MGAP applications in machine perception

Heung Nam Kim, Mary Jane Irwin, Robert Michael Owens

Research output: Contribution to conferencePaper

9 Citations (Scopus)

Abstract

Since image processing tasks in machine perception are computationally intensive, massively parallel processing is often employed to exploit the inherent parallelism. Some pioneering researchers have developed massively parallel processing systems including the CLIP family, the MPP, and the CM. All of these systems, however, are hard to use in machine perception systems because of their expensiveness and physical size. To tackle these problems we developed an inexpensive and easily portable massively parallel processing system, the MGAP (Micro Grained Array Processor). The MGAP is a very fine-grained, massively parallel, programmable array processor which is designed to be used as a low-cost massively parallel co-processor board in a desk-top workstation. In this paper, we discuss the versatile applications of the MGAP for image processing subtasks including an efficient histogramming algorithm, the systolic 2-D Discrete Cosine Transform (DCT), and the Dynamic Space Warping Algorithm (DSWA).

Original languageEnglish (US)
Pages67-73
Number of pages7
StatePublished - Dec 1 1995
EventProceedings of the Conference on Computer Architectures for Machine Perception, CAMP'95. - Como, Italy
Duration: Sep 18 1995Sep 20 1995

Other

OtherProceedings of the Conference on Computer Architectures for Machine Perception, CAMP'95.
CityComo, Italy
Period9/18/959/20/95

Fingerprint

Parallel processing systems
Image processing
Discrete cosine transforms
Processing
Costs

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Cite this

Kim, H. N., Irwin, M. J., & Owens, R. M. (1995). MGAP applications in machine perception. 67-73. Paper presented at Proceedings of the Conference on Computer Architectures for Machine Perception, CAMP'95., Como, Italy, .
Kim, Heung Nam ; Irwin, Mary Jane ; Owens, Robert Michael. / MGAP applications in machine perception. Paper presented at Proceedings of the Conference on Computer Architectures for Machine Perception, CAMP'95., Como, Italy, .7 p.
@conference{33927ecf73a3447c89f816f59b31d673,
title = "MGAP applications in machine perception",
abstract = "Since image processing tasks in machine perception are computationally intensive, massively parallel processing is often employed to exploit the inherent parallelism. Some pioneering researchers have developed massively parallel processing systems including the CLIP family, the MPP, and the CM. All of these systems, however, are hard to use in machine perception systems because of their expensiveness and physical size. To tackle these problems we developed an inexpensive and easily portable massively parallel processing system, the MGAP (Micro Grained Array Processor). The MGAP is a very fine-grained, massively parallel, programmable array processor which is designed to be used as a low-cost massively parallel co-processor board in a desk-top workstation. In this paper, we discuss the versatile applications of the MGAP for image processing subtasks including an efficient histogramming algorithm, the systolic 2-D Discrete Cosine Transform (DCT), and the Dynamic Space Warping Algorithm (DSWA).",
author = "Kim, {Heung Nam} and Irwin, {Mary Jane} and Owens, {Robert Michael}",
year = "1995",
month = "12",
day = "1",
language = "English (US)",
pages = "67--73",
note = "Proceedings of the Conference on Computer Architectures for Machine Perception, CAMP'95. ; Conference date: 18-09-1995 Through 20-09-1995",

}

Kim, HN, Irwin, MJ & Owens, RM 1995, 'MGAP applications in machine perception', Paper presented at Proceedings of the Conference on Computer Architectures for Machine Perception, CAMP'95., Como, Italy, 9/18/95 - 9/20/95 pp. 67-73.

MGAP applications in machine perception. / Kim, Heung Nam; Irwin, Mary Jane; Owens, Robert Michael.

1995. 67-73 Paper presented at Proceedings of the Conference on Computer Architectures for Machine Perception, CAMP'95., Como, Italy, .

Research output: Contribution to conferencePaper

TY - CONF

T1 - MGAP applications in machine perception

AU - Kim, Heung Nam

AU - Irwin, Mary Jane

AU - Owens, Robert Michael

PY - 1995/12/1

Y1 - 1995/12/1

N2 - Since image processing tasks in machine perception are computationally intensive, massively parallel processing is often employed to exploit the inherent parallelism. Some pioneering researchers have developed massively parallel processing systems including the CLIP family, the MPP, and the CM. All of these systems, however, are hard to use in machine perception systems because of their expensiveness and physical size. To tackle these problems we developed an inexpensive and easily portable massively parallel processing system, the MGAP (Micro Grained Array Processor). The MGAP is a very fine-grained, massively parallel, programmable array processor which is designed to be used as a low-cost massively parallel co-processor board in a desk-top workstation. In this paper, we discuss the versatile applications of the MGAP for image processing subtasks including an efficient histogramming algorithm, the systolic 2-D Discrete Cosine Transform (DCT), and the Dynamic Space Warping Algorithm (DSWA).

AB - Since image processing tasks in machine perception are computationally intensive, massively parallel processing is often employed to exploit the inherent parallelism. Some pioneering researchers have developed massively parallel processing systems including the CLIP family, the MPP, and the CM. All of these systems, however, are hard to use in machine perception systems because of their expensiveness and physical size. To tackle these problems we developed an inexpensive and easily portable massively parallel processing system, the MGAP (Micro Grained Array Processor). The MGAP is a very fine-grained, massively parallel, programmable array processor which is designed to be used as a low-cost massively parallel co-processor board in a desk-top workstation. In this paper, we discuss the versatile applications of the MGAP for image processing subtasks including an efficient histogramming algorithm, the systolic 2-D Discrete Cosine Transform (DCT), and the Dynamic Space Warping Algorithm (DSWA).

UR - http://www.scopus.com/inward/record.url?scp=0029546726&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029546726&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0029546726

SP - 67

EP - 73

ER -

Kim HN, Irwin MJ, Owens RM. MGAP applications in machine perception. 1995. Paper presented at Proceedings of the Conference on Computer Architectures for Machine Perception, CAMP'95., Como, Italy, .