A new hybrid tracking strategy based on Pulse Coupled Neural Network - 文章详情页

作者：

Jia, S. (Jia, S..) | Xu, T. (Xu, T..) | Dong, Z. (Dong, Z..) | Li, X. (Li, X..) | Zhang, P. (Zhang, P..)

收录：

Scopus

摘要：

Visual　object　tracking　is　a　fundamental　research　topic　in　computer　vision.　In　this　paper,　we　proposed　a　novel　hybrid　tracking　method　based　on　Pulse　Coupled　Neural　Network　(PCNN)　and　Multiple　Instance　Learning　(MIL).　Most　modern　trackers　may　be　inaccurate　when　the　training　samples　are　imprecise　which　causes　drift.　To　resolve　these　problems,　MIL　method　is　introduced　into　the　tracking　task,　which　can　alleviate　drift　to　some　extent.　However,　the　MIL　tracker　may　detect　the　positive　sample　that　is　less　important.　PCNN　is　different　from　traditional　artificial　neural　networks,　which　can　be　applied　in　many　image　processing　fields,　such　as　image　segmentation.　So,　the　PCNN　was　employed　as　sample　detector　which　can　know　the　most　important　sample　when　training　the　classifier.　Then,　a　more　robust　and　much　faster　tracker　is　proposed　to　approximately　maximize　the　bag　likelihood　function.　Empirical　results　on　a　large　set　of　sequences　demonstrate　the　superior　performance　of　the　proposed　approach　in　robustness,　stability　and　efficiency　to　state-of-　The-art　methods　in　the　literature.　©　2015　IEEE.

关键词：

hybrid tracking strategy; image segmentation; Multiple Instance Learning; PCNN; sliding window

作者机构：

[ 1 ] [Jia, S.]College of Electronic and Control Engineering, Beijing University of Technology, Beijing, 100124, China
[ 2 ] [Jia, S.]Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing, 100124, China
[ 3 ] [Jia, S.]Engineering Research Center of Digital Community, Ministry of Education, Beijing, 100124, China
[ 4 ] [Xu, T.]College of Electronic and Control Engineering, Beijing University of Technology, Beijing, 100124, China
[ 5 ] [Xu, T.]Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing, 100124, China
[ 6 ] [Xu, T.]Engineering Research Center of Digital Community, Ministry of Education, Beijing, 100124, China
[ 7 ] [Xu, T.]School of Mechanical and Electrical Engineering, Henan Institute of Science and Technology, Xinxiang, 453003, China
[ 8 ] [Dong, Z.]College of Electronic and Control Engineering, Beijing University of Technology, Beijing, 100124, China
[ 9 ] [Dong, Z.]Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing, 100124, China
[ 10 ] [Dong, Z.]Engineering Research Center of Digital Community, Ministry of Education, Beijing, 100124, China
[ 11 ] [Li, X.]College of Electronic and Control Engineering, Beijing University of Technology, Beijing, 100124, China
[ 12 ] [Li, X.]Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing, 100124, China
[ 13 ] [Li, X.]Engineering Research Center of Digital Community, Ministry of Education, Beijing, 100124, China
[ 14 ] [Zhang, P.]College of Electronic and Control Engineering, Beijing University of Technology, Beijing, 100124, China
[ 15 ] [Zhang, P.]Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing, 100124, China
[ 16 ] [Zhang, P.]Engineering Research Center of Digital Community, Ministry of Education, Beijing, 100124, China

通讯作者信息：

电子邮件地址：

查看成果更多字段

成果类型
所属机构

所有年份指定年份从至