Motion analysis on the micro grained array processor

Heung Nam Kim, Mary Jane Irwin, Robert Michael Owens

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Motion analysis plays a key role in video coding (e.g., video telephone, MPEG, HDTV) and computer vision systems (e.g., image segmentation, structure from motion). Motion estimation methods can be classified into three groups - matching-based, gradient-based, and frequency-based methods. The block matching algorithm (BMA) has been widely used for region matching in image coding, for example in MPEG (Motion Picture Expert's Group). Optical flow computation based on the spatio-temporal constraint equation has been broadly used in image segmentation to compute each pixel's velocity on a moving object. For both of these tasks, dedicated ASIC systems have been developed and widely used. Unfortunately, such systems have the disadvantage of restricted adaptability. The Micro Grained Array Processor (MGAP), which is a fine-grained, mesh-connected, SIMD array processor being developed at Penn State University, can provide a more regular, flexible, and efficient approach for solving, in real time, these two important computations. In this paper, we propose a new data flow scheme for an efficient, systolic, full-search BMA on programmable array processors so that we can process as many adjacent template blocks as possible in unison in order to reduce the data memory accesses. In particular we present an efficient implementation of the BMA on the MGAP. As a result, the BMA for the MPEG SIF video format (352 × 240 pixels) with a block size of 16 × 16 pixels, a displacement range of 16 pixels, and frame rate of 30 frames/sec can be computed at real-time processing rates on the MGAP. We also show a real-time mapping to the MGAP of the optical flow computation for images of size 256 × 256 pixels.

Original languageEnglish (US)
Pages (from-to)101-110
Number of pages10
JournalReal-Time Imaging
Volume3
Issue number2
StatePublished - Dec 1 1997

Fingerprint

Parallel processing systems
Pixels
Motion pictures
Optical flows
Image coding
Image segmentation
High definition television
Motion estimation
Application specific integrated circuits
Telephone
Computer vision
Motion analysis
Data storage equipment
Processing

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Kim, H. N., Irwin, M. J., & Owens, R. M. (1997). Motion analysis on the micro grained array processor. Real-Time Imaging, 3(2), 101-110.
Kim, Heung Nam ; Irwin, Mary Jane ; Owens, Robert Michael. / Motion analysis on the micro grained array processor. In: Real-Time Imaging. 1997 ; Vol. 3, No. 2. pp. 101-110.
@article{6811be7d07404cd78fcfabda55430b12,
title = "Motion analysis on the micro grained array processor",
abstract = "Motion analysis plays a key role in video coding (e.g., video telephone, MPEG, HDTV) and computer vision systems (e.g., image segmentation, structure from motion). Motion estimation methods can be classified into three groups - matching-based, gradient-based, and frequency-based methods. The block matching algorithm (BMA) has been widely used for region matching in image coding, for example in MPEG (Motion Picture Expert's Group). Optical flow computation based on the spatio-temporal constraint equation has been broadly used in image segmentation to compute each pixel's velocity on a moving object. For both of these tasks, dedicated ASIC systems have been developed and widely used. Unfortunately, such systems have the disadvantage of restricted adaptability. The Micro Grained Array Processor (MGAP), which is a fine-grained, mesh-connected, SIMD array processor being developed at Penn State University, can provide a more regular, flexible, and efficient approach for solving, in real time, these two important computations. In this paper, we propose a new data flow scheme for an efficient, systolic, full-search BMA on programmable array processors so that we can process as many adjacent template blocks as possible in unison in order to reduce the data memory accesses. In particular we present an efficient implementation of the BMA on the MGAP. As a result, the BMA for the MPEG SIF video format (352 × 240 pixels) with a block size of 16 × 16 pixels, a displacement range of 16 pixels, and frame rate of 30 frames/sec can be computed at real-time processing rates on the MGAP. We also show a real-time mapping to the MGAP of the optical flow computation for images of size 256 × 256 pixels.",
author = "Kim, {Heung Nam} and Irwin, {Mary Jane} and Owens, {Robert Michael}",
year = "1997",
month = "12",
day = "1",
language = "English (US)",
volume = "3",
pages = "101--110",
journal = "Real-Time Imaging",
issn = "1007-2014",
publisher = "Academic Press Inc.",
number = "2",

}

Kim, HN, Irwin, MJ & Owens, RM 1997, 'Motion analysis on the micro grained array processor', Real-Time Imaging, vol. 3, no. 2, pp. 101-110.

Motion analysis on the micro grained array processor. / Kim, Heung Nam; Irwin, Mary Jane; Owens, Robert Michael.

In: Real-Time Imaging, Vol. 3, No. 2, 01.12.1997, p. 101-110.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Motion analysis on the micro grained array processor

AU - Kim, Heung Nam

AU - Irwin, Mary Jane

AU - Owens, Robert Michael

PY - 1997/12/1

Y1 - 1997/12/1

N2 - Motion analysis plays a key role in video coding (e.g., video telephone, MPEG, HDTV) and computer vision systems (e.g., image segmentation, structure from motion). Motion estimation methods can be classified into three groups - matching-based, gradient-based, and frequency-based methods. The block matching algorithm (BMA) has been widely used for region matching in image coding, for example in MPEG (Motion Picture Expert's Group). Optical flow computation based on the spatio-temporal constraint equation has been broadly used in image segmentation to compute each pixel's velocity on a moving object. For both of these tasks, dedicated ASIC systems have been developed and widely used. Unfortunately, such systems have the disadvantage of restricted adaptability. The Micro Grained Array Processor (MGAP), which is a fine-grained, mesh-connected, SIMD array processor being developed at Penn State University, can provide a more regular, flexible, and efficient approach for solving, in real time, these two important computations. In this paper, we propose a new data flow scheme for an efficient, systolic, full-search BMA on programmable array processors so that we can process as many adjacent template blocks as possible in unison in order to reduce the data memory accesses. In particular we present an efficient implementation of the BMA on the MGAP. As a result, the BMA for the MPEG SIF video format (352 × 240 pixels) with a block size of 16 × 16 pixels, a displacement range of 16 pixels, and frame rate of 30 frames/sec can be computed at real-time processing rates on the MGAP. We also show a real-time mapping to the MGAP of the optical flow computation for images of size 256 × 256 pixels.

AB - Motion analysis plays a key role in video coding (e.g., video telephone, MPEG, HDTV) and computer vision systems (e.g., image segmentation, structure from motion). Motion estimation methods can be classified into three groups - matching-based, gradient-based, and frequency-based methods. The block matching algorithm (BMA) has been widely used for region matching in image coding, for example in MPEG (Motion Picture Expert's Group). Optical flow computation based on the spatio-temporal constraint equation has been broadly used in image segmentation to compute each pixel's velocity on a moving object. For both of these tasks, dedicated ASIC systems have been developed and widely used. Unfortunately, such systems have the disadvantage of restricted adaptability. The Micro Grained Array Processor (MGAP), which is a fine-grained, mesh-connected, SIMD array processor being developed at Penn State University, can provide a more regular, flexible, and efficient approach for solving, in real time, these two important computations. In this paper, we propose a new data flow scheme for an efficient, systolic, full-search BMA on programmable array processors so that we can process as many adjacent template blocks as possible in unison in order to reduce the data memory accesses. In particular we present an efficient implementation of the BMA on the MGAP. As a result, the BMA for the MPEG SIF video format (352 × 240 pixels) with a block size of 16 × 16 pixels, a displacement range of 16 pixels, and frame rate of 30 frames/sec can be computed at real-time processing rates on the MGAP. We also show a real-time mapping to the MGAP of the optical flow computation for images of size 256 × 256 pixels.

UR - http://www.scopus.com/inward/record.url?scp=0031122135&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031122135&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0031122135

VL - 3

SP - 101

EP - 110

JO - Real-Time Imaging

JF - Real-Time Imaging

SN - 1007-2014

IS - 2

ER -

Kim HN, Irwin MJ, Owens RM. Motion analysis on the micro grained array processor. Real-Time Imaging. 1997 Dec 1;3(2):101-110.