步态分析数据集
该数据集包含178名不同阶段脑瘫患者的1139次步态试验数据，采用高频VICON运动捕捉系统采集的三维坐标数据模态，记录了19个身体标记点的运动轨迹，主要用于脑瘫患者的步态分析、运动功能评估、康复治疗效果监测以及生物力学建模等研究领域。
基本信息
资源简介
步态分析数据集
【数据集背景】
本数据集源站标题为《lucabergamini/gait-analysis-dataset》。源站首次发布：2019-03-11。
【数据内容】
源站原始描述：Raw dataset from "Signal Processing and Machine Learning for Diplegia Classification" and "Gait-Based Diplegia Classification Using LSMT Networks" # gait-analysis-dataset Raw dataset from "Signal Processing and Machine Learning for Diplegia Classification" and "Gait-Based Diplegia Classification Using LSMT Networks" # Introduction Diplegia is one of the most common forms of a broad family of motion disorders named cerebral palsy (CP) affecting the voluntary muscular system. In recent years, vari…
【主题与分类】
主题标签：diplegia、gait、gait-analysis、gait-recognition。
【获取与许可】
源站页面：https://github.com/lucabergamini/gait-analysis-dataset
使用许可：GPL-3.0。
【使用注意】
· 源站最后修改于 2019-04-05，引用时请注意版本时效。
下载信息
注册下载
需要注册 Kaggle 账号并登录后下载，适合需要跟踪下载记录和使用 API 的用户。
暂未开放公开下载
无需注册即可直接获取公开样本或文档，适合快速预览和评估数据集质量。
免登录有偿下载
公开数据集受托下载与技术交付服务。
提供高速下载与技术交付服务（收技术服务费，非数据销售）
暂未开放当前数据集主要来源为 Kaggle 公开托管，完整影像包建议通过原始链接或 Kaggle API 获取。
使用方式
数据集获取
git clone https://github.com/lucabergamini/gait-analysis-dataset.git
curl -L -o repo.zip https://github.com/lucabergamini/gait-analysis-dataset/archive/refs/heads/master.zip
unzip repo.zip
源站 README 摘录（使用方式）
gait-analysis-dataset
Raw dataset from “Signal Processing and Machine Learning for Diplegia Classification” and “Gait-Based Diplegia Classification Using LSMT Networks”
Introduction
Diplegia is one of the most common forms of a broad family of motion
disorders named cerebral palsy (CP) affecting the voluntary
muscular system. In recent years, various
classification criteria have been proposed for CP, to assist in diagnosis, clinical decision-making and communication.
Data
Dataset is available HERE.
Our dataset refers to 1139 trials acquired from 178 patients affected by different stages of diplegia using high frequency VICON
cameras in an Italian hospital.
WARNING: some trials may be invalid (e.g. invalid markers throughout the sequence).
X
Each .npy file has a variable number of frames.
For each frame, 19 markers are reported with 3D coordinates (first 3 elements) along with a validation flag.
If you’'re interested in other markers or other medical indicators, please write me an email.
Y
The path to a .npy file is the follow:
base_folder/class_label/subject_label/.npy
Utils
Along with the script employed to extract .npy file, the repo comes with a handy minimal visualizer based on Open3D.
Here are some examples:
<table style=“width:100%”>
<tr>
<th>
<br>Class 0 example.
<th>
<br>Class 1 example.
</tr>
</table>
<table style=“width:100%”>
<tr>
<th>
<p align=“center”>
<img src=“./img/70_3.gif” alt=“Example” width=“75%” height=“75%”>
<br>Class 2 example.
</p>
</th>
<th>
<p align=“center”>
<img src=“./img/114_1.gif” alt=“Example” width=“75%” height=“75%”>
<br>Class 3 example.
</p>
</th>
</tr>
</table>
How to cite
If you have employed our dataset in your research,
please cite both the followings:
@inproceedings{bergamini2017signal,
title={Signal Processing and Machine Learning for Diplegia Classification},
author={Bergamini, Luca and Calderara, Simone and Bicocchi, Nicola and Ferrari, Alberto and Vitetta, Giorgio},
booktitle={International Conference on Image Analysis and Processing},
pages={97108},
year={2017},
organization={Springer}
> 完整仓库：[github.com/lucabergamini/gait-analysis-dataset](https://github.com/lucabergamini/gait-analysis-dataset)数据缺失？
依托陕西、四川两大基地，我们与超过十家三甲医院建立直接合作关系，覆盖合规授权、采集治理、专业标注、数据交付的全流程，为AI医疗团队提供即拿即用的高质量临床数据。
⚡️ 需要数据支持或标注服务？立即联系我们获取专业方案。
