Abstract
Hand function is critical for our interactions and quality of life. Spinal cord injuries (SCI) can impair hand function, reducing independence. A comprehensive evaluation of function in home and community settings requires a hand grasp taxonomy for individuals with impaired hand function. Developing such a taxonomy is challenging due to unrepresented grasp types in standard taxonomies, uneven data distribution across injury levels, and limited data. This study aims to automatically identify the dominant distinct hand grasps in egocentric video using semantic clustering. Egocentric video recordings collected in the homes of 19 individual with cervical SCI were used to cluster grasping actions with semantic significance. A deep learning model integrating posture and appearance data was employed to create a personalized hand taxonomy. Quantitative analysis reveals a cluster purity of 67.6% +- 24.2% with with 18.0% +- 21.8% redundancy. Qualitative assessment revealed meaningful clusters in video content. This methodology provides a flexible and effective strategy to analyze hand function in the wild. It offers researchers and clinicians an efficient tool for evaluating hand function, aiding sensitive assessments and tailored intervention plans.
Abstract (translated)
手功能对于我们的人际交往和生活质量至关重要。脊髓损伤(SCI)可能损害手功能,降低独立性。对残疾人士在家庭和社区环境中的功能进行全面评估需要为损伤手功能的人开发手握类目。由于标准 taxonomies 中未包括的握姿类型、等级水平数据分布不均以及数据的限制,开发这种税目具有挑战性。 本研究旨在通过语义聚类在以自我为中心的视频中自动识别主导的握姿。使用19个患有脊髓SCI的个别人家中收集的自我中心视频进行聚类。采用深度学习模型结合姿势和外观数据创建了个性化的手 taxonomy。定量分析显示,握姿集群的纯度为67.6% +- 24.2%,冗余度为18.0% +- 21.8%。定性评估显示视频内容中有意义的聚类。这种方法为研究者和临床医生研究手功能提供了一个灵活而有效的工具,有助于敏感评估和定制干预计划。
URL
https://arxiv.org/abs/2403.18094