天津大学学报
天津大學學報
천진대학학보
JOURNAL OF TIANJIN UNIVERSITY SCIENCE AND TECHNOLOGY
2013年
10期
917-922
,共6页
鹿凯宁%孙琪%刘安安%杨兆选
鹿凱寧%孫琪%劉安安%楊兆選
록개저%손기%류안안%양조선
隐条件随机场%人体行为识别%Gist特征
隱條件隨機場%人體行為識彆%Gist特徵
은조건수궤장%인체행위식별%Gist특정
hidden conditional random field%human action recognition%Gist feature
提出了一种基于隐条件随机场的人体行为识别方法。首先,通过目标检测和目标跟踪提取图像序列中人体所在时空区域;其次,提取人体区域的 Gist 特征作为人体行为视觉描述子;最后,利用隐条件随机场模型对人体行为进行建模和识别。通过大规模试验证明了该方法的有效性,与其他方法的对比实验验证了该方法的优越性。
提齣瞭一種基于隱條件隨機場的人體行為識彆方法。首先,通過目標檢測和目標跟蹤提取圖像序列中人體所在時空區域;其次,提取人體區域的 Gist 特徵作為人體行為視覺描述子;最後,利用隱條件隨機場模型對人體行為進行建模和識彆。通過大規模試驗證明瞭該方法的有效性,與其他方法的對比實驗驗證瞭該方法的優越性。
제출료일충기우은조건수궤장적인체행위식별방법。수선,통과목표검측화목표근종제취도상서렬중인체소재시공구역;기차,제취인체구역적 Gist 특정작위인체행위시각묘술자;최후,이용은조건수궤장모형대인체행위진행건모화식별。통과대규모시험증명료해방법적유효성,여기타방법적대비실험험증료해방법적우월성。
This paper proposes a hidden conditional random field-based human action recognition method. First,the consecutive spatiotemporal region of human body is extracted by object detection and tracking. Then,the Gist feature is computed for each frame within the extracted spatiotemporal region to serve as visual characteristics. At last,the Hidden conditional random field classifier is constructed to model the visual transition within one human action se-quence. Large-scale experimental results demonstrate that the proposed method can recognize human action accurately and outperform the competing methods.