Specialized mappings and the estimation of human body pose from a single image
Specialized mappings and the estimation of human body pose from a single image
复制标题
DOI：
10.1109/humo.2000.897366
复制
发表时间：
2000-12
期刊：
影响因子：
--
通讯作者：
Rómer Rosales;S. Sclaroff
中科院分区：
文献类型：
--
作者：
Rómer Rosales;S. Sclaroff
我们提出了一种使用专业映射架构（SMA）（一种非线性监督学习架构）从单个单眼图像中恢复关节式身体姿势的方法。 SMA 由几个专门的前向（输入到输出空间）映射函数和一个反馈匹配函数组成，根据数据自动估计。这些前向函数中的每一个都将输入空间的某些区域（可能是断开的）映射到输出空间。首先形式化该架构的概率模型以及学习其参数的机制。使用最大似然估计框架来解决学习问题；我们提出了几种不同的似然函数选择的期望最大化（EM）算法。在根据从单个图像获得的低级视觉特征估计人体姿势的任务中，对这些不同似然函数下所提出的解决方案的性能进行了比较，显示出有希望的结果。
We present an approach for recovering articulated body pose from single monocular images using the Specialized Mappings Architecture (SMA), a nonlinear supervised learning architecture. SMAs consist of several specialized forward (input to output space) mapping functions and a feedback matching function, estimated automatically from data. Each of these forward functions maps certain areas (possibly disconnected) of the input space onto the output space. A probabilistic model for the architecture is first formalized along with a mechanism for learning its parameters. The learning problem is approached using a maximum likelihood estimation framework; we present expectation maximization (EM) algorithms for several different choices of the likelihood function. The performance of the presented solutions under these different likelihood functions is compared in the task of estimating human body posture from low-level visual features obtained from a single image, showing promising results.