Optimal periodic memory allocation for image processing with multiple windows

Yasuhiro Kobayashi; Masanori Hariyama; Michitaka Kameyama

doi:10.1109/TVLSI.2008.2004547

Optimal periodic memory allocation for image processing with multiple windows

Yasuhiro Kobayashi, Masanori Hariyama, Michitaka Kameyama

INF - Computer and Mathematical Sciences

Research output: Contribution to journal › Article

4 Citations (Scopus)

Abstract

One major issue in designing image processors is to design a memory system that supports parallel access with a simple interconnection network. This paper presents an efficient memory allocation to minimize the number of memory modules and processing elements with a parallel access capability when multiple windows with arbitrary shapes are specified. This paper also presents an efficient search method based on regularity of window-type image processing. We give some practical examples including a stereo-matching processor for acquiring 3-D information, and an optical-flow processor for motion estimation. These examples show that the numbers of memory modules are reduced to 2.7% and 10%, respectively, in comparison with a basic approach. It is also shown that the search time is less than 1 ms for practical image sizes and window sizes.

Original language	English
Article number	4757197
Pages (from-to)	403-416
Number of pages	14
Journal	IEEE Transactions on Very Large Scale Integration (VLSI) Systems
Volume	17
Issue number	3
DOIs	https://doi.org/10.1109/TVLSI.2008.2004547
Publication status	Published - 2009 Mar 1

Keywords

Image processing
Memory design
Optimization
Parallel processors

ASJC Scopus subject areas

Software
Hardware and Architecture
Electrical and Electronic Engineering

Access to Document

10.1109/TVLSI.2008.2004547

Fingerprint Dive into the research topics of 'Optimal periodic memory allocation for image processing with multiple windows'. Together they form a unique fingerprint.

Cite this

@article{fafe70661f784def9db07e4fc60f8dfd,

title = "Optimal periodic memory allocation for image processing with multiple windows",

abstract = "One major issue in designing image processors is to design a memory system that supports parallel access with a simple interconnection network. This paper presents an efficient memory allocation to minimize the number of memory modules and processing elements with a parallel access capability when multiple windows with arbitrary shapes are specified. This paper also presents an efficient search method based on regularity of window-type image processing. We give some practical examples including a stereo-matching processor for acquiring 3-D information, and an optical-flow processor for motion estimation. These examples show that the numbers of memory modules are reduced to 2.7% and 10%, respectively, in comparison with a basic approach. It is also shown that the search time is less than 1 ms for practical image sizes and window sizes.",

keywords = "Image processing, Memory design, Optimization, Parallel processors",

author = "Yasuhiro Kobayashi and Masanori Hariyama and Michitaka Kameyama",

year = "2009",

month = mar,

day = "1",

doi = "10.1109/TVLSI.2008.2004547",

language = "English",

volume = "17",

pages = "403--416",

journal = "IEEE Transactions on Very Large Scale Integration (VLSI) Systems",

issn = "1063-8210",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "3",

}

TY - JOUR

T1 - Optimal periodic memory allocation for image processing with multiple windows

AU - Kobayashi, Yasuhiro

AU - Hariyama, Masanori

AU - Kameyama, Michitaka

PY - 2009/3/1

Y1 - 2009/3/1

N2 - One major issue in designing image processors is to design a memory system that supports parallel access with a simple interconnection network. This paper presents an efficient memory allocation to minimize the number of memory modules and processing elements with a parallel access capability when multiple windows with arbitrary shapes are specified. This paper also presents an efficient search method based on regularity of window-type image processing. We give some practical examples including a stereo-matching processor for acquiring 3-D information, and an optical-flow processor for motion estimation. These examples show that the numbers of memory modules are reduced to 2.7% and 10%, respectively, in comparison with a basic approach. It is also shown that the search time is less than 1 ms for practical image sizes and window sizes.

AB - One major issue in designing image processors is to design a memory system that supports parallel access with a simple interconnection network. This paper presents an efficient memory allocation to minimize the number of memory modules and processing elements with a parallel access capability when multiple windows with arbitrary shapes are specified. This paper also presents an efficient search method based on regularity of window-type image processing. We give some practical examples including a stereo-matching processor for acquiring 3-D information, and an optical-flow processor for motion estimation. These examples show that the numbers of memory modules are reduced to 2.7% and 10%, respectively, in comparison with a basic approach. It is also shown that the search time is less than 1 ms for practical image sizes and window sizes.

KW - Image processing

KW - Memory design

KW - Optimization

KW - Parallel processors

UR - http://www.scopus.com/inward/record.url?scp=63149159774&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=63149159774&partnerID=8YFLogxK

U2 - 10.1109/TVLSI.2008.2004547

DO - 10.1109/TVLSI.2008.2004547

M3 - Article

AN - SCOPUS:63149159774

VL - 17

SP - 403

EP - 416

JO - IEEE Transactions on Very Large Scale Integration (VLSI) Systems

JF - IEEE Transactions on Very Large Scale Integration (VLSI) Systems

SN - 1063-8210

IS - 3

M1 - 4757197

ER -