Spatial Attention Deep Net with Partial PSO for Hierarchical Hybrid Hand Pose Estimation

TL;DR

This paper introduces a hybrid hierarchical hand pose estimation method combining spatial attention in CNNs and hierarchical PSO, effectively reducing variations and enforcing kinematic constraints, outperforming existing methods.

Contribution

It applies the kinematic hierarchy strategy to both input and output spaces using spatial attention and hierarchical PSO, a novel approach in hand pose estimation.

Findings

Outperforms four state-of-the-art methods on three benchmarks

Significantly reduces viewpoint and articulation variations

Enforces kinematic constraints effectively

Abstract

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.