Auto-Gait共济失调步态视频数据集

数据集获取

git clone https://github.com/ROC-HCI/Automated-Ataxia-Gait.git

curl -L -o repo.zip https://github.com/ROC-HCI/Automated-Ataxia-Gait/archive/refs/heads/main.zip
unzip repo.zip

源站 README 摘录（使用方式）

This repository contains code and an anonymized version of the dataset used in the paper, Auto-Gait: Automatic Ataxia Risk Assessment with Computer Vision from Gait Task Videos published at Proceedings of ACM on Interactive, Mobile, Wearable, and Ubiquitous Computing (IMWUT), 2023.
Anonymized dataset: https://rochester.box.com/v/AtaxiaDataset

Warning: In order to make the public release, the participant faces and the background had to be blurred. Which might cause the object detection and pose estimation models to fail.

If you use this dataset, please provide attribution to READISCA and NIH grant number U01NS104326.
Ataxia is a neurodegenerative disease that surfaces as difficulty with motor control, such as walking imbalance. Many patients with Ataxia do not have easy access to neurologists – especially those living in remote localities and developing/ underdeveloped countries. In a multi-year collaboration effort with READISCA, we collected a video dataset of ataxia diagnosed and control subjects from 11 clinics located in 8 different states across the United States. The dataset contains 150 (anonymized version of the 155 videos used in the original study) 6 seconds long videos from 89 unique study participants (24 control, 65 diagnosed) performing gait task.
Furthermore, we developed a computer vision and machine learning pipeline to identify, track, and separate participants from complex surroundings and predict their risk and severity of Spinocerebellar Ataxia. Ataxia risk-prediction model achieves 83.06% accuracy and an 80.23% F1 score. Ataxia severity-assessment model achieves MAE score of 0.6225 and a Pearson’'s correlation coefficient score of 0.7268. Our model performs competitively while tested on clinics completely unseen during training. Our feature importance analysis shows the model automatically picks up traits that are consistent with established clinical knowledge.
Limitations:

• 5 of the videos were removed during the anonymization process for the public release. Hence the results using this dataset might vary slightly from the original study.
• #146 is a video of the study subject attempting tandem walking instead of regular walk.
• #144, the subject is wearing shoes, which is a protocol violation, but pra

数据加载示例（图像类）

from PIL import Image
import glob, os

files = (glob.glob(os.path.join(path, "**", "*.png"), recursive=True)
       + glob.glob(os.path.join(path, "**", "*.jpg"), recursive=True)
       + glob.glob(os.path.join(path, "**", "*.tif"), recursive=True))
print("图像文件数:", len(files))
img = Image.open(files[0]); print("尺寸/模式:", img.size, img.mode)

# torchvision Dataset 方式:
# from torchvision import datasets
# ds = datasets.ImageFolder(path)  # 要求 子目录=类别

目录组织与标注格式以源站说明和下载后实际文件为准。

完整仓库：github.com/ROC-HCI/Automated-Ataxia-Gait