Presentation 2008/3/20
A VLSI Architecture of Parallel Hough Transform with Localized Voting Space Access
Masayuki GOTO, Kazuhiro NAKAMURA, Yoshikazu ASADA, Kazuyoshi TAKAGI, Naofumi TAKAGI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Hough transform is a computer vision algorithm, which detects lines and circles in a binary image. We propose a VLSI architecture for Hough transform. The architecture is memory efficient and suitable for embedded systems that require real-time performance and low-power. The architecture implements parallel Hough computation with localized voting space access. The voting process is besed on proposing patch-based image access order. This image access order enables the voting space access to be localized. This causes the number of indexes of voting memory in the circuit to be independent of image size. The necessary voting memory in the circuit can be reduced by about 97% on QVGA, and about 99% on SVGA compared with the circuit architecture in which localization is not considered.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Hough transform / ASIC / image processing / memory access localization / parallel Hough transform circuit
Paper # CPSY2007-93,DC2007-97
Date of Issue

Conference Information
Committee DC
Conference Date 2008/3/20(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 Dependable Computing (DC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A VLSI Architecture of Parallel Hough Transform with Localized Voting Space Access
Sub Title (in English)
Keyword(1) Hough transform
Keyword(2) ASIC
Keyword(3) image processing
Keyword(4) memory access localization
Keyword(5) parallel Hough transform circuit
1st Author's Name Masayuki GOTO
1st Author's Affiliation Graduate School of Information Science, Nagoya University()
2nd Author's Name Kazuhiro NAKAMURA
2nd Author's Affiliation Graduate School of Information Science, Nagoya University
3rd Author's Name Yoshikazu ASADA
3rd Author's Affiliation Graduate School of Information Science, Nagoya University
4th Author's Name Kazuyoshi TAKAGI
4th Author's Affiliation Graduate School of Information Science, Nagoya University
5th Author's Name Naofumi TAKAGI
5th Author's Affiliation Graduate School of Information Science, Nagoya University
Date 2008/3/20
Paper # CPSY2007-93,DC2007-97
Volume (vol) vol.107
Number (no) 559
Page pp.pp.-
#Pages 6
Date of Issue