抗遮挡和模糊的平面目标鲁棒追踪算法研究  

Research on Robust Tracking Algorithm for Planar Object Against Occlusion and Blur

作　　者：方晗 姚剑[1,2] FANG HanYAO Jian(School of Remote Sensing and Information Engineering,Wuhan University,Wuhan 430079,China;AI Application and Innovation Research Center,The Open University of Guangdong,Guangzhou 510091,China)

机构地区：[1]武汉大学遥感信息工程学院,湖北武汉430079 [2]广东开放大学人工智能应用创新研究中心,广东广州510091

出　　处：《测绘地理信息》2024年第5期33-37,共5页Journal of Geomatics

基　　金：国家自然科学基金(42271445);深圳市科技计划资助(JCYJ20220530140618040);深圳市中央引导地方科技展专项资金资助(2021Szvup100)

摘　　要：本文提出一种基于渲染的数据生成方式,可模拟相机运动导致的运动模糊、散焦模糊等效果,并由此构建了一个新的数据集,以支持平面目标追踪算法的研究。此外,基于图像光流和平面掩码多任务学习,提出一种新的平面目标追踪模型。具体来说,该方法通过估计的平面掩码剔除背景和遮挡干扰,筛选出可靠的稠密光流估计,以提高追踪算法的鲁棒性。通过在公共数据集和补充数据上进行验证,该算法精度和鲁棒性都有所提升,同时在模糊、遮挡以及纹理缺乏等情况下都可进行有效追踪。This paper proposes a rendering-based data generation method that can simulate motion blur,defocus blur and other effects caused by camera movement,and builds a new data set based on this to support the research of planar target tracking algorithms.In addition,this new planar object tracking model based on image optical flow and planar mask multitask learning.Specifically,the method eliminates background and occlusion interference through the estimated plane mask,and screens out reliable dense optical flow estimates to im-prove the robustness of the tracking algorithm.The application of the planar target tracking algorithm on public datasets and supplementary data reveals that its accuracy and robustness improve,and it can be effectively tracked under conditions such as blur,occlusion,and lack of texture.

关 键 词：平面目标追踪 光流估计 掩码估计 数据集构建 

分 类 号：P237[天文地球—摄影测量与遥感] TP391[天文地球—测绘科学与技术]