Estimating Human Body Configurations Using Shape Context Matching
Estimating Human Body Configurations Using Shape Context Matching
复制标题
DOI：
10.1007/3-540-47977-5_44
复制
发表时间：
2002-05
期刊：
影响因子：
--
通讯作者：
Greg Mori;Jitendra Malik
中科院分区：
文献类型：
--
作者：
Greg Mori;Jitendra Malik
我们在本文中考虑的问题是采取一个单一的二维图像包含一个人体，定位的关节位置，并使用这些来估计身体的配置和姿态在三维空间。基本的方法是以各种不同的配置和相对于相机的视点来存储人体的许多示例性2D视图。在这些存储的视图中的每一个上，身体关节（左肘、右膝等）的位置被显示在显示器上。手动标记和标记以备将来使用。测试形状，然后匹配到每个存储的视图，使用形状上下文匹配技术结合基于运动链的变形模型。假设存在在配置和姿态上足够相似的存储视图，则对应过程将成功。然后，身体关节的位置从示例视图转移到测试形状。给定关节位置，然后估计3D身体配置和姿势。我们可以将这种技术应用于视频，通过独立处理每一帧-跟踪只是重复识别！我们提出了各种数据集的结果。
The problem we consider in this paper is to take a single two-dimensional image containing a human body, locate the joint positions, and use these to estimate the body configuration and pose in three-dimensional space. The basic approach is to store a number of exemplar 2D views of the human body in a variety of different configurations and viewpoints with respect to the camera. On each of these stored views, the locations of the body joints (left elbow, right knee, etc.) are manually marked and labelled for future use. The test shape is then matched to each stored view, using the technique of shape context matching in conjunction with a kinematic chain-based deformation model. Assuming that there is a stored view sufficiently similar in configuration and pose, the correspondence process will succeed. The locations of the body joints are then transferred from the exemplar view to the test shape. Given the joint locations, the 3D body configuration and pose are then estimated. We can apply this technique to video by treating each frame independently - tracking just becomes repeated recognition! We present results on a variety of datasets.