Textual description of human activities by tracking head and hand motions
Textual description of human activities by tracking head and hand motions
复制标题
通过跟踪头部和手部运动对人类活动进行文字描述
DOI：
--
复制
发表时间：
2002
期刊：
影响因子：
--
通讯作者：
K. Fukunaga
中科院分区：
文献类型：
--
作者：
A. Kojima;Takeshi Tamura;K. Fukunaga
我们提出了一种通过跟踪人体皮肤区域：面部和手部区域来描述视频图像中人类活动的方法。为了稳健地检测出皮肤区域，利用Dempster-Shafer理论提取并整合了三种概率信息。将视频图像转换为文本描述的主要困难是弥合它们之间的语义鸿沟。通过将头部和手部运动的视觉特征与自然语言概念相关联，确定合适的句法成分，如动词、对象等，并将其翻译成自然语言。
We propose a method for describing human activities from video images by tracking human skin regions: facial and hand regions. To detect skin regions robustly, three kinds of probabilistic information are extracted and integrated using Dempster-Shafer theory. The main difficulty in transforming video images into textual descriptions is bridging the semantic gap between them. By associating visual features of head and hand motion with natural language concepts, appropriate syntactic components such as verbs, objects, etc. are determined and translated into natural language.