基于光流运动约束马尔可夫随机场改进模型的多目标跟踪算法  

Multi-Target Tracking Algorithm Based on Improved Markov Random Field Model of Optical Flow Motion Constraint

作　　者：牛宇辉 奚峥皓[1] 薛亚静[1] 陈健超 Niu Yuhui;Xi Zhenghao;Xue Yajing;Chen Jianchao(School of Electrical and Electronic Engineering,Shanghai University of Engineering Science,Shanghai 201620,China)

机构地区：[1]上海工程技术大学电子电气工程学院,上海201620

出　　处：《激光与光电子学进展》2022年第2期374-381,共8页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(61801286)。

摘　　要：多目标跟踪时目标之间的交互、部分遮挡或完全遮挡会造成跟踪准确度降低或目标的丢失等问题。针对这些问题,提出了一种融合光流法与马尔可夫随机场(MRF)的多目标跟踪算法。首先,利用首帧图像光流场提取出目标光流,得到目标的速度信息;其次,根据目标运动特性与已建立的MRF模型进行融合并约束优化;最后,在所提模型中,通过核相关滤波算法得到目标最优状态分布以实现对多个目标的跟踪。实验结果表明,与同类先进算法相比,所提算法在多目标交互之后,能够继续对目标进行准确跟踪,降低了目标彼此遮挡时的误报率,具有更优越的准确性。In multi-target tracking,the interaction between targets,partial occlusion or complete occlusion can cause degradation of tracking accuracy or loss of targets.To address these problems,a multi-target tracking algorithm that combines optical flow and Markov random field(MRF)is proposed.First,the target optical flow is extracted by using the optical flow field of the first frame image to obtain the velocity information of the target;then,the target motion characteristics are fused with the established MRF model and constrained to optimize;finally,in the proposed model,the optimal state distribution of the target is obtained by the kernel correlation filter algorithm to achieve the tracking of multiple targets.The experimental results show that,compared with similar advanced algorithms,the proposed algorithm can continue to accurately track targets after multi-target interaction,reduce the false alarm rate when targets are obscured by each other,and has superior accuracy.

关 键 词：机器视觉 多目标跟踪 马尔可夫随机场 光流场 遮挡 

分 类 号：TP29[自动化与计算机技术—检测技术与自动化装置]