瞿中,赵从梅.一种抗遮挡的自适应尺度目标跟踪算法[J].计算机科学,2018,45(4):296-300
一种抗遮挡的自适应尺度目标跟踪算法
Anti-occlusion Adaptive-scale Object Tracking Algorithm
投稿时间:2017-03-23  修订日期:2017-06-16
DOI:10.11896/j.issn.1002-137X.2018.04.050
中文关键词:  目标跟踪,随机蕨丛,多尺度,相关滤波器,CN颜色空间
英文关键词:Object tracking,Random fern,Multi-scale,Correlation filter,CN colour space
基金项目:本文受重庆市高校优秀成果转化资助
作者单位
瞿中 重庆邮电大学计算机科学与技术学院 重庆400065 
赵从梅 重庆邮电大学计算机科学与技术学院 重庆400065 
摘要点击次数: 249
全文下载次数: 224
中文摘要:
      在处理尺度变化和目标遮挡方面,利用相关滤波器的不同特征进行目标跟踪仍然存在问题。提出了一种基于随机蕨丛检测器的多尺度核相关滤波器算法。该算法将跟踪任务分解为目标尺度估计和位移估计,同时将CN颜色特征和HOG特征进行响应融合,进一步提高了整体跟踪性能。此外,文中训练了一个在线随机蕨分类器,在目标丢失后其能重新获取目标。与KCF,DSST,TLD,MIL,CT共5种算法相比,所提算法不仅能够准确地估计目标状态,而且可以有效处理目标的遮挡问题。
英文摘要:
      There are still some problems in the aspect of handling scale and object occlusion by using different features of correlation filter to perform object tracking.In this paper,a multi-scale kernel correlation filter algorithm based on random fern detector was proposed.The tracking task was decomposed into the target scale estimation and the translation estimation.At the same time,the CN colour feature and HOG feature were fused in response level to further improve the overall tracking performance of the algorithm.In addition,an online random fern classifier was trained to reob-tain the target after the target was lost.By comparing with KCF,DSST,TLD, MIL and CT algorithms,it is proved that the proposed method can accurately estimate target status and effectively deal with the occlusion problem.
查看全文  查看/发表评论  下载PDF阅读器