CAJ | 학술논문

为提高视频人体行为识别的性能，提出了一种分层建模行为的方法。该分层模型根据人体运动的属性概述不同时空域的行为内容。首先，利用时间梯度并结合连贯的运动模式约束提取稳定、密集的运动特征作为点特征；然后，采用自适应尺度核的 mean-shift 聚类算法标定这些特征。具有同一标签的特征组通过最大池运算产生身体部分表示后，累积大尺度的视频体内视觉词响应作为视频对象的表示。在基准的 KTH 和UCF-sports 行为数据库上，实验结果表明所提方法增强了行为特征的代表性和判别能力，同时提高了识别率。与其他相关文献相比，所提方法获得了优越的识别性能。
위제고시빈인체행위식별적성능，제출료일충분층건모행위적방법。해분층모형근거인체운동적속성개술불동시공역적행위내용。수선，이용시간제도병결합련관적운동모식약속제취은정、밀집적운동특정작위점특정；연후，채용자괄응척도핵적 mean-shift 취류산법표정저사특정。구유동일표첨적특정조통과최대지운산산생신체부분표시후，루적대척도적시빈체내시각사향응작위시빈대상적표시。재기준적 KTH 화UCF-sports 행위수거고상，실험결과표명소제방법증강료행위특정적대표성화판별능력，동시제고료식별솔。여기타상관문헌상비，소제방법획득료우월적식별성능。
To improve the recognition performance of video human actions,an approach that models the video actions in a hierarchical way is proposed. This hierarchical model summarizes the action contents with different spatio-temporal domains according to the properties of human body movement.First,the temporal gradient combined with the constraint of coherent motion pattern is utilized to extract stable and dense motion features that are viewed as point features,then the mean-shift clustering algorithm with the adaptive scale kernel is used to label these features.After pooling the features with the same label to generate part-based representation,the visual word responses within one large scale volume are collected as video object representation.On the benchmark KTH(Kungliga Tekniska H?gskolan)and UCF (University of Central Florida)-sports action datasets,the experimental results show that the proposed method enhances the representative and discriminative power of action features, and improves recognition rates.Compared with other related literature,the proposed method obtains superior performance.