arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.01997cs.AI
收藏

GenGait:一种基于Transformer的模型用于人体步态异常检测和规范双生生成

GenGait: A Transformer-Based Model for Human Gait Anomaly Detection and Normative Twin Generation

HRI$^{2}$ Laboratory, Istituto Italiano di Tecnologia (IIT)(HRI²实验室,意大利技术研究院(IIT));Department of Occupational and Environmental Medicine, Epidemiology and Hygiene, INAIL(INAIL职业与环境医学、流行病学与卫生学系);Department of Medical and Surgical Sciences and Biotechnologies, Sapienza University of Rome(罗马大学医学外科学科与生物技术系)

Elisa Motta, Marta Lorenzini, Clara Mouawad, Alberto Ranavolo, Mariano Serrao, Arash Ajoudani

AI总结:

本文提出一种无需标签的框架,通过基于Transformer的掩码自动编码器,实现步态异常检测和运动学校正,验证显示能准确定位生物力学不一致的关节,减少角度偏差,保留规范运动学。

摘要:

步态分析提供了一种客观的步态功能表征,广泛用于支持神经性和骨科疾病的诊断和康复监测。深度学习已越来越多地应用于该领域,但大多数方法依赖于在疾病标记数据上训练的监督分类器,限制了对异质病理表现的泛化能力。本文提出了一种基于Transformer掩码自动编码器的无标签框架,该框架仅使用150名成年人的规范步态序列进行训练,这些序列通过无标记多摄像机运动捕捉系统获取。在推理过程中,采用两步程序处理潜在病理输入序列,首先通过遮蔽个体关节并测量与学习到的规范先验的偏差来估计关节不一致分数。然后,从编码器输入中排除被标记的关节,并从剩余的时空上下文中重建完整的骨骼,从而在被标记的位置获得校正的运动学轨迹。在10名被排除的规范参与者上验证,这些参与者模仿了七种模拟步态异常,结果显示能够准确定位生物力学不一致的关节,所有分析关节的角度偏差显著减少,效果显著,同时保留了规范运动学。所提出的方法能够在不需疾病标签的情况下实现可解释的、针对个体的步态障碍定位。视频可在https://youtu.be/Rcm3jqR5pN4上查看。

英文摘要:

Gait analysis provides an objective characterization of locomotor function and is widely used to support diagnosis and rehabilitation monitoring across neurological and orthopedic disorders. Deep learning has been increasingly applied to this domain, yet most approaches rely on supervised classifiers trained on disease-labeled data, limiting generalization to heterogeneous pathological presentations. The methodological objective of this work is to develop a label-free framework for joint-level anomaly detection and kinematic correction based on a Transformer masked autoencoder trained exclusively on normative gait sequences from 150 adults, acquired with a markerless multi-camera motion-capture system. At inference, a two-pass procedure is applied to potentially pathological input sequences: first, it estimates joint inconsistency scores by occluding individual joints and measuring deviations from the learned normative prior. Then, it withholds the flagged joints from the encoder input and reconstructs the full skeleton from the remaining spatiotemporal context, yielding corrected kinematic trajectories at the flagged positions. The validation objective is to assess whether the framework preserves unseen normative gait and reduces angular deviation in simulated abnormal gait patterns. In this proof-of-concept evaluation, data from 10 held-out normative participants, who performed seven simulated abnormal gait patterns, showed a significant reduction in angular deviation across all analyzed joints with large effect sizes, and preservation of normative kinematics. The proposed approach enables interpretable, subject-specific localization of joints that are inconsistent with learned normative gait patterns and generation of an individualized normative reconstruction without requiring disease labels. Video is available at https://youtu.be/Rcm3jqR5pN4.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑