人类对象交互活动中的对象和人体姿势的建模Modeling Mutual Context of Object and Human Pose in Human-Object Interaction Activities |
|
课程网址: | http://videolectures.net/cvpr2010_fei_fei_mmco/ |
主讲教师: | Fei-Fei Li |
开课单位: | 斯坦福大学 |
开课时间: | 2010-07-19 |
课程语种: | 英语 |
中文简介: | 在杂乱的场景中检测物体并估计铰接的人体部位是计算机视觉中的两个具有挑战性的问题。困难尤其是涉及人类对象交互(例如,游戏)的活动,其中相关对象往往是小的或仅部分可见的,并且人体部分通常是自身被遮挡的。然而,我们观察到,对象和人类可以作为彼此的相互背景 - 识别一个有助于识别另一个。在本文中,我们提出了一种新的随机场模型来编码人类对象交互活动中的对象和人体姿势的相互关系。然后我们将模型学习任务作为结构学习问题,其中通过结构搜索估计对象,整体人体姿势和不同身体部位之间的结构连通性,并通过新的最大边际算法估计模型的参数。在六类人类物体相互作用的运动数据集[12]中,我们表明我们的相互背景模型明显优于检测非常困难的物体和人体姿势的状态。 |
课程简介: | Detecting objects in cluttered scenes and estimating articulated human body parts are two challenging problems in computer vision. The difficulty is particularly pronounced in activities involving human-object interactions (e.g. playing tennis), where the relevant object tends to be small or only partially visible, and the human body parts are often self-occluded. We observe, however, that objects and human poses can serve as mutual context to each other – recognizing one facilitates the recognition of the other. In this paper we propose a new random field model to encode the mutual context of objects and human poses in human-object interaction activities. We then cast the model learning task as a structure learning problem, of which the structural connectivity between the object, the overall human pose, and different body parts are estimated through a structure search approach, and the parameters of the model are estimated by a new max-margin algorithm. On a sports data set of six classes of human-object interactions [12], we show that our mutual context model significantly outperforms state-of-theart in detecting very difficult objects and human poses. |
关 键 词: | 计算机视觉; 识别; 随机场模型 |
课程来源: | 视频讲座网 |
最后编审: | 2019-03-13:lxf |
阅读次数: | 40 |