Abstract
This paper presents a novel silhouette-based feature for vision-based human action recognition, which relies on the contour of the silhouette and a radial scheme. Its low-dimensionality and ease of extraction result in an outstanding proficiency for real-time scenarios. This feature is used in a learning algorithm that by means of model fusion of multiple camera streams builds a bag of key poses, which serves as a dictionary of known poses and allows converting the training sequences into sequences of key poses. These are used in order to perform action recognition by means of a sequence matching algorithm. Experimentation on three different datasets returns high and stable recognition rates. To the best of our knowledge, this paper presents the highest results so far on the MuHAVi-MAS dataset. Real-time suitability is given, since the method easily performs above video frequency. Therefore, the related requirements that applications as ambient-assisted living services impose are successfully fulfilled.
Highlights
Its low-dimensionality and ease of extraction result in an outstanding proficiency for real-time scenarios. This feature is used in a learning algorithm that by means of model fusion of multiple camera streams builds a bag of key poses, which serves as a dictionary of known poses and allows converting the training sequences into sequences of key poses
Human action recognition has been in great demand in the field of pattern recognition, given its direct relation to video surveillance, human-computer interaction, and ambientassisted living (AAL), among other application scenarios
The current proposal builds upon earlier work, where we have presented a human action recognition method based on silhouettes and sequences of key poses, which shows to be suitable for real-time scenarios and specially robust to actor variances [5]
Summary
Human action recognition has been in great demand in the field of pattern recognition, given its direct relation to video surveillance, human-computer interaction, and ambientassisted living (AAL), among other application scenarios In the latter, human behavior analysis (HBA), in which human action recognition plays a fundamental role, can endow smart home services with the required “smartness” needed to perform fall detection, intelligent safety services (closing a door or an open tap), or activities of daily living (ADL) recognition. Upon these detection stages, AAL services may learn subjects’ routines, diets, and even personal hygiene habits, which allow providing useful and proactive services. Simpler 2D-based methods fail to achieve the same recognition robustness [4]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have