|
三维人体姿态估计的多视图图形结构
Multi-view Pictorial Structures for 3D Human Pose Estimation |
|
| |
| 课程网址: |
http://videolectures.net/bmvc2013_amin_pictorial_structures/
|
| 主讲教师: |
Sikandar Amin
|
| 开课单位: |
慕尼黑大学
|
| 开课时间: |
2014-04-03
|
| 课程语种: |
英语
|
| 中文简介: |
图片结构模型是2D人体姿势估计的事实上的标准。已经提出了许多改进和改进，例如，经过区别训练的身体部位检测器，灵活的身体模型以及局部和全局混合物。尽管这些技术允许实现2D姿势估计的最新技术性能，但它们尚未扩展为能够进行3D姿势估计。因此，本文提出了一种基于2D姿势估计的最新进展的多视图图形结构模型，并结合了跨多个视点的证据以实现可靠的3D姿势估计。我们评估了HumanEva I和MPII Cooking数据集上的多视图图片结构方法。与3D姿势估计的相关工作相比，我们的方法仅在单个帧上运行，而不依赖于特定于活动的运动模型或跟踪，从而获得了相似或更好的结果。值得注意的是，对于具有更复杂动作的活动，我们的方法要优于最新技术。
|
| 课程简介: |
Pictorial structure models are the de facto standard for 2D human pose estimation. Numerous refinements and improvements have been proposed such as discriminatively trained body part detectors, flexible body models, and local and global mixtures. While these techniques allow to achieve state-of-the-art performance for 2D pose estimation, they have not yet been extended to enable pose estimation in 3D. This paper thus proposes a multi-view pictorial structures model that builds on recent advances in 2D pose estimation and incorporates evidence across multiple viewpoints to allow for robust 3D pose estimation. We evaluate our multi-view pictorial structures approach on the HumanEva-I and MPII Cooking dataset. In comparison to related work for 3D pose estimation our approach achieves similar or better results while operating on single-frames only and not relying on activity specific motion models or tracking. Notably, our approach outperforms state-of-the-art for activities with more complex motions.
|
| 关 键 词: |
3D姿势; 图形结构; 数据集
|
| 课程来源: |
视频讲座网
|
| 数据采集: |
2021-03-25：zyk
|
| 最后编审: |
2021-03-25：zyk
|
| 阅读次数: |
53
|
|
图 书 馆