Presentation 2005-09-16
Bio-Inspired Camera System with FPGA
Yoshiki YAMAGUCHI, Noriyuki AIBE, Kazuya HAYASHI, Yorihisa YAMAMOTO, Ikuo YOSHIHARA, Moritoshi YASUNAGA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Bio-inspired camera system is an object tracking system based on two video cameras and three XILINX FPGAs. One camcorder is a wide-lens video camera, and captures over a wide range (panoramic view). The other is a zoom-lens camera, and magnifies a target object (closeup view) which is detected by the wide-lens video camera. In a panoramic view, FPGAs specify the location of the object to control servomotors because the tracking system must keep the zoom-lens camera trained on the object. In a closeup view, FPGAs recognize what the object is using a sample pattern database. In the current system, probabilistic neural network (PNN) and a mosaic-processing are used for the object recognition and the pre-processing, respectively. Thanks to the FPGA-based design, not only PNN and the mosaic-processing but other recognition techniques and pre-processing algorithms can be implemented onto the system also to adapt various images, targets, and situations.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) FPGA / image recognition / probabilistic neural network(PNN) / surveillance system
Paper # RECONF2005-49
Date of Issue

Conference Information
Committee RECONF
Conference Date 2005/9/9(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Reconfigurable Systems (RECONF)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Bio-Inspired Camera System with FPGA
Sub Title (in English)
Keyword(1) FPGA
Keyword(2) image recognition
Keyword(3) probabilistic neural network(PNN)
Keyword(4) surveillance system
1st Author's Name Yoshiki YAMAGUCHI
1st Author's Affiliation the Graduate School of Systems and Information Engineering, University of Tsukuba()
2nd Author's Name Noriyuki AIBE
2nd Author's Affiliation the Graduate School of Systems and Information Engineering, University of Tsukuba
3rd Author's Name Kazuya HAYASHI
3rd Author's Affiliation the Graduate School of Systems and Information Engineering, University of Tsukuba
4th Author's Name Yorihisa YAMAMOTO
4th Author's Affiliation Yamamoto System Design
5th Author's Name Ikuo YOSHIHARA
5th Author's Affiliation Faculty of Engineering, University of Miyazaki
6th Author's Name Moritoshi YASUNAGA
6th Author's Affiliation the Graduate School of Systems and Information Engineering, University of Tsukuba
Date 2005-09-16
Paper # RECONF2005-49
Volume (vol) vol.105
Number (no) 288
Page pp.pp.-
#Pages 6
Date of Issue