摘要
基于深度图像的手势识别通常需要大量的训练数据,如何快速标定和建立姿态数据集是一个具有挑战性的任务.文中提出一种半自动标定方法,利用随机决策树森林建立深度像素的标定数据集;在此基础上设计了一个基于视觉的手势交互桌面应用开发框架,该框架采用RGB-D信息作为数据输入,同时利用3D手形轮廓降低手势匹配的复杂度.实验结果表明,文中方法能够支持复杂手势的实时识别.
For depth sensor based hand gesture recognition, how to collect training data and built a gesture database with suitable size are challenging tasks. In this paper, we present a semi-automatic labeling scheme for establishing the real hand gesture dataset. A framework for developing hand gesture driven desktop applications is designed based on this scheme, which use RGB-D sensor as input. Moreover, a hand contour model is proposed to simplify the gesture matching process and reduce the computational complexity. The experimental evaluations and a demo application demonstrate the effectiveness of this framework.
出处
《计算机辅助设计与图形学学报》
EI
CSCD
北大核心
2013年第12期1810-1817,共8页
Journal of Computer-Aided Design & Computer Graphics
基金
国家自然科学基金(60703029)
关键词
手势识别
RGB—D
轮廓模型
标本标记
姿态估计
hand gesture recognition
RGB-D
contour model
sample labeling
pose estimation
