Title: Slow feature action prototypes effect assessment in mechanism for recognition of biological movement ventral stream
Authors: Bardia Yousefi; Chu Kiong Loo
Addresses: Department of Artificial Intelligence, University of Malaya, Kuala Lumpur, Malaysia ' Department of Artificial Intelligence, University of Malaya, Kuala Lumpur, Malaysia
Abstract: In analysis of the brain and visual system functionality, scientific evidence points to two independent processing pathways in recognising biological movement, i.e. dorsal and ventral streams. Motion information generated in the dorsal processing stream is presented as fuzzy optical flow division while ventral processing stream with information of the object form is implemented as an active basis model. The recognition task however still requires decision-making and mutual interaction between these pathways. This process is done using slow features as action prototypes dictionary of biological movements. For motion information interaction, dorsal pathway guides the shared sketch algorithm that leads to decision-making for a more accurate outcome. Extreme learning machine classifier is used for decision-making unit kernel. The proposed approach is tested on the KTH human action database videos. Good performances are indicated compared to existing methods, with good interaction between dorsal and ventral processing streams.
Keywords: bio-inspired computation; stream interaction; ventral stream; dorsal streams; human action recognition; active basis model; ABM; fuzzy optical flow division; slow feature analysis; SFA; synergetic neural networks; SNNs; biological movement; movement recognition; motion information; slow features; action prototypes; extreme learning machine; ELM.
International Journal of Bio-Inspired Computation, 2016 Vol.8 No.6, pp.410 - 424
Received: 08 Feb 2014
Accepted: 18 Nov 2014
Published online: 05 Jan 2017 *