Publication: Silhouette-based human action recognition with a multi-class support vector machine
Loading...
Identifiers
Publication date
2018-05
Defense date
Advisors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
Institution Of Engineering And Technology (IET)
Impact
Export
Abstract
Computer vision systems have become increasingly popular, being used to solve a wide range of problems. In this paper, a computer vision algorithm with a support vector machine (SVM) classifier is presented. The work focuses on the recognition of human actions through computer vision, using a multi-camera dataset of human actions called MuHAVi. The algorithm uses a method to extract features, based on silhouettes. The challenge is that in MuHAVi these silhouettes are noisy and in many cases include shadows. As there are many actions that need to be recognised, we take a multiclass classification ap-proach that combines binary SVM classifiers. The results are compared with previous results on the same dataset and show a significant improvement, especially for recognising actions on a different view, obtaining overall accuracy of 85.5% and of 93.5% for leave-one-camera-out and leave-one-actor-out tests respectively.
Description
This paper has been presented at : 9th International Conference on Pattern Recognition Systems (ICPRS 2018)
Keywords
Bag of key poses, MuHAVi, SVM, Computer vision, Human action recognition
Bibliographic citation
González, L., Velastin, S.A y Acuña, G. (2018). Silhouette-based human action recognition with a multi-class support vector machine. In 9th International Conference on Pattern Recognition Systems (ICPRS 2018).