Abstract
Human action analysis has recently received growing interest from vision researchers. Since it is often insufficient for a single type of feature derived from action videos to characterize variations among different motions, two complementary types of features are combined for better action representation with early fusion, namely depthmap-based features (HON4D) and skeleton-based features (Fourier Temporal Pyramid). Then, SVM is applied to classify actions. The proposed approach is tested on public benchmark dataset-MSR Action3D, and the experimental evaluations demonstrate that fusion of multiple features help to improve performance significantly, compared with any single feature type.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.