基于自适应搜索范围调整的视觉目标跟踪  

Visual Object Tracking Based on Adaptive Search Range Adjustment

作　　者：王超 王凯 WANG Chao;WANG Kai(School of Information and Electrical Engineering,Hebei University of Engineering,HeBei,Handan 056000,China;Hebei Key Laboratory of Security&Protection Information Sensing and Processing,HeBei,Handan 056000,China)

机构地区：[1]河北工程大学信息与电气工程学院,河北邯郸056038 [2]河北省安防信息感知与处理重点实验室,河北邯郸056000

出　　处：《计算机科学》2023年第S02期168-173,共6页Computer Science

基　　金：国家自然科学基金(62071071);邯郸市科技计划项目(21422031251)。

摘　　要：当前主流的视觉目标跟踪算法检测目标时,其搜索范围是以前一帧目标位置为中心设定的。然而目标可能由于运动而偏离设定的搜索中心,其在当前帧的检测响应易受到余弦窗惩罚机制的抑制,导致跟踪失败。为解决上述问题,提出了自适应搜索范围调整(Adaptive Search Range Adjustment,ASRA)方法。该方法采用了基于循环神经网络的运动预测模型来预测当前帧目标位置,并与相关滤波响应相结合来对搜索中心进行调整,进一步根据目标的运动矢量对搜索范围尺寸进行调整。将ASRA方法应用于当前先进的基于孪生网络的目标跟踪算法,在OTB2015和VOT2018数据集上进行的实验结果表明ASRA方法可以改善跟踪算法的准确率和鲁棒性。The mainstream visual object tracking algorithms generally set the position of object that tracked in the last frame as the center of a search range,which is used to detect the object in current frame.However,the tracking object may deviate from the center of search range due to its motion,thus its detection response in current frame can be easily inhibited by the cosine window penalty mechanism,which leads to tracking failure.To solve this problem,an adaptive search range adjustment(ASRA)method is proposed.In this method,a motion prediction model based on recurrent neural network(RNN)is used to predict the object position in current frame,and it is combined with the correlation filtering response to adjust the center of search range.The size of search range is further adjusted according to the motion vector of the tracking object.The proposed ASRA method is applied to current state-of-the-art object tracking algorithms based on Siamese networks.Experiments on OTB2015 and VOT2018 datasets show that ASRA can improve the accuracy and robustness of these algorithms.

关 键 词：视觉目标跟踪 搜索范围 运动预测 相关滤波 孪生网络 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]