Northwestern-UCLA Multiview Action 3D Dataset
收藏OpenDataLab2026-05-24 更新2024-05-09 收录
下载链接:
https://opendatalab.org.cn/OpenDataLab/Northwestern-UCLA_Multiview_Action_etc
下载链接
链接失效反馈官方服务:
资源简介:
Multiview 3D事件数据集由我和niaohan Nie在UCLA中捕获。它包含由三个Kinect相机同时捕获的RGB,深度和人体骨骼数据。该数据集包括10个动作类别: 用一只手捡起,用两只手捡起,扔垃圾,四处走动,坐下,站起来,穿上,落纱,扔,携带。每个动作由10名演员表演。该数据集包含从各种观点获取的数据。数据集可以在第1部分,第2部分,第3部分,第4部分,第5部分,第6部分,第7部分,第8部分,第9部分,第10部分,第11部分,第12部分,第13部分,第14部分,第15部分,第16部分,我们还创建了一个仅包含RGB视频的数据集版本: 仅RGB视频。
The Multiview 3D Event Dataset was captured by niaohan Nie and myself at UCLA. It contains RGB, depth and human skeleton data simultaneously collected by three Kinect cameras. This dataset includes 10 action categories: picking up with one hand, picking up with two hands, throwing trash, walking around, sitting down, standing up, putting on, yarn dropping, throwing, and carrying. Each action is performed by 10 actors. This dataset contains data acquired from various viewpoints. The dataset is available in Part 1, Part 2, Part 3, Part 4, Part 5, Part 6, Part 7, Part 8, Part 9, Part 10, Part 11, Part 12, Part 13, Part 14, Part 15, Part 16. We have also created a version of the dataset that only contains RGB videos, denoted as the "Only RGB Videos" version.
提供机构:
OpenDataLab
创建时间:
2023-02-06
搜集汇总
数据集介绍

背景与挑战
背景概述
Northwestern-UCLA Multiview Action 3D Dataset是一个多视角3D动作数据集,包含由三个Kinect相机同时捕获的RGB、深度和人体骨骼数据,涵盖10个动作类别,每个动作由10名演员表演,适用于动作识别研究。数据集提供多视角数据,并有一个仅RGB视频的版本,由University of Adelaide和西北工业大学于2018年发布。
以上内容由遇见数据集搜集并总结生成



