Spatial Attention Deep Net with Partial PSO for Hierarchical Hybrid Hand Pose Estimation
Spatial Attention Deep Net with Partial PSO for Hierarchical Hybrid Hand Pose Estimation
复制标题
DOI：
10.1007/978-3-319-46484-8_21
复制
发表时间：
2016-04
期刊：
影响因子：
--
通讯作者：
Qianru Ye;Shanxin Yuan;Tae-Kyun Kim
中科院分区：
文献类型：
--
作者：
Qianru Ye;Shanxin Yuan;Tae-Kyun Kim
判别式方法通常会产生运动学上不合理的手部姿势，然后使用生成方法在混合方法中纠正（或验证）这些结果。通过将高维输出空间分解成更小的输出空间，在层次结构中估计三维手姿是有效的。现有的分层方法主要关注输出空间的分解，而输入空间沿层次结构几乎保持不变。本文通过空间注意机制将运动层次策略应用于判别法的输入空间（以及输出空间），并通过层次粒子群优化（PSO）对生成方法进行优化，提出了一种混合手部姿态估计方法。空间注意机制通过转换输入（和特征空间）和输出空间，将级联和层次回归集成到CNN框架中，大大减少了视点和发音的变化。在层次结构的各个层次之间，层次PSO将运动约束强加给cnn的结果。实验结果表明，我们的方法在三个公共基准上明显优于四种最先进的方法和三个基线。
Discriminative methods often generate hand poses kinematically implausible, then generative methods are used to correct (or verify) these results in a hybrid method. Estimating 3D hand pose in a hierarchy, where the high-dimensional output space is decomposed into smaller ones, has been shown effective. Existing hierarchical methods mainly focus on the decomposition of the output space while the input space remains almost the same along the hierarchy. In this paper, a hybrid hand pose estimation method is proposed by applying the kinematic hierarchy strategy to the input space (as well as the output space) of the discriminative method by a spatial attention mechanism and to the optimization of the generative method by hierarchical Particle Swarm Optimization (PSO). The spatial attention mechanism integrates cascaded and hierarchical regression into a CNN framework by transforming both the input (and feature space) and the output space, which greatly reduces the viewpoint and articulation variations. Between the levels in the hierarchy, the hierarchical PSO forces the kinematic constraints to the results of the CNNs. The experimental results show that our method significantly outperforms four state-of-the-art methods and three baselines on three public benchmarks.