A multimodal Parkinson quantification by fusing eye and gait motion patterns, using covariance descriptors, from non-invasive computer vision

• Published in: Computer methods and programs in biomedicine Vol. 215; p. 106607
• Main Authors: Archila, John, Manzanera, Antoine, Martínez, Fabio
• Format: Journal Article
• Language: English
• Published: Ireland Elsevier B.V 01.03.2022; Elsevier
• Subjects: Bioengineering; Biomechanics; Computer Science; Computer Vision and Pattern Recognition; Computers; Deep features; Engineering Sciences; Gait; Humans; Image Processing; Imaging; Kinematic features; Life Sciences; Mechanics; Multimodal approach; Neurodegenerative Diseases; Neurons and Cognition; Parkinson; Parkinson Disease - diagnostic imaging; Temporal mean covariance; Tremor; Kinematic features; Multimodal approach; Deep features; Parkinson; Temporal mean covariance; deep features; temporal mean covariance; kinematic features; multimodal approach

•A multimodal fusion strategy that successfully integrates gait and eye fixational markerless patterns.•A very compact mean Riemannian covariance descriptor to stand out motion mode patterns.•A low-motion level characterization from kinematic and deep features that could be easily integrated into co...