计算机工程
計算機工程
계산궤공정
COMPUTER ENGINEERING
2010年
2期
189-191,200
,共4页
增量式子空间学习%增量式主成分分析%粒子滤波
增量式子空間學習%增量式主成分分析%粒子濾波
증량식자공간학습%증량식주성분분석%입자려파
incremental subspace learning%Incremental Principal Component Analysis(IPCA)%particle filtering
为了提高视觉跟踪方法在物体外观发生变化时的性能,提出一种基于增量式子空间学习的视觉跟踪系统.该系统利用基于增量式主成分分析的粒子滤波方法增量式地学习一个表示跟踪结果的低维特征空间,以反映目标物体的外观变化.实验结果表明,当目标物体在复杂环境中承受姿态和光照变化时,该视觉跟踪系统具有更好的性能.
為瞭提高視覺跟蹤方法在物體外觀髮生變化時的性能,提齣一種基于增量式子空間學習的視覺跟蹤繫統.該繫統利用基于增量式主成分分析的粒子濾波方法增量式地學習一箇錶示跟蹤結果的低維特徵空間,以反映目標物體的外觀變化.實驗結果錶明,噹目標物體在複雜環境中承受姿態和光照變化時,該視覺跟蹤繫統具有更好的性能.
위료제고시각근종방법재물체외관발생변화시적성능,제출일충기우증량식자공간학습적시각근종계통.해계통이용기우증량식주성분분석적입자려파방법증량식지학습일개표시근종결과적저유특정공간,이반영목표물체적외관변화.실험결과표명,당목표물체재복잡배경중승수자태화광조변화시,해시각근종계통구유경호적성능.
In order to enhance the performance of visual tracking methods with object appearance variation, this paper proposes an visual tracking system based on incremental subspace learning. By using particle filter method based on Incremental Principal Component Analysis(IPCA), this system incrementally learns a low dimensional eigenspace representation of the tracking results to reflect appearance variation of the target object. Experiments demonstrate that the system has better performance when the target objects undergo large pose and illumination changes in some complex environments.
