Model-Free Detection, Encoding, Retrieval, and Visualization of Human Poses From Kinect Data

Model-Free Detection, Encoding, Retrieval, and Visualization of Human Poses From Kinect Data
复制标题

基于 Kinect 数据的人体姿势的无模型检测、编码、检索和可视化

DOI:
10.1109/tmech.2014.2322376
复制
发表时间:
--
期刊:
IEEE/ASME Transactions on Mechatronics
影响因子:
--
通讯作者:
Weiliang Xu
Weiliang Xu
中科院分区:
--
文献类型:
--
作者:
Martin Stommel;Michael Beetz;Weiliang Xu

文献摘要

参考文献

被引文献

相似文献

在许多人机交互的机电一体化应用中,Kinect相机数据中的人体识别是一个关键问题。为了改善许多基于运动学或表面网格模型的方法的局限性,我们提出了一种由深度轮廓的骨架化提供的关键点时空分割方法。矢量形状的姿态描述符允许检索相似的姿态,并且更容易与许多机器学习库一起使用。基于希尔伯特曲线的可视化方法为检测到的姿势提供了有价值的见解。我们的实验结果表明,所提出的方法能够适应厨房场景中的人数,并随着时间的推移跟踪他们。我们能够从数据库中检索相似的姿势,并在数据集中识别集群。通过应用我们的方法,普林斯顿跟踪基准,我们证明了我们的方法适用于人类运动学或表面网格模型过于受限的场景。
The recognition of humans in Kinect camera data is a crucial problem in many mechatronics applications with human-computer interaction. In order to improve the limited scope of many methods based on a kinematic or surface mesh model, we propose a spatiotemporal segmentation of keypoints provided by a skeletonization of depth contours. A vector-shaped pose descriptor allows for the retrieval of similar poses and is easier to use with many machine learning libraries. A visualization method based on the Hilbert curve provides valuable insight in the detected poses. Our experimental results show that the proposed method is able to adapt to the number of people in a kitchen scenario, and track them over time. We were able to retrieve similar poses from a database and identify clusters in the dataset. By applying our method, the Princeton Tracking Benchmark, we demonstrated that our method is applicable in scenes where a human kinematic or surface mesh model would be overly restrictive.
构建行人轮廓层次结构以改进交通场景中的检测
DOI: --
发表时间: 2008
期刊: International Conference on Computer Vision and Graphics
影响因子: --
作者:
Ion Giosan;S. Nedevschi
通讯作者: S. Nedevschi
使用未标记的标记进行稳健的人体姿势识别
DOI: --
发表时间: 2008
期刊: IEEE Workshop on Applications of Computer Vision
影响因子: --
作者:
Yi Wang;G. Qian
通讯作者: G. Qian
从单目图像序列进行自遮挡鲁棒 3D 人体姿态跟踪
DOI: --
发表时间: 2012
期刊: IEEE International Conference on Systems, Man and Cybernetics
影响因子: --
作者:
Nam;A. Yuille;Seong
通讯作者: Seong
从具有部分遮挡和噪声污染的损坏图像中进行稳健的人体姿势估计
DOI: --
发表时间: 2011
期刊: IEEE International Conference on Granular Computing
影响因子: --
作者:
Guoliang Lu;Mineichi Kudo;J. Toyama
通讯作者: J. Toyama
DOI: 10.1109/tmech.2004.834650
发表时间: 2004-09
期刊: IEEE/ASME Transactions on Mechatronics
影响因子: --
作者:
T. Sato;T. Harada;T. Mori
通讯作者: T. Sato;T. Harada;T. Mori