Sparse probabilistic regression for activity-independent human pose inference
Sparse probabilistic regression for activity-independent human pose inference
复制标题
DOI：
10.1109/cvpr.2008.4587360
复制
发表时间：
2008-06
期刊：
影响因子：
--
通讯作者：
R. Urtasun;Trevor Darrell
中科院分区：
文献类型：
--
作者：
R. Urtasun;Trevor Darrell
人体姿势推断的辨别性方法包括将视觉观察映射到关节身体形状。目前学习这种映射的概率方法在处理具有大量活动的域的能力方面受到限制，这些活动需要非常大的训练集。我们提出了一种在线概率回归方案，用于复杂、高维和多模式映射的有效推理。我们的技术是基于高斯过程的局部混合，其中局部性是基于外观和姿势来定义的，并且映射超参数可以在局部邻域中变化，以更好地适应姿势空间中的特定区域。混合成分是在非常小的社区中在线定义的，因此学习和推理非常高效。当映射是一一对应时，我们得到了单调递减协方差函数的局部回归(vs.全局回归)的逼近误差的界。我们的方法可以确定在给定数据库其余部分的情况下，训练样本何时是冗余的，并使用这一标准进行剪枝。我们报告了合成(POSER)和真实(Humaneva)姿势数据库的结果，使用高达105个训练集的大小获得快速而准确的姿势估计。
Discriminative approaches to human pose inference involve mapping visual observations to articulated body configurations. Current probabilistic approaches to learn this mapping have been limited in their ability to handle domains with a large number of activities that require very large training sets. We propose an online probabilistic regression scheme for efficient inference of complex, high- dimensional, and multimodal mappings. Our technique is based on a local mixture of Gaussian processes, where locality is defined based on both appearance and pose, and where the mapping hyperparameters can vary across local neighborhoods to better adapt to specific regions in the pose space. The mixture components are defined online in very small neighborhoods, so learning and inference is extremely efficient. When the mapping is one-to-one, we derive a bound on the approximation error of local regression (vs. global regression) for monotonically decreasing co- variance functions. Our method can determine when training examples are redundant given the rest of the database, and use this criteria for pruning. We report results on synthetic (Poser) and real (Humaneva) pose databases, obtaining fast and accurate pose estimates using training set sizes up to 105.