Automatic Annotation of Everyday Movements
Automatic Annotation of Everyday Movements
复制标题
DOI：
--
复制
发表时间：
2003-12
期刊：
影响因子：
--
通讯作者：
Deva Ramanan;D. Forsyth
中科院分区：
文献类型：
--
作者：
Deva Ramanan;D. Forsyth
本文介绍了一种系统，可以注释视频序列：每个演员的外观的描述;当演员在视图中;和演员的活动，而在视图中的表示。该系统不需要固定的背景，并且是自动的。该系统的工作原理是：（1）在2D中跟踪人，然后使用带注释的运动捕捉数据集，（2）合成与2D轨迹匹配的带注释的3D运动序列。使用描述日常运动的类结构离线手动注释3D运动捕获数据，并允许合成运动注释-例如，可以在跑步时跳跃。对真实的运动视频的描述表明，该方法是准确的。
This paper describes a system that can annotate a video sequence with: a description of the appearance of each actor; when the actor is in view; and a representation of the actor's activity while in view. The system does not require a fixed background, and is automatic. The system works by (1) tracking people in 2D and then, using an annotated motion capture dataset, (2) synthesizing an annotated 3D motion sequence matching the 2D tracks. The 3D motion capture data is manually annotated off-line using a class structure that describes everyday motions and allows motion annotations to be composed — one may jump while running, for example. Descriptions computed from video of real motions show that the method is accurate.