Quantification and recognition of parkinsonian gait from monocular video imaging using kernel-based principal component analysis

• Main Authors: Chen, S.-W, Lin, S.-H, Liao, L.-D, Lai, H.-Y, Pei, Y.-C, Kuo, T.-S, Lin, C.-T, Chang, J.-Y, Chen, Y.-Y, Lo, Y.-C, Chen, S.-Y, Wu, R, Tsang, S
• Other Authors: LIFE SCIENCES INSTITUTE
• Format: Article
• Published: 2020
• Subjects: Accuracy rate; Analysis approach; Binary silhouettes; Clinical assessments; Ease of use; Gait cycles; Gait parameters; Gait pattern; Image frames; Light-Colored; Low-cost solution; Lower frequencies; Monocular video; Motor function; Parkinson's disease; Principal Components; Stride length; Vision based; Walking velocity; Computer aided analysis; Computer vision; Digital cameras; Frequency bands; Gait analysis; Medical computing; Neurodegenerative diseases; Power spectrum; Video cameras; Principal component analysis; Parkinsonia; algorithm; article; gait; human; methodology; nonlinear system; Parkinson disease; pathophysiology; principal component analysis; reproducibility; theoretical model; videorecording; walking; Algorithms; Gait; Humans; Models, Theoretical; Nonlinear Dynamics; Parkinson Disease; Principal Component Analysis; Reproducibility of Results; Research Design; Videotape Recording; Walking
• Online Access: https://scholarbank.nus.edu.sg/handle/10635/181624
• Institution: National University of Singapore

10.1186/1475-925X-10-99