An Improved UPF Object Tracking Algorithm Based on Multi-Feature Fusion

Abstract

Abstract:

Abstract： To solve the robustness problem and poor use of the latest measurement information in object tracking with single feature, this paper proposed an improved UPF tracking algorithm based on multifeature fusion. First, the algorithm was improved by using the UPF algorithm with the scaled minimal skew simplex sampling strategy and the IKF algorithm. Then, the uncertain measurement method was adopted to fuse the color and texture features of the object and track the object with the framework of the improved algorithm. The simulation results show that the proposed algorithm improves the tracking accuracy, has a better effect on tracking the object under complex scenes accurately and tracks the occluded object effectively.

Key words: object tracking, scaled minimal skew simplex sampling, unscented particle filter(UPF) algorithm, iterated Kalman filter(IKF) algorithm； multiple features fusion, uncertainty measurement

CLC Number:

TP 391.41

LI Xiaoxu1,DAI Bin1,CAO Jie1,2. An Improved UPF Object Tracking Algorithm Based on Multi-Feature Fusion[J]. Journal of Shanghai Jiaotong University, 2014, 48(10): 1473-1478.

References

［1］侯志强，韩崇昭.视觉跟踪技术综述［J］. 自动化学报,2006, 32(4):603675.

HOU Zhiqiang, HAN Chongzhao. A survey of visual tracking［J］. Acta Automatica Sinica, 2006, 32(4):603675.

［2］Gordon N，Salmond，Smith A. Novel approach to nonlinear/nonGaussian Bayesian state estimation［J］. Proceeding of Institute Electric Engineering, 1993, 140(2):107113.

［3］胡振涛，潘泉，杨峰. 将粒子残差一致性度量的滤波算法用于纯方位被动跟踪［J］. 红外与毫米波学报, 2010,29(1): 7580.

HU Zhentao, PAN Quan, YANG Feng. Applying the filtering algorithm with particle residual consistency measure to bearingsonly passive tracking［J］. Journal of Infrared and Millimeter Waves, 2010,29(1): 7580.

［4］王晓,韩崇昭. 基于混合采样的多模型机动目标跟踪算法［J］. 自动化学报, 2013,39(7):11521156.

WANG Xiao, HAN Chongzhao. A multiple model particles filter for maneuvering target tracking based on composite sampling［J］. Acta Automatica Sinica, 2013,39(7):11521156.

［5］王慧斌,陈哲,王鑫,等. 基于随机有限集的UPFCPHD多目标跟踪［J］. 通信学报, 2012,33(12):147153.WANG Huibin, CHEN Zhe, WANG Xin,et al. Random finite sets based UPFCPHD multiobject tracking［J］. Journal on Communications, 2012,33(12):147153.

［6］程水英，余莉.迭代无味卡尔曼滤波器的算法实现与应用评价［J］. 系统工程与电子技术, 2011,33(11):25462553.

CHENG Shuiying, YU Li. Algorithm realization and its application evaluation of the iterated unscented Kalman filter［J］. Systems Engineering and Electronics, 2011,33(11):25462553.

［7］Julier S J. The scaled unscented transformation［C］∥Proceedings of the American Control Conference. Anchorage Alaska, USA: American Automatic Control Council,2002: 45554559.

［8］潘泉，杨峰，叶亮,等.一类非线性滤波器—UKF综述［J］. 控制与决策, 2005,20(5):481489.

PAN Quan, YANG Feng, YE Liang, et al. Survey of a king of nonlinear filtersUKF［J］.Control and Decision, 2005,20(5):481489.

［9］李鹏，宋申民，陈兴林，等. 基于迭代sigma点粒子滤波的再入目标跟踪［J］. 吉林大学学报(工学版), 2009, 39(6):15851589.

LI Peng, SONG Shenmin, CHEN Xinglin, et al. Iterative sigma point particle filter in target tracking on reentry［J］. Journal of Jilin University (Engineering and Technology Edition), 2009, 39(6):15851589.

［10］顾鑫，王海涛，汪凌峰，等.基于不确定性度量的多特征融合跟踪［J］. 自动化学报, 2011, 37(5):550559.

GU Xin, WANG Haitao, WANG Lingfeng, et al. Fusing multiple features for object tracking based on uncertainty measurement［J］. Acta Automatica Sinica, 2011, 37(5):550559.

［11］Fisher R. Caviar test case scenarios［DB/OL］.［20110915］(20131121).http://groups.inf.ed.ac.uk/vision/Caviar/Caviardata1/

[1]	CHEN Jiacheng (陈佳诚), LI Lin(李霖), YANG Xubo (杨旭波). Eﬃcient Online Vehicle Tracking for Real–Virtual Mapping Systems [J]. J Shanghai Jiaotong Univ Sci, 2021, 26(5): 598-606.
[2]	WANG Muyuan∗ (王木塬), WU Xiaodong (吴晓东). Multi-Object Tracking Strategy of Autonomous Vehicle Using Modiﬁed Unscented Kalman Filter and Reference Point Switching [J]. J Shanghai Jiaotong Univ Sci, 2021, 26(5): 607-614.
[3]	LU Jiahui (陆佳辉), CHEN Yimin* (陈一民), ZOU Yibo (邹一波), ZOU Guozhi (邹国志). Long-Term Tracking Based on Spatio-Temporal Context [J]. Journal of shanghai Jiaotong University (Science), 2017, 22(4): 504-512.
[4]	CHEN Dongyue,CHEN Zongwen. Meanshift Robust Object Tracking Based on Feature Saliency [J]. Journal of Shanghai Jiaotong University, 2013, 47(11): 1807-1812.
[5]	ZHANG Tie-Dong, WAN Lei, WANG Bo, ZENG Wen-Jing. Underwater Object Tracking Based on Improved Particle Filter [J]. Journal of Shanghai Jiaotong University, 2012, 46(06): 943-948.