Grid point extraction exploiting point symmetry in a pseudo-random color pattern
Grid point extraction exploiting point symmetry in a pseudo-random color pattern
复制标题
DOI：
10.1109/icip.2008.4712165
复制
发表时间：
2008
期刊：
影响因子：
--
通讯作者：
Zhan Song;R. Chung
中科院分区：
文献类型：
--
作者：
Zhan Song;R. Chung
本文研究了从单目图像中恢复三维人体姿态的问题。在文献中，贝叶斯专家混合（BME）被成功地用于表示多模态图像到姿态分布。然而，学习BME模型的期望最大化（EM）算法可能收敛到次优局部最大值。最终解的质量很大程度上取决于初始值。在本文中，我们提出了一个有效的初始化方法BME学习。我们首先对训练集进行分区，使得每个子集都可以由单个专家很好地建模，并且总回归误差最小化。然后在一个划分子集上初始化BME模型的每个专家和门。我们的初始化方法在准合成数据集和真实的数据集（HumanEva）上进行了测试。实验结果表明，该方法在提高测试精度的同时，大大降低了训练的计算量。
This paper addresses the problem of recovering 3D human pose from a single monocular image. In the literature, Bayesian Mixtures of Experts (BME) was successfully used to represent the multimodal image-to-pose distributions. However, the expectation-maximization (EM) algorithm that learns the BME model may converge to a suboptimal local maximum. And the quality of the final solution depends largely on the initial values. In this paper, we propose an efficient initialization method for BME learning. We first partition the training set so that each subset can be well modeled by a single expert and the total regression error is minimized. Then each expert and gate of BME model is initialized on a partition subset. Our initialization method is tested on both a quasi-synthetic dataset and a real dataset (HumanEva). Results show that it greatly reduces the computational cost in training while improves testing accuracy.