CAJ | 학술논문

在对动作运动过程探索中发现动作具有时间序列不变的特性，并利用这一特性提出了一种新的视角无关行为识别的方法。论文利用了时空特征，特征融合和时间顺序一致性约束来确保匹配过程中的时间顺序。首先从视频序列中提取时空特征点，并运用基于 PCA 和 LPP 算法特征融合技术将视角相同的相似点封装到一个类内。对于每一个动作类，构造一个特征融合表以便于在不同的视角进行特征匹配。匹配度是通过基于全局时间顺序约束条件和匹配特征的数量计算出来的。最后拥有最大匹配度的行为标签分配给要查询的动作。通过在 IXMAS 多视角数据库和西弗吉尼亚大学的行为数据库大量实验评估了该算法，实验结果表明，该方法在视角无关行为识别方面具有较高的准确性。
재대동작운동과정탐색중발현동작구유시간서렬불변적특성，병이용저일특성제출료일충신적시각무관행위식별적방법。논문이용료시공특정，특정융합화시간순서일치성약속래학보필배과정중적시간순서。수선종시빈서렬중제취시공특정점，병운용기우 PCA 화 LPP 산법특정융합기술장시각상동적상사점봉장도일개류내。대우매일개동작류，구조일개특정융합표이편우재불동적시각진행특정필배。필배도시통과기우전국시간순서약속조건화필배특정적수량계산출래적。최후옹유최대필배도적행위표첨분배급요사순적동작。통과재 IXMAS 다시각수거고화서불길니아대학적행위수거고대량실험평고료해산법，실험결과표명，해방법재시각무관행위식별방면구유교고적준학성。
The invariance property of temporal order of action instances is explored during action execution and it is uti‐lized for devising a new view‐invariant action recognition approach .To ensure temporal order during matching ,spatiotempo‐ral features ,feature fusion and temporal order consistency constraint are utilized .Start by extracting spatiotemporal cuboid features from video sequences and applying feature fusion based on PCA and LPP algorithm to encapsulate within‐class simi‐larity for the same viewpoints .For each action class ,a feature fusion table is constructed to facilitate feature matching across different views .An action matching score is then calculated based on global temporal order constraint and number of matc‐hing features .Finally ,the action label of the class with the maximum value of the matching score is assigned to the query ac‐tion .Experimentation is performed on multiple view Inria Xmas motion acquisition sequences and West Virginia University action datasets ,with encouraging results ,that are comparable to the existing view‐invariant action recognition techniques .