Opening the Black Box: Hierarchical Sampling Optimization for Estimating Human Hand Pose
Opening the Black Box: Hierarchical Sampling Optimization for Estimating Human Hand Pose
复制标题
DOI：
10.1109/iccv.2015.380
复制
发表时间：
2015-12
期刊：
影响因子：
--
通讯作者：
Danhang Tang;Jonathan Taylor;Pushmeet Kohli;Cem Keskin;Tae-Kyun Kim;J. Shotton
中科院分区：
文献类型：
--
作者：
Danhang Tang;Jonathan Taylor;Pushmeet Kohli;Cem Keskin;Tae-Kyun Kim;J. Shotton
我们解决了手势估计的问题，这是一个逆问题。典型的方法使用黑盒图像生成过程来优化相对于姿势参数的能量函数。这一过程对参数之间的关系或能量函数的形式知之甚少。在本文中，我们表明，通过利用参数结构的高级知识和使用局部代理能量函数，我们可以显著改进黑盒优化。我们的新框架，分层抽样优化，由组织成运动学层次结构的一系列预测器组成。每个预测器以其祖先为条件，并在姿势参数的子集上生成一组样本。使用高效的代理能量在样本中进行选择。评估完整个层次后，连接部分姿势样本以生成完整姿势假设。使用相同的过程生成多个假设，最后由原始的全能量函数选择最佳结果。在三个公开可用的数据集上的实验评估表明，我们的方法在低计算场景下尤其令人印象深刻，它的性能显著优于所有其他最先进的方法。
We address the problem of hand pose estimation, formulated as an inverse problem. Typical approaches optimize an energy function over pose parameters using a 'black box' image generation procedure. This procedure knows little about either the relationships between the parameters or the form of the energy function. In this paper, we show that we can significantly improving upon black box optimization by exploiting high-level knowledge of the structure of the parameters and using a local surrogate energy function. Our new framework, hierarchical sampling optimization, consists of a sequence of predictors organized into a kinematic hierarchy. Each predictor is conditioned on its ancestors, and generates a set of samples over a subset of the pose parameters. The highly-efficient surrogate energy is used to select among samples. Having evaluated the full hierarchy, the partial pose samples are concatenated to generate a full-pose hypothesis. Several hypotheses are generated using the same procedure, and finally the original full energy function selects the best result. Experimental evaluation on three publically available datasets show that our method is particularly impressive in low-compute scenarios where it significantly outperforms all other state-of-the-art methods.