Understanding the Representation of Older Adults in Motion Capture Locomotion Datasets

TL;DR

This paper investigates how older adults are represented in public MoCap locomotion datasets and whether old-style motions truly reflect age-related gait differences. It combines a qualitative survey of 41 datasets with a quantitative fidelity assessment of old-style walking using age-sensitive gait parameters, applied to four datasets. The study finds pronounced underrepresentation of older adults, limited full-body data for them, and questionable fidelity of old-style motions, which often do not align with known age-related gait changes. The results highlight the need for better demographic coverage, richer motion diversity, and robust, data-efficient metrics to evaluate age-aware motion representations in MoCap datasets, with implications for healthcare AI and motion-analysis applications.

Abstract

The Internet of Things (IoT) sensors have been widely employed to capture human locomotions to enable applications such as activity recognition, human pose estimation, and fall detection. Motion capture (MoCap) systems are frequently used to generate ground truth annotations for human poses when training models with data from wearable or ambient sensors, and have been shown to be effective to synthesize data in these modalities. However, the representation of older adults, an increasingly important demographic in healthcare, in existing MoCap locomotion datasets has not been thoroughly examined. This work surveyed 41 publicly available datasets, identifying eight that include older adult motions and four that contain motions performed by younger actors annotated as old style. Older adults represent a small portion of participants overall, and few datasets provide full-body motion data for this group. To assess the fidelity of old-style walking motions, quantitative metrics are introduced, defining high fidelity as the ability to capture age-related differences relative to normative walking. Using gait parameters that are age-sensitive, robust to noise, and resilient to data scarcity, we found that old-style walking motions often exhibit overly controlled patterns and fail to faithfully characterize aging. These findings highlight the need for improved representation of older adults in motion datasets and establish a method to quantitatively evaluate the quality of old-style walking motions.

Figures (4)

• Figure 1: Basic gait parameters in a gait cycle.
• Figure 2: Walking trajectories of old-style forward walking motions and their control groups. Old-style motion and normative walking are plotted in blue and red, respectively. The units of the x and y axes are equal. The walking protocols included are daily walking, walking at a preferred speed, and F8WT walking.
• Figure 3: Feet height and step counting in old-style forward walking records. The x- and y-axis represent time and height values, respectively. The green crosses are used to count steps.
• Figure 4: Visualization of smoothness using joint kinematics from walking motions from subject 137 of the CMU dataset.