Skip to main content
Fig. 2 | Journal of NeuroEngineering and Rehabilitation

Fig. 2

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

Fig. 2

Patches cropped from right or left parts of sample frames: a laminate flooring (high-friction material), b asphalt, c carpet (high-friction material), d partial view of furniture. Although the type of the walking surfaces are different, the \(453\times 453\) patches are very similar in terms of color and texture. EgoPlaceNet was adopted to classify frames into outdoor and indoor before terrain type identification to improve the framework’s performance

Back to article page