Egocentric vision-based detection of surfaces: towards context-aware free-living digital biomarkers for gait and fall risk assessment

Table 1 Demographic information and the distribution of crops/frames over different classes

From MAGFRA-W, only frames and patches attributed to walking bouts ≥3steps (level walking) were annotated. Fall history: number of falls in the previous one year, \(\star\): camera was unintentionally mounted upside-down by the participants or was set to take photos (not videos) resulted in smaller sample size, †: Participants living in the same home. HFM: high-friction materials

ISSN: 1743-0003