An Energy Computing Method Inspired from Visual Cognitive Function for Dynamic Behavioural Detection in Video Frames

Zuojin Li, Jun Peng, Liukui Chen, Chen Gui and Lei Song
Additional contact information
Zuojin Li: Chongqing University of Science and Technology, Chongqing, China
Jun Peng: Chongqing University of Science and Technology, Chongqing, China
Liukui Chen: Chongqing University of Science and Technology, Chongqing, China
Chen Gui: Chongqing University of Science and Technology, Chongqing, China
Lei Song: Department of Computing, Unitec Institute of Technology, Mount Albert, New Zealand

International Journal of Cognitive Informatics and Natural Intelligence (IJCINI), 2014, vol. 8, issue 3, 1-12

Abstract: The brain visual cortical simple cells have strong response to notable edges with directivity and contrast of light and dark, as well as the non-classical receptive fields of the neurons in visual cortex that have inhibition function to small light-spot stimulation. Because of this property, human vision system contrast sensitivity tends to dynamic videos. This paper, based on biological visual features, constructs an energy-computing model for dynamic video behaviors analysis, and designs computing methods for strengthening selectivity to directions of edges and inhibiting energy of non-significant areas in the images. The experiment is conducted on 30,000 frames of dynamic behaviors in video and shows 90% accuracy, which proves that the proposed method is capable to simulate the function of visual cortex simple cells, i.e. the enhancement to directional selection, and the inhabitation function of non-classical receptive fields, as well as extract energy features of dynamic behaviors in video. This contributes a choice for computer image processing and improves the understanding of machine vision.

Date: 2014
References: Add references at CitEc
Citations:

Downloads: (external link)
http://services.igi-global.com/resolvedoi/resolve. ... 18/IJCINI.2014070101 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:igg:jcini0:v:8:y:2014:i:3:p:1-12

Access Statistics for this article

International Journal of Cognitive Informatics and Natural Intelligence (IJCINI) is currently edited by Kangshun Li

More articles in International Journal of Cognitive Informatics and Natural Intelligence (IJCINI) from IGI Global
Bibliographic data for series maintained by Journal Editor ().