Efficient Hand Articulations Tracking using Adaptive Hand Model and Depth map
This addresses the problem of high power consumption and cost in hand tracking for VR/AR and tablet interactions, offering a more accessible solution for mobile applications, though it appears incremental in optimizing existing methods.
The paper tackles real-time hand articulations tracking for mobile and wearable devices by proposing an efficient system that avoids high-performance GPUs, achieving automatic hand model adjustment and real-time tracking with improved accuracy through hierarchical random sampling.
Real-time hand articulations tracking is important for many applications such as interacting with virtual / augmented reality devices or tablets. However, most of existing algorithms highly rely on expensive and high power-consuming GPUs to achieve real-time processing. Consequently, these systems are inappropriate for mobile and wearable devices. In this paper, we propose an efficient hand tracking system which does not require high performance GPUs. In our system, we track hand articulations by minimizing discrepancy between depth map from sensor and computer-generated hand model. We also initialize hand pose at each frame using finger detection and classification. Our contributions are: (a) propose adaptive hand model to consider different hand shapes of users without generating personalized hand model; (b) improve the highly efficient frame initialization for robust tracking and automatic initialization; (c) propose hierarchical random sampling of pixels from each depth map to improve tracking accuracy while limiting required computations. To the best of our knowledge, it is the first system that achieves both automatic hand model adjustment and real-time tracking without using GPUs.