利用单深度图像同时进行手势和骨骼长度估计

每天一分钟，带你读遍机器人顶级会议文章

标题：Simultaneous Hand Pose and Skeleton Bone-Lengths Estimation from a Single Depth Image

作者：Jameel Malik, Ahmed Elhayek,

and Didier Stricker

来源：3dv 2017 (International Conference on 3D Vision )

播音员：郭晨

编译：袁梦

欢迎个人转发朋友圈；其他机构或自媒体如需转载，后台留言申请授权

摘要

今天介绍的文章是“Simultaneous Hand Pose and Skeleton Bone-Lengths Estimation from a Single Depth Image”——利用单深度图像同时进行手势和骨骼长度估计，该文章发表在 3dv-2017。

关节手位估计是一项具有挑战性的人机交互任务。目前最先进的手势估计算法只适用于一个或几个被校准或训练的物体。

特别是基于学习的混合方法，模型拟合的方法或基于模型的深度学习的方法，都并没有明确考虑到不同的手型和尺寸。

本文，我们提出了一种通过从一个单一的深度图像同时估计三维手的姿势以及骨骼长度的新混合算法。利用CNN架构同时学习手的姿势参数、尺度参数与骨骼长度。之后，一种新的基于混合正向运动学的网络层利用上述所有参数来估计三维关节位置的手。

通过端到端的训练，统一了NYU，icvl和msra-2015三个公共数据集的格式，并使得该网络能够适应大幅度变化的手的形状和尺寸。

通过复合数据集和包含多个学科的icvl数据集进行验证，我们的方法相对于目前多种先进的混合方法精度更高。此外，我们的算法被证明能很好地处理不可见图像。

同时手势和骨架估计的模型演示。该算法从三开始。卷积层和两个全连接层。最后一个全连接层的输出参数（Θ）和手的姿势与骨骼长度相关的标度参数。最后，提出了一种混合前向运动学函数。应用手部比例和姿态参数输出三维关节位置。

Abstract

Articulated hand pose estimation is a challenging task for human-computer interaction. The state-of-the-art hand pose estimation algorithms work only with one or a few subjects for which they have been calibrated or trained. Par-ticularly, the hybrid methods based on learning followed by model fitting or model based deep learning do not explicitly consider varying hand shapes and sizes. In this work, we introduce a novel hybrid algorithm for estimating the 3D hand pose as well as bone-lengths of the hand skeleton at the same time, from a single depth image. The proposed CNN architecture learns hand pose parameters and scale parameters associated with the bone-lengths simul-taneously. Subsequently, a new hybrid forward kinematics layer employs both parameters to estimate 3D joint positions of the hand. For end-to-end training, we combine three public datasets NYU, ICVL and MSRA-2015 in one unified format to achieve large variation in hand shapes and sizes. Among hybrid methods, our method shows improved accuracy over the state-of-the-art on the combined dataset and the ICVL dataset that contain multiple subjects. Also, our algorithm is demonstrated to work well with unseen images.

如果你对本文感兴趣，想要下载完整文章进行阅读，可以关注【泡泡机器人SLAM】公众号（paopaorobot_slam）。