014:2304-2311.
[5]KIM C,LI F,CIPTADI A,et al.Multiple Hypothesis Tracking Revisited[C]∥IEEE International Conference on Computer Vision.IEEE,2015:4696-4704.
[6]REZATOFIGHI S H,MILAN A,ZHANG Z,et al.Joint Probabilistic Data Association Revisited[C]∥IEEE International Conference on Computer Vision.IEEE,2015:3047-3055.
[7]BAE S H,YOON K J.Robust Online Multi-object TrackingBased on Tracklet Confidence and Online Discriminative Appearance Learning[C]∥IEEE Conference on Computer Vision and Pattern Recognition.IEEE Computer Society,2014:1218-1225.
[8]XIANG Y,ALAHI A,SAVARESE S.Learning to Track:Online Multi-object Tracking by Decision Making[C]∥IEEE International Conference on Computer Vision.IEEE,2015:4705-4713.
[9]BEWLEY A,GE Z,OTT L,et al.Simple online and realtime tracking[C]∥IEEE International Conference on Image Proces-sing.IEEE,2016:3464-3468.
[10]CHEN J G,QIN X S,MA L L.Fast GM-PHD Filter for Multi-target Tracking[J].Computer Science,2016,43(3):317-321.(in Chinese)陈金广,秦晓姗,马丽丽.快速多目标跟踪GM-PHD滤波算法[J].计算机科学,2016,43(3):317-321.
[11]JU H Y,YANG M H,LIM J,et al.Bayesian Multi-objectTracking Using Motion Context from Multiple Objects[C]∥Applications of Computer Vision.IEEE,2015:33-40.
[12]YANG M,JIA Y.Temporal Dynamic Appearance Modeling for Online Multi-Person Tracking[J].Computer Vision & Image Understanding,2015,31(9):626-633.
[13]BENFOLD B,REID I.Stable multi-target tracking in real-time surveillance video[C]∥Computer Vision and Pattern Recognition.IEEE,2011:3457-3464.
[14]KUHN H W.The Hungarian method for the assignment problem[J].Naval Research Logistics,2005,52(1):7-21.
[15]BREITENSTEIN M D,REICHLIN F,LEIBE B,et al.OnlineMultiperson Tracking-by-Detection from a Single,Uncalibrated Camera[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2011,33(9):1820-1833.
[16]YUAN D L,JI Q G.Multiple Object Tracking Algorithm via Collaborative Motion Status Estimation[J].Computer Science,2017,44(Z11):154-159.(in Chinese)袁大龙,纪庆革.协同运动状态估计的多目标跟踪算法[J].计算机科学,2017,44(Z11):154-159.
[17]BIRCHFIELD S T,RANGARAJAN S.Spatiograms versus Histograms for Region-Based Tracking[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition.IEEE,2005:1158-1163.
[18]CONAIRE C O,O’CONNOR N E,SMEATON A F.An Improved Spatiogram Similarity Measure for Robust Object Loca-lisation[J].IEEE International Conference on Acoustics,2007,1(4):1069-1072.
[19]YANG B,NEVATIA R.Online Learned Discriminative Part-Based Appearance Models for Multi-human Tracking[C]∥European Conference on Computer Vision.Springer-Verlag,2012:484-498.
[20]LEMENAGER E,BOUET T,BRAIBANT V.Kalman filterming:a new approach for building global approximations.Application to the inverse optimization of an explosively formed penetractor(EEP)[J].Structural Optimization,1997,14(2／3):158-164.

相关文章 15

[1]	沈祥培, 丁彦蕊. 多检测器融合的深度相关滤波视频多目标跟踪算法 Multi-detector Fusion-based Depth Correlation Filtering Video Multi-target Tracking Algorithm 计算机科学, 2022, 49(8): 184-190. https://doi.org/10.11896/jsjkx.210600004
[2]	史殿习, 刘聪, 佘馥江, 张拥军. GPS拒止环境下基于定位置信度的多无人机协同定位方法 Cooperation Localization Method Based on Location Confidence of Multi-UAV in GPS-deniedEnvironment 计算机科学, 2022, 49(4): 302-311. https://doi.org/10.11896/jsjkx.210200106
[3]	文成宇, 房卫东, 陈伟. 多目标跟踪的对象初始化综述 Object Initialization in Multiple Object Tracking:A Review 计算机科学, 2022, 49(3): 152-162. https://doi.org/10.11896/jsjkx.210200048
[4]	高枫越, 王琰, 朱铁兰. 有适应力的分布式状态估计方法 Resilient Distributed State Estimation Algorithm 计算机科学, 2021, 48(5): 308-312. https://doi.org/10.11896/jsjkx.200300117
[5]	刘彦, 秦品乐, 曾建朝. 基于YOLOv3与分层数据关联的多目标跟踪算法 Multi-object Tracking Algorithm Based on YOLOv3 and Hierarchical Data Association 计算机科学, 2021, 48(11A): 370-375. https://doi.org/10.11896/jsjkx.201000115
[6]	王秉洲, 王慧斌, 沈洁, 张丽丽. 基于自适应渐消UKF的FastSLAM算法 FastSLAM Algorithm Based on Adaptive Fading Unscented Kalman Filter 计算机科学, 2020, 47(9): 213-218. https://doi.org/10.11896/jsjkx.190700186
[7]	冯安琪, 钱丽萍, 欧阳金源, 吴远. 车联网络通过两级量化自适应卡尔曼滤波实现车辆状态预测 Vehicular Networking Enabled Vehicle State Prediction with Two-level Quantized AdaptiveKalman Filtering 计算机科学, 2020, 47(5): 230-235. https://doi.org/10.11896/jsjkx.190300155
[8]	张良成, 王运锋. 动态自适应的多雷达信息加权融合方法 Dynamic Adaptive Multi-radar Tracks Weighted Fusion Method 计算机科学, 2020, 47(11A): 321-326. https://doi.org/10.11896/jsjkx.2004000145
[9]	黄婷婷, 冯锋. 无线传感器网络异构数据融合模型优化研究 Study on Optimization of Heterogeneous Data Fusion Model in Wireless Sensor Network 计算机科学, 2020, 47(11A): 339-344. https://doi.org/10.11896/jsjkx.200100109
[10]	龚轩, 乐孜纯, 王慧, 武玉坤. 多目标跟踪中的数据关联技术综述 Survey of Data Association Technology in Multi-target Tracking 计算机科学, 2020, 47(10): 136-144. https://doi.org/10.11896/jsjkx.200200041
[11]	王宏霞,徐英婕,赵云波,张文安. 基于无偏线性最优估计的PET图像重建 PET Image Reconstruction Based on Unbiased Linear Optimal Estimation 计算机科学, 2020, 47(1): 165-169. https://doi.org/10.11896/jsjkx.181202329
[12]	胡海根, 周莉莉, 周乾伟, 陈胜勇, 张俊康. 基于CNN的相衬显微图像序列的癌细胞多目标跟踪 Multi-target Tracking of Cancer Cells under Phase Contrast Microscopic Images Based on Convolutional Neural Network 计算机科学, 2019, 46(5): 279-285. https://doi.org/10.11896/j.issn.1002-137X.2019.05.043
[13]	冯安琪, 钱丽萍, 黄玉蘋, 吴远. RFID环境下基于自适应卡尔曼滤波的高速移动车辆速度预测 RFID Data-driven Vehicle Speed Prediction Using Adaptive Kalman Filter 计算机科学, 2019, 46(4): 100-105. https://doi.org/10.11896/j.issn.1002-137X.2019.04.016
[14]	王正宁, 周阳, 吕侠, 曾凡伟, 张翔, 张锋军. 一种基于2D和3D联合信息的改进MDP跟踪算法 Improved MDP Tracking Method by Combining 2D and 3D Information 计算机科学, 2019, 46(3): 97-102. https://doi.org/10.11896/j.issn.1002-137X.2019.03.013
[15]	马林宏, 陈廷伟, 郝明, 张雷. 多线路信息融合的公交车行程时间预测算法 Bus Travel Time Prediction Algorithm Based on Multi-line Information Fusion 计算机科学, 2019, 46(11): 222-227. https://doi.org/10.11896/jsjkx.180901764

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed