作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程

• 图形图像处理 • 上一篇    下一篇

基于深度图像梯度特征的人体姿态估计

徐岳峰,周书仁,王刚,佘凯晟   

  1. (长沙理工大学计算机与通信工程学院,长沙 410004)
  • 收稿日期:2014-11-27 出版日期:2015-12-15 发布日期:2015-12-15
  • 作者简介:徐岳峰(1988-),男,硕士研究生,主研方向:图像处理,模式识别;周书仁,副教授、博士;王刚,硕士研究生;佘凯晟,学士。
  • 基金资助:
    湖南省自然科学基金资助项目(12JJ6057);湖南省教育厅科学研究基金资助项目(13B132);湖南省交通运输厅科技进步与创新计划基金资助项目(201334);湖南省大学生研究性学习和创新性实验计划基金资助项目(湘教通[2012]402号136)。

Human Body Attitude Estimation Based on Gradient Feature of Depth Images

XU Yuefeng,ZHOU Shuren,WANG Gang,SHE Kaisheng   

  1. (School of Computer and Communication Engineering,Changsha University of Science and Technology,Changsha 410004,China)
  • Received:2014-11-27 Online:2015-12-15 Published:2015-12-15

摘要: 人体姿态估计中由于人体姿态的多样性、遮挡与自遮挡,导致系统准确率低、鲁棒性不强和运行效率低。为此,提出一种基于深度图像梯度的特征提取方法。利用图像中深度信息计算出每个像素点在水平方向和垂直方向的梯度值,计算每个像素点与邻域内像素点之间的差值 ,从而得到一个四维特征,对随机森林进行优化,并估计图像中的人体姿态。实验结果表明,与像素偏移比较法相比,该方法的鲁棒性和准确率都有明显提升,同时优化的随机森林决策方法,可使在只降低0.1%准确率的情况下,提升随机森林的测试运行效率。

关键词: 计算机视觉, 人体姿态估计, 深度图像, 特征提取, 随机森林

Abstract: Because of the diversity of human body pose occlusion and self-occlusion in human pose estimation,the accuracy of the system is not strong and the operation efficiency is low.This paper proposes a feature extraction method base on Gradient of Depth(GoD) for feature representation in human body posture estimation.This method firstly calculates each pixel’s gradient value in the horizontal direction and vertical direction by using the image’s depth information.Then the method calculates the difference between each pixel and its neighborhood pixels and obtains a 4D feature.At the same time,the method optimizes the random forests then estimates the human body posture in the image.The method has a significant improvement of human body posture estimation robustness and the accuracy in the process of single frame image compared with the optimized random forest decision-making method,and improves the test efficiency by reducing the accuracy rate of 0.1%.

Key words: computer vision, human body attitude estimation, depth image, feature extraction, random forest

中图分类号: