\r田 丹1, 2,张国山1,孙申申\r2\r
\r
AuthorsHTML:\r田 丹1, 2,张国山1,孙申申\r2\r
\r
AuthorsListE:\rTian Dan1, 2,Zhang Guoshan 1,Sun Shenshen \r2\r
\r
AuthorsHTMLE:\rTian Dan1, 2,Zhang Guoshan 1,Sun Shenshen \r2\r
\r
Unit:\r\r1. 天津大学电气自动化与信息工程学院,天津 300072;\r
\r\r2. 沈阳大学信息工程学院,沈阳 110044\r
\r
\r
Unit_EngLish:\r1. School of Electrical and Informatin Engineering,Tianjin University,Tianjin 300072,China;
2. School of Information Engineering,Shenyang University,Shenyang 110044,China\r
\r
Abstract_Chinese:\r现有的低秩稀疏优化目标跟踪算法容易存在下述两方面问题:①需要求解大量l1 优化问题,计算复杂度高.②在目标突变运动情况下,经常出现跟踪漂移现象.为此,提出一种反向低秩稀疏约束下基于融合最小绝对值收缩和选择算子(Lasso)的目标跟踪算法.首先,建立目标表观的反向稀疏表示描述,利用候选粒子反向稀疏表示目标模板,将在线跟踪中l1 优化问题的数目由候选粒子数简化为1.其次,将融合Lasso 模型引入到目标跟踪建模中,约束表示系数差分的绝对值之和,保证表示系数稀疏性的同时,使其连续性差异亦稀疏.从而限制目标表观在相邻帧间具有较小差异,但允许个别帧间存在较大差异性,以适应目标的突变运动.再次,利用核范数凸近似低秩约束,限制目标表观的时域相关性,以适应目标的外观变化.实验结果表明,面向具有严重遮挡、光照和尺度变化、目标突变运动等挑战性的标准跟踪数据集,提出算法能完成复杂场景下的跟踪任务.与目前几种热点算法进行定性与定量分析比较,提出算法具有更高的跟踪精度和较快的跟踪速度,特别是在目标突变运动情况下具有更好的鲁棒性.\r
\r
Abstract_English:\rThe existing low-rank sparse optimization-based object tracking algorithms usually feature the following problems:① requirement for solutions to considerable optimization problems l1 and high computation complexity;② usually occurring drift phenomenon when facing object abrupt motion. Therefore,a fused least-absolute shrinkage and selection operator-based object tracking algorithm with inverse low-rank and sparse constraint is proposed. First,an inverse sparse representation formulation for object appearance is built using candidate particles to represent the target template inversely,simplifying the number of optimization problem l1 for online tracking from candidate particle number to one. Second,the fused Lasso model is introduced to the object tracking modeling to constraint the absolute value sum of the sparse coefficient difference,resulting in the sparse representation coefficient and continuity difference. This condition can restrict the object appearance with minimal difference between the consecutive frames but allow for the greater variation between the individual frames to adopt an abrupt motion. Third,the low-rank constraint based on the nuclear norm is used to restrain the temporal correlation of the objective appearance to adopt the appearance change. The experimental results show that when subjecting the benchmark tracking dataset to challenging situations under serious occlusion,illumination and scale variation,and object abrupt motion,the proposed algorithm can perform tracking in complicated scenes. Both qualitative and quantitative evaluations demonstrate that the proposed algorithm features higher precision and faster speed against other state-of-art algorithms,especially exhibiting better adaptability for object abrupt motion.\r
\r
Keyword_Chinese:目标跟踪;反向稀疏表示;低秩约束;融合Lasso;粒子滤波\r
Keywords_English:object tracking;inverse sparse representation;low-rank constraint;fused Lasso;particle filter\r
PDF全文下载地址:http://xbzrb.tju.edu.cn/#/digest?ArticleID=6377
删除或更新信息,请邮件至freekaoyan#163.com(#换成@)
反向低秩稀疏约束下的融合Lasso 目标跟踪算法\r\n\t\t
本站小编 Free考研考试/2022-01-16
相关话题/算法 目标
基于EM-EKF 算法的RLV 再入段气动参数辨识\r\n\t\t
窦立谦1,杜苗苗1,张秀云1,王跃萍2AuthorsHTML:窦立谦1,杜苗苗1,张秀云1,王跃萍2AuthorsListE:DouLiqian1,DuMiaomiao1,ZhangXiuyun1,WangYueping2AuthorsHTMLE: ...天津大学科研学术 本站小编 Free考研考试 2022-01-16基于改进模糊C均值算法的颈动脉超声图像分割
李锵,张琦珺,关欣,滕建辅AuthorsHTML:李锵,张琦珺,关欣,滕建辅AuthorsListE:LiQiang,ZhangQijun,GuanXin,TengJianfuAuthorsHTMLE:LiQiang,ZhangQijun,GuanXin,TengJianfuUnit:天津大学微电子 ...天津大学科研学术 本站小编 Free考研考试 2022-01-16联合TOA和DOA的浅海多径定位算法
刘开华1,魏冲冲1,于洁潇2AuthorsHTML:刘开华1,魏冲冲1,于洁潇2AuthorsListE:LiuKaihua1,WeiChongchong1,YuJiexiao2AuthorsHTMLE:LiuKaihua1,WeiChongchong1,YuJiexiao2Unit:1.天津大学微 ...天津大学科研学术 本站小编 Free考研考试 2022-01-16基于Adaboost的无源RFID射频层析成像伪目标识别
马永涛,高鑫AuthorsHTML:马永涛,高鑫AuthorsListE:MaYongtao,GaoXinAuthorsHTMLE:MaYongtao,GaoXinUnit:天津大学微电子学院,天津300072Unit_EngLish:SchoolofMicroelectronics,Tianjin ...天津大学科研学术 本站小编 Free考研考试 2022-01-16直线约束和不同相机间距的立体图像克隆算法
侯春萍1,刘琦1,阎维青2,王致芃1,陈天宇3AuthorsHTML:侯春萍1,刘琦1,阎维青2,王致芃1,陈天宇3AuthorsListE:HouChunping1,LiuQi1,YanWeiqing2,WangZhipeng1,ChenTianyu3AuthorsHTMLE:HouChunpin ...天津大学科研学术 本站小编 Free考研考试 2022-01-16浅滩掩埋管道横截面圆的声回波模型及定位算法
陈世利,谢思捷,曾周末AuthorsHTML:陈世利,谢思捷,曾周末AuthorsListE:ChenShili,XieSijie,ZengZhoumoAuthorsHTMLE:ChenShili,XieSijie,ZengZhoumoUnit:天津大学精密仪器测试技术及仪器国家重点实验室,天津30 ...天津大学科研学术 本站小编 Free考研考试 2022-01-16基于梯度域引导滤波的视差精炼迭代算法
朱程涛,李锵AuthorsHTML:朱程涛,李锵AuthorsListE:ZhuChengtao,LiQiangAuthorsHTMLE:ZhuChengtao,LiQiangUnit:天津大学微电子学院,天津300072Unit_EngLish:SchoolofMicroelectronics,T ...天津大学科研学术 本站小编 Free考研考试 2022-01-16基于极坐标系下二维直方图的图像分割算法
张军,张治恒,朱新山AuthorsHTML:张军,张治恒,朱新山AuthorsListE:ZhangJun,ZhangZhiheng,ZhuXinshanAuthorsHTMLE:ZhangJun,ZhangZhiheng,ZhuXinshanUnit:天津大学电气自动化与信息工程学院,天津3000 ...天津大学科研学术 本站小编 Free考研考试 2022-01-16基于SSIM的自适应样本块图像修复算法
何凯,牛俊慧,沈成南,卢雯霞AuthorsHTML:何凯,牛俊慧,沈成南,卢雯霞AuthorsListE:HeKai,NiuJunhui,ShenChengnan,LuWenxiaAuthorsHTMLE:HeKai,NiuJunhui,ShenChengnan,LuWenxiaUnit:天津大学电 ...天津大学科研学术 本站小编 Free考研考试 2022-01-16基于改进入侵杂草算法的有源配电网重构
石季英1,袁大玲1,薛飞2,马丽1,杨挺1AuthorsHTML:石季英1,袁大玲1,薛飞2,马丽1,杨挺1AuthorsListE:ShiJiying1,YuanDaling1,XueFei2,MaLi1,YangTing1AuthorsHTMLE:ShiJiying1,YuanDaling1,X ...天津大学科研学术 本站小编 Free考研考试 2022-01-16