华东师范大学学报(自然科学版) ›› 2020, Vol. 2020 ›› Issue (4): 124-133.doi: 10.3969/j.issn.1000-5641.201921004

• 计算机科学 • 上一篇    下一篇

基于深度图像预旋转的手势估计改进方法

徐正则1,2, 张文俊1   

  1. 1. 上海大学 上海电影学院, 上海 200072;
    2. 华东师范大学 传播学院, 上海 200241
  • 收稿日期:2019-04-28 发布日期:2020-07-20
  • 通讯作者: 张文俊,男,教授,博士生导师,研究方向为数字图像处理.E-mail:wjzhang@shu.edu.cn E-mail:wjzhang@shu.edu.cn
  • 作者简介:徐正则, 男, 博士研究生, 研究方向为数字媒体技术. E-mail: zzxu@comm.ecnu.edu.cn
  • 基金资助:
    华东师范大学实验技术研究项目(20190704)

An improved method for hand gesture estimation based on depth image pre-rotation

XU Zhengze1,2, ZHANG Wenjun1   

  1. 1. Shanghai Film Academy, Shanghai University, Shanghai 200072, China;
    2. School of Communication, East China Normal University, Shanghai 200241, China
  • Received:2019-04-28 Published:2020-07-20

摘要: 基于深度图像的手势估计比人体姿势估计更加困难, 部分原因在于算法不能很好地识别同一个手势经旋转后的不同外观样式. 提出了一种基于卷积神经网络(Convolutional Neural Network, CNN)推测预旋转角度的手势姿态估计改进方法: 先利用自动算法标注的最佳旋转角度来训练CNN; 在手势识别之前, 用训练好的CNN模型回归计算出应预旋转的角度, 然后再对手部深度图像进行旋转; 最后采用随机决策森林(Random Decision Forest, RDF)方法对手部像素进行分类, 聚类产生出手部关节位置. 实验证明该方法可以减少预测的手部关节位置与准确位置之间的误差, 手势姿态估计的正确率平均上升了约4.69%.

关键词: 手势估计, 图像旋转, 深度图像

Abstract: Hand gesture estimation is much more difficult than human pose estimation from depth images, in part because existing algorithms are unable to recognize different appearances of the same hand gesture after rotation. In this paper, an improved approach for hand gesture estimation based on in-plane image rotation is proposed. First, a convolutional neural network (CNN) was trained by datasets with an auto tagged optimum angle of rotation. Then, prior to hand gesture recognition, an in-plane image of the hand depth was processed by the predicted angle of rotation through the trained CNN model. Lastly, depth pixels were classified by random decision forest (RDF), followed by clustering to generate the hand joint position. Experiments show that this method can reduce the error between the predicted position of the hand joint and the exact position, and the accuracy of gesture estimation improves by about 4.69% from the baseline.

Key words: hand pose estimation, image rotation, depth image

中图分类号: