Live demonstration: A bio-inspired event-based size and position invariant human posture recognition algorithm

Author

Chen, Shoushun ; Martini, Berin ; Culurciello, Eugenio

Author_Institution

Electr. Eng. Dept., Yale Univ., New Haven, CT, USA

fYear

2009

fDate

24-27 May 2009

Firstpage

779

Lastpage

779

Abstract

We demonstrate a realtime human postures recognition platform. The algorithm employs temporal difference imaging between video sequences as input and then decompose the contour of the active object into vectorial line segments. A scheme based on simplified line segment Hausdorff distance combined with projection histograms is proposed to achieve size and position invariance recognition. Inspired by the hierarchical model of human visual system, the whole classification is described as a coarse to fine procedure. 88% average realtime recognition rate is achieved in the experiment.

Keywords

image sequences; object recognition; video signal processing; bio-inspired event-based position invariant; bio-inspired event-based size invariant; human posture recognition algorithm; human visual system; line segment Hausdorff distance; live demonstration; projection histograms; vectorial line segments; video sequences; Application software; CMOS image sensors; Cellular phones; Computed tomography; Computer displays; Hardware; Humans; Image segmentation; Image sensors; Visual system;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 2009. ISCAS 2009. IEEE International Symposium on

Conference_Location

Taipei

Print_ISBN

978-1-4244-3827-3

Electronic_ISBN

978-1-4244-3828-0

Type

conf

DOI

10.1109/ISCAS.2009.5117865

Filename

5117865