Side DepthImages supporting Paper "Functional movement screen dataset collected with two Azure Kinect depth sensors"

This is depth images of Azure Kinect sensor in side position.<br> This dataset supports the following publication: Xing, QJ., Shen, YY., Cao, R. et al. Functional movement screen dataset collected with two Azure Kinect depth sensors. Sci Data 9, 104 (2022). https://doi.org/10.1038/s41597-022-01188-7 <br>See related materials in collection at: https://doi.org/10.25452/figshare.plus.c.5774969 <br>Collection Description: This presents a dataset for vision-based autonomous functional movement screen (FMS) collected from 45 human subjects of different ages (18-59 years old) executing the following movements: deep squat, hurdle step, in-line lunge, shoulder mobility, active straight raise, trunk stability push-up, and rotary stability. Specifically, shoulder mobility was performed only once by different subjects, while the other movements were repeated for three episodes each. Each episode was saved as one record and was annotated from 0 to 3 by three FMS experts. The main strength of our database is twofold. One is the multimodal data provided, including color images, depth images, and 3D human skeleton joints. The other is the multiview data collected from the two synchronized Azure Kinect sensors in front of and on the side of the subjects. Finally, three-dimensional trajectories, quaternions, and 2D pixel trajectories of 32 joints were recorded. Our dataset contains a total of 1812 recordings, with 3624 episodes. The size of the dataset is 158 GB. As a supplement, we also provide color image data from the other two cameras (back and side low positions). This dataset provides the opportunity for automatic action quality evaluation of FMS.

本数据集包含侧置Azure Kinect传感器采集的深度图像。
本数据集关联以下发表学术论文：Xing QJ、Shen YY、Cao R 等学者题为《采用两台Azure Kinect深度传感器采集的功能性动作筛查数据集》的研究，刊载于《Scientific Data》2022年第9卷第104页，DOI：10.1038/s41597-022-01188-7。
相关馆藏材料可通过以下链接获取：https://doi.org/10.25452/figshare.plus.c.5774969。
数据集说明：本数据集为基于视觉的自主功能性动作筛查（Functional Movement Screen, FMS）数据集，采集自45名年龄介于18至59岁的人类受试者，受试者需完成以下七项动作：深蹲、跨栏步、直线弓步、肩部活动度测试、主动直腿上抬、躯干稳定俯卧撑以及旋转稳定性测试。
具体而言，肩部活动度测试仅由每名受试者完成一次，其余六项动作每名受试者均重复完成三个试次。每个动作试次均保存为一条数据记录，并由三名FMS专家按照0至3的评分等级进行标注。
本数据集的核心优势主要有两点：其一为提供多模态数据，涵盖彩色图像、深度图像以及三维人体骨骼关节数据；其二为采集多视角数据，通过两台同步部署的Azure Kinect传感器分别置于受试者前方与侧方完成数据采集。
此外，本数据集还记录了32个人体骨骼关节的三维运动轨迹、四元数数据以及二维像素坐标轨迹。
本数据集总计包含1812条数据记录，对应3624个动作试次，总数据量达158 GB。
作为补充内容，本数据集还提供另外两台相机（背部机位与侧低位机位）采集的彩色图像数据。
本数据集可为功能性动作筛查的自动化动作质量评估提供重要的数据支撑。