摘要
在粒子滤波框架下,提出了基于快速视网膜特征点(Fast Retina Keypoint,FREAK)和主成分-典型相关分析(Principal Component-Canonical Correlation Analysis,P3CA)的目标跟踪算法.该文提出的基于FREAK的多模态运动模型提高了目标位置预测准确性,缩小了目标搜索空间.基于P3CA的外观模型利用图像子区域间的典型相关性衡量候选目标的优劣,解决了基于全局信息外观模型对遮挡敏感的问题;利用主成分分析在数据降维方面的优势,解决了典型相关分析用于跟踪存在的小样本问题,降低了计算开销.同时,P3CA在线更新算法使跟踪器可以更好地应对跟踪过程中目标外观变化.通过在多个具有挑战性的视频上与多种优秀算法对比实验表明,该文的方法可以很好地应对光照变化、遮挡、旋转以及复杂背景等问题.
We proposed a novel tracking algorithm based on the Fast Retina Keypoint（FREAK）and Principal Component-Canonical Correlation Analysis（P3CA）.The proposed FREAK-based multi-mode dynamic model improves the prediction accuracy of the object location,reduces the searching space.P3CA-based appearance model is more robust in handling occlusion than holistic information based appearance model due to the adoption of the canonical correlation between subpatches in an image,and the integration of principal component analysis（PCA）,which is very excellent in data dimension reduction,successfully solves the small sample size problem and reduces the computation cost in the generation of canonical correlation analysis（CCA）subspace.Meanwhile,the tracker can deal with the appearance variations with time thanks to the novel online updating method for P3 CA subspace.The comparison experimental results on several challenging video sequences demonstrate that our algorithm can cope with the appearance variations caused by illumination changes,occlusion,rotation and background clutters etc.and performs better than some state-of-the-art methods according to the tracking accuracy.
出处
《计算机学报》
EI
CSCD
北大核心
2015年第6期1188-1201,共14页
Chinese Journal of Computers
基金
国家自然科学基金(61175096
61300082)资助~~
关键词
目标跟踪
快速视网膜特征
主成分-典型相关分析
主成分分析
典型相关分析
object tracking
Fast Retina Keypoint
Principal Component-Canonical Correlation Analysis
principal component analysis
canonical correlation analysis
