计算机科学 ›› 2010, Vol. 37 ›› Issue (3): 268-270.
• 图形图像及体系结构 • 上一篇 下一篇
刘长红,杨扬,陈勇
出版日期:
发布日期:
基金资助:
LIU Chang-hong,YANG Yang,CHEN Yong
Online:
Published:
摘要: 判别式3D人体姿态估计方法直接学习图像观测到姿态之间的映射,需要大量训练集,而CPR对这种大训练集的映射模型学习由于计算复杂度太高而受到极大限制。提出了一种基于GPR和LWPR的增量式映射模型的学 习方法,利用CPR学习各局部映射模型,基于工WPR的思想在线调整现有的模型和训练新的局部模型以及姿态估计。实验表明,该方法能够极大地减少大数据集上高斯过程回归的计算代价,并获得准确的姿态估计。
关键词: 姿态估计,高斯过程回归,局部加权投影回归,增量学习
Abstract: Dicriminative approaches to 3D human pose estimation directly learn a mapping from image observations to pose,which requires large training sets. Gaussian process regression(GPR) to learn this mappings has been limited for high computational complexity, so we proposed a incrementally learning mappings based on GPR and Locally Weighted Projection Regression(LWPR). The approach utilized GPR to learn individual local models and LWPR to update existing models or learn a new local model for pose estimation. The experiment showed that the approach could greatly decrease computational complexity and exactly estimate the poses.
Key words: Pose estimation, Gaussian process regression, Locally weighted projection regression, Incremental learning
刘长红,杨扬,陈勇. 增量式人体姿态映射模型的学习方法[J]. 计算机科学, 2010, 37(3): 268-270. https://doi.org/
LIU Chang-hong,YANG Yang,CHEN Yong. Incrementally Learning Human Pose Mapping Model[J]. Computer Science, 2010, 37(3): 268-270. https://doi.org/
0 / / 推荐
导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks
链接本文: https://www.jsjkx.com/CN/
https://www.jsjkx.com/CN/Y2010/V37/I3/268
Cited