A dual fast and slow feature interaction in biologically inspired visual recognition of human action

Yousefi, Bardia and Loo, Chu Kiong (2018) A dual fast and slow feature interaction in biologically inspired visual recognition of human action. Applied Soft Computing, 62. pp. 57-72. ISSN 1568-4946, DOI https://doi.org/10.1016/j.asoc.2017.10.021.

Full text not available from this repository.
Official URL: https://doi.org/10.1016/j.asoc.2017.10.021


Computational neuroscience studies have examined the human visual system through functional magnetic resonance imaging (fMRI) and identified a model where the mammalian brain pursues two independent pathways for recognizing biological movement tasks. On the one hand, the dorsal stream analyzes the motion information by applying optical flow, which considers the fast features. On the other hand, the ventral stream analyzes the form information with slow features. The proposed approach suggests that the motion perception of the human visual system comprises fast and slow feature interactions to identify biological movements. The form features in the visual system follow the application of the active basis model (ABM) with incremental slow feature analysis (IncSFA). Episodic observation is required to extract the slowest features, whereas the fast features update the processing of motion information in every frame. Applying IncSFA provides an opportunity to abstract human actions and use action prototypes. However, the fast features are obtained from the optical flow division, which gives an opportunity to interact with the system as the final recognition is performed through a combination of the optical flow and ABM-IncSFA information and through the application of kernel extreme learning machine. Applying IncSFA into the ventral stream and involving slow and fast features in the recognition mechanism are the major contributions of this research. The two human action datasets for benchmarking (KTH and Weizmann) and the results highlight the promising performance of this approach in model modification.

Item Type: Article
Funders: This research was done under the High Impact Research (HIR) foundation grant: contract No. UM.C/HIR/MOHE/FCSIT/10, in University Malaya (UM), Malaysia
Uncontrolled Keywords: Biologically inspired model; Interaction between ventral and dorsal stream; Human action recognition; Incremental slow feature analysis; Extreme learning machine; Dual processing pathways
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Faculty of Computer Science & Information Technology
Depositing User: Ms. Juhaida Abd Rahim
Date Deposited: 12 Feb 2019 01:15
Last Modified: 12 Feb 2019 01:15
URI: http://eprints.um.edu.my/id/eprint/20258

Actions (login required)

View Item View Item