The basic assembly of skeletal models in the fall detection problem

• Published in: Kompʹûternaâ optika Vol. 47; no. 2; pp. 323 - 334
• Main Authors: Seredin, O.S., Kopylov, A.V., Surkov, E.E., Huang, S.-C.
• Format: Journal Article
• Language: English
• Published: Samara National Research University 01.04.2023
• Subjects: activity map; basic assembly; convolutional neural networks; featureless pattern recognition; pairwise similarity; skeletal model of human figure
• ISSN: 0134-2452; 2412-6179
• DOI: 10.18287/2412-6179-CO-1158

The paper considers the appliance of the featureless approach to the human activity recognition problem, which exclude the direct anthropomorphic and visual characteristics of human figure from further analysis and thus increase the privacy of the monitoring system. A generalized pairwise comparison function of two human skeletal models, invariant to the sensor type, is used to project the object of interest to the secondary feature space, formed by the basic assembly of skeletons. A sequence of such projections in time forms an activity map, which allows an application of deep learning methods based on convolution neural networks for activity recognition. The proper ordering of skeletal models in a basic assembly plays an important role in secondary space design. The study of ordering of the basic assembly by the shortest unclosed path algorithm and correspondent activity maps for video streams from the TST Fall Detection v2 database are presented.