基于双模型竞争机制的目标跟踪算法

Object Tracking Algorithm Based on Dual-Model Competition Mechanism

为解决背景感知相关滤波器存在的特征表达能力不足和模型漂移问题,本文提出了一种基于双模型竞争机制的目标跟踪算法.一方面,本文基于颜色和梯度信息设计了一种简单高效的特征描述子,以实现更鲁棒的目标表观建模.另一方面,本文分别构建初始模型和变化模型作用于目标搜索区域,并根据两者的跟踪响应图置信度来决定跟踪结果 .跟踪过程中,随着双模型主导地位不断地动态切换,变化模型也被赋予了可逆向学习的能力,从而达到缓解模型漂移的效果.实验结果表明,相比于基准算法,本文算法在OTB2015、TinyTLP和UAV20L三个数据集的跟踪精度分别提升5.0%、1.3%和4.1%,跟踪成功率分别提升3.8%、2.8%和1.7%,且在对不同跟踪场景实现稳定跟踪的同时能够保持25.5 fps的实时跟踪速度.

To solve the problems of insufficient feature expression ability and model drift in the background-aware correlation filters,this paper proposes an object tracking algorithm based on a dual-model competition mechanism.On the one hand,a simple and efficient feature descriptor that integrates color and gradient information is designed to achieve more robust target appearance modeling.On the other hand,we construct two filter models to describe the object's initial appear-ance and its variations,and then apply them to the target searching area respectively.The tracking results are determined by the confidence of the tracking response maps corresponding to these two models.During the tracking process,with the dy-namic switching of the dominant position of the two models,the filter model for adapting to object variations is also en-dowed with the ability of reversible learning to alleviate the model drift.The experimental results show that,compared with the baseline tracker,the tracking precision of the proposed algorithm on OTB2015,TinyTLP and UAV20L datasets is im-proved by 5.0%,1.3%and 4.1%,and the tracking success rate is improved by 3.8%,2.8%and 1.7%.The proposed algo-rithm can also achieve stable tracking performance for different tracking scenarios while maintaining a running speed of 25.5 fps.