Implementation of Multi-Agent Object Attention System Based on Biologically Inspired Attractor Selection

Ryoji HASHIMOTO; Tomoya MATSUMURA; Yoshihiro NOZATO; Kenji WATANABE; Takao ONOYE

doi:10.1093/ietfec/e91-a.10.2909

Implementation of Multi-Agent Object Attention System Based on Biologically Inspired Attractor Selection

Ryoji HASHIMOTO, Tomoya MATSUMURA, Yoshihiro NOZATO, Kenji WATANABE, Takao ONOYE

Full Text Views

0

Cite this

Summary :

A multi-agent object attention system is proposed, which is based on biologically inspired attractor selection model. Object attention is facilitated by using a video sequence and a depth map obtained through a compound-eye image sensor TOMBO. Robustness of the multi-agent system over environmental changes is enhanced by utilizing the biological model of adaptive response by attractor selection. To implement the proposed system, an efficient VLSI architecture is employed with reducing enormous computational costs and memory accesses required for depth map processing and multi-agent attractor selection process. According to the FPGA implementation result of the proposed object attention system, which is accomplished by using 7,063 slices, 640512 pixel input images can be processed in real-time with three agents at a rate of 9 fps in 48 MHz operation.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E91-A No.10 pp.2909-2917

Publication Date: 2008/10/01

Publicized

Online ISSN: 1745-1337

DOI: 10.1093/ietfec/e91-a.10.2909

Type of Manuscript: Special Section PAPER (Special Section on Smart Multimedia & Communication Systems)

Category: Video Processing Systems

Cite this

Copy

Ryoji HASHIMOTO, Tomoya MATSUMURA, Yoshihiro NOZATO, Kenji WATANABE, Takao ONOYE, "Implementation of Multi-Agent Object Attention System Based on Biologically Inspired Attractor Selection" in IEICE TRANSACTIONS on Fundamentals, vol. E91-A, no. 10, pp. 2909-2917, October 2008, doi: 10.1093/ietfec/e91-a.10.2909.
Abstract: A multi-agent object attention system is proposed, which is based on biologically inspired attractor selection model. Object attention is facilitated by using a video sequence and a depth map obtained through a compound-eye image sensor TOMBO. Robustness of the multi-agent system over environmental changes is enhanced by utilizing the biological model of adaptive response by attractor selection. To implement the proposed system, an efficient VLSI architecture is employed with reducing enormous computational costs and memory accesses required for depth map processing and multi-agent attractor selection process. According to the FPGA implementation result of the proposed object attention system, which is accomplished by using 7,063 slices, 640512 pixel input images can be processed in real-time with three agents at a rate of 9 fps in 48 MHz operation.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1093/ietfec/e91-a.10.2909/_p

Copy

@ARTICLE{e91-a_10_2909,
author={Ryoji HASHIMOTO, Tomoya MATSUMURA, Yoshihiro NOZATO, Kenji WATANABE, Takao ONOYE, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Implementation of Multi-Agent Object Attention System Based on Biologically Inspired Attractor Selection},
year={2008},
volume={E91-A},
number={10},
pages={2909-2917},
abstract={A multi-agent object attention system is proposed, which is based on biologically inspired attractor selection model. Object attention is facilitated by using a video sequence and a depth map obtained through a compound-eye image sensor TOMBO. Robustness of the multi-agent system over environmental changes is enhanced by utilizing the biological model of adaptive response by attractor selection. To implement the proposed system, an efficient VLSI architecture is employed with reducing enormous computational costs and memory accesses required for depth map processing and multi-agent attractor selection process. According to the FPGA implementation result of the proposed object attention system, which is accomplished by using 7,063 slices, 640512 pixel input images can be processed in real-time with three agents at a rate of 9 fps in 48 MHz operation.},
keywords={},
doi={10.1093/ietfec/e91-a.10.2909},
ISSN={1745-1337},
month={October},}

Copy

TY - JOUR
TI - Implementation of Multi-Agent Object Attention System Based on Biologically Inspired Attractor Selection
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 2909
EP - 2917
AU - Ryoji HASHIMOTO
AU - Tomoya MATSUMURA
AU - Yoshihiro NOZATO
AU - Kenji WATANABE
AU - Takao ONOYE
PY - 2008
DO - 10.1093/ietfec/e91-a.10.2909
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E91-A
IS - 10
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - October 2008
AB - A multi-agent object attention system is proposed, which is based on biologically inspired attractor selection model. Object attention is facilitated by using a video sequence and a depth map obtained through a compound-eye image sensor TOMBO. Robustness of the multi-agent system over environmental changes is enhanced by utilizing the biological model of adaptive response by attractor selection. To implement the proposed system, an efficient VLSI architecture is employed with reducing enormous computational costs and memory accesses required for depth map processing and multi-agent attractor selection process. According to the FPGA implementation result of the proposed object attention system, which is accomplished by using 7,063 slices, 640512 pixel input images can be processed in real-time with three agents at a rate of 9 fps in 48 MHz operation.
ER -