基于双分支在线优化和特征融合的视频目标跟踪算法  

Video object tracking algorithm based on dual-branch online optimization and feature fusion

作　　者：李新鹏 王鹏[1] 李晓艳[1] 孙梦宇 陈遵田[2] 郜辉[1] LI Xinpeng;WANG Peng;LI Xiaoyan;SUN Mengyu;CHEN Zuntian;GAO Hui(School of Electronics and Information Engineering,Xi′an Technological University,Xi′an 710021,China;Xi′an Institute of Electromechanical Information Technology,Xi′an 710065,China)

机构地区：[1]西安工业大学电子信息工程学院,陕西西安710021 [2]西安机电信息技术研究所,陕西西安710065

出　　处：《液晶与显示》2024年第8期1079-1089,共11页Chinese Journal of Liquid Crystals and Displays

基　　金：国家自然基金(No.62171360);陕西省科技厅重点研发计划(No.2024GX-YBXM-162);陕西省电子设备智能测试与可靠性评估工程技术研究中心项目(2023-ZC-GCZX-0047);2022年度陕西高校青年创新团队项目;山东省智慧交通重点实验室(筹)项目;2023年陕西省高校工程研究中心项目;西安市军民两用智能测评技术重点实验室项目。

摘　　要：针对D3S算法对跟踪目标的判别能力不足的问题,提出了一种基于双分支在线优化和特征融合的视频目标跟踪算法。首先,构建双分支的在线优化分类器,实现对目标的二次定位,得到更准确的目标位置响应图;然后,在特征层上实现响应图与搜索特征的融合,并通过encoder模块促进融合过程,进一步突出跟踪目标的特征;最后,通过encoder模块实现模板特征的更新,拟合特征间的差异,提高分割模块的判别能力。在VOT2018和UAV123数据集进行实验,改进后算法与原算法相比,在VOT2018数据集上EAO提高了2.9%,在UAV123数据集上成功率提高了2.4%,准确率提高了2.9%。实验结果表明,本文方法提高了算法的判别能力,并且进一步提升了精度和鲁棒性。In response to the issue of inadequate discrimination capability in the D3S algorithm for tracking target,a video object tracking algorithm based on dual-branch online optimization and feature fusion is proposed.Firstly,a dual-branch online optimization classifier is constructed,which achieves secondary location of the target,resulting in a more accurate target position response map.Secondly,the fusion of the response map and search features is realized on the feature layer,and the encoder module promotes the fusion process,further highlighting the features of tracking target.Finally,by updating the template features with the encoder module,the differences between features are fitted,thereby enhancing the discriminative capability of the segmentation module.Experimental evaluations are conducted on the VOT2018 and UAV123 datasets.Compared with the original algorithm,the improved algorithm improves EAO by 2.9%on the VOT2018 dataset,increases success rate by 2.4%and accuracy by 2.9%on the UAV123 dataset.The experimental results demonstrate that the method in this paper improves the algorithm’s discriminative ability and further improves accuracy and robustness.

关 键 词：视频目标跟踪 目标分割 在线优化 特征融合 注意力机制 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]