计算机工程与应用
計算機工程與應用
계산궤공정여응용
COMPUTER ENGINEERING AND APPLICATIONS
2013年
21期
191-194
,共4页
视频检索%金字塔匹配%稀疏编码
視頻檢索%金字塔匹配%稀疏編碼
시빈검색%금자탑필배%희소편마
video retrieval%pyramid matching%sparse coding
针对金字塔匹配下的视频检索系统中基础特征用矢量量化方法表示不够精确的问题,结合稀疏编码方法进行视频检索。视频的基础特征通过稀疏编码表示后,用金字塔方法进行多次匹配,将多次匹配结果线性合并,作为修正后的相似性度量结果。通过对UCF50的检索实验表明,该方法能显著提高检索的准确率。
針對金字塔匹配下的視頻檢索繫統中基礎特徵用矢量量化方法錶示不夠精確的問題,結閤稀疏編碼方法進行視頻檢索。視頻的基礎特徵通過稀疏編碼錶示後,用金字塔方法進行多次匹配,將多次匹配結果線性閤併,作為脩正後的相似性度量結果。通過對UCF50的檢索實驗錶明,該方法能顯著提高檢索的準確率。
침대금자탑필배하적시빈검색계통중기출특정용시량양화방법표시불구정학적문제,결합희소편마방법진행시빈검색。시빈적기출특정통과희소편마표시후,용금자탑방법진행다차필배,장다차필배결과선성합병,작위수정후적상사성도량결과。통과대UCF50적검색실험표명,해방법능현저제고검색적준학솔。
This paper proposes an extended video indexing approach combined with the sparse coding method, in order to improve the accuracy for feature vector quantizing within pyramid matching, which has been widely applied in CBVR systems. Essential features of video sequence, extracted from the adjacent two frames, are coded by the sparse coding method previously, and then registered by the pyramid matching for several times, in order to produce slight different alignments. After that, these alignments between two frames are linearly combined to be the corrected similarity measurement. The experiment on UCF 50 shows the proposed method can greatly increase the accuracy of video retrieval task.