Presentation 2008-06-12
Hardware Implementation of Run-time Learning for Object Recognition
Kazunori KIMURA, Hiroyuki OCHI, Ryusuke MIYAMOTO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Cascade Particle Filter is one of the latest schemes which enables highly accurate object recognition. In order to apply the scheme to embedded applications such as surveillance, automobiles, and robotics, a specialized processor or hardware implementation is indispensable because of limitation of power consumption. In this paper we propose a hardware implementation of run-time learning process that is the most computationally intensive part of Cascade Particle Filter. Implementation result shows that the hardware on Virtex-5 FPGA achieves real-time processing at 30 frames per second.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) object recognition / Cascade Particle Filter / boosting / hardware implementation / run-time learning
Paper # SIS2008-5
Date of Issue

Conference Information
Committee SIS
Conference Date 2008/6/5(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 Smart Info-Media Systems (SIS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Hardware Implementation of Run-time Learning for Object Recognition
Sub Title (in English)
Keyword(1) object recognition
Keyword(2) Cascade Particle Filter
Keyword(3) boosting
Keyword(4) hardware implementation
Keyword(5) run-time learning
1st Author's Name Kazunori KIMURA
1st Author's Affiliation Dept. of Communications and Computer Engineering, Graduate School of Informatics, Kyoto Univ.()
2nd Author's Name Hiroyuki OCHI
2nd Author's Affiliation Dept. of Communications and Computer Engineering, Graduate School of Informatics, Kyoto Univ.
3rd Author's Name Ryusuke MIYAMOTO
3rd Author's Affiliation Dept. of Information Systems, Graduate School of Information Science, Nara Institute of Science and Technology
Date 2008-06-12
Paper # SIS2008-5
Volume (vol) vol.108
Number (no) 85
Page pp.pp.-
#Pages 6
Date of Issue