Stream processing of moment invariants for real-time classifiers

C. H. Messom; A. L.C. Barczak

doi:10.1109/ICARA.2000.4804024

Stream processing of moment invariants for real-time classifiers

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research › peer-review

Abstract

This paper introduces a general purpose graphicsprocessing unit (GPGPU) stream processing implementation ofmoment invariants using an integral image or summed area tableapproach. Summed area tables have been used to help attainreal-time performance for some classifier systems, however dueto the computational complexity of moment invariants, a highthroughput computational platform is required to obtain real-time processing. The stream programming algorithm ispresented and its performance is evaluated and compared withalternate CPU based approaches. The significant performancegains means that moment invariant classifiers can beimplemented for real-time performance on a GPGPU that wouldnot be possible on current CPU platforms.

Original language	English
Title of host publication	ICARA 2009 - Proceedings of the 4th International Conference on Autonomous Robots and Agents
Publisher	IEEE
Pages	233-238
Number of pages	6
ISBN (Print)	9781424427130
DOIs	https://doi.org/10.1109/ICARA.2000.4804024
Publication status	Published - 2009
Externally published	Yes
Event	4th International Conference on Autonomous Robots and Agents, ICARA 2009 - Wellington, New Zealand Duration: 10 Feb 2009 → 12 Feb 2009 Conference number: 4th

Publication series

Name	ICARA 2009 - Proceedings of the 4th International Conference on Autonomous Robots and Agents

Conference

Conference	4th International Conference on Autonomous Robots and Agents, ICARA 2009
Abbreviated title	ICARA 2009
Country/Territory	New Zealand
City	Wellington
Period	10/02/09 → 12/02/09

Access to Document

10.1109/ICARA.2000.4804024

Cite this

Messom, C. H., & Barczak, A. L. C. (2009). Stream processing of moment invariants for real-time classifiers. In ICARA 2009 - Proceedings of the 4th International Conference on Autonomous Robots and Agents (pp. 233-238). Article 4804024 (ICARA 2009 - Proceedings of the 4th International Conference on Autonomous Robots and Agents). IEEE. https://doi.org/10.1109/ICARA.2000.4804024

@inproceedings{eeac28955acb4c9a82aae1a3c8b8515a,

title = "Stream processing of moment invariants for real-time classifiers",

abstract = "This paper introduces a general purpose graphicsprocessing unit (GPGPU) stream processing implementation ofmoment invariants using an integral image or summed area tableapproach. Summed area tables have been used to help attainreal-time performance for some classifier systems, however dueto the computational complexity of moment invariants, a highthroughput computational platform is required to obtain real-time processing. The stream programming algorithm ispresented and its performance is evaluated and compared withalternate CPU based approaches. The significant performancegains means that moment invariant classifiers can beimplemented for real-time performance on a GPGPU that wouldnot be possible on current CPU platforms.",

author = "Messom, {C. H.} and Barczak, {A. L.C.}",

year = "2009",

doi = "10.1109/ICARA.2000.4804024",

language = "English",

isbn = "9781424427130",

series = "ICARA 2009 - Proceedings of the 4th International Conference on Autonomous Robots and Agents",

publisher = "IEEE",

pages = "233--238",

booktitle = "ICARA 2009 - Proceedings of the 4th International Conference on Autonomous Robots and Agents",

note = "4th International Conference on Autonomous Robots and Agents, ICARA 2009, ICARA 2009 ; Conference date: 10-02-2009 Through 12-02-2009",

}

Messom, CH & Barczak, ALC 2009, Stream processing of moment invariants for real-time classifiers. in ICARA 2009 - Proceedings of the 4th International Conference on Autonomous Robots and Agents., 4804024, ICARA 2009 - Proceedings of the 4th International Conference on Autonomous Robots and Agents, IEEE, pp. 233-238, 4th International Conference on Autonomous Robots and Agents, ICARA 2009, Wellington, New Zealand, 10/02/09. https://doi.org/10.1109/ICARA.2000.4804024

Stream processing of moment invariants for real-time classifiers. / Messom, C. H.; Barczak, A. L.C.
ICARA 2009 - Proceedings of the 4th International Conference on Autonomous Robots and Agents. IEEE, 2009. p. 233-238 4804024 (ICARA 2009 - Proceedings of the 4th International Conference on Autonomous Robots and Agents).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research › peer-review

TY - GEN

T1 - Stream processing of moment invariants for real-time classifiers

AU - Messom, C. H.

AU - Barczak, A. L.C.

N1 - Conference code: 4th

PY - 2009

Y1 - 2009

N2 - This paper introduces a general purpose graphicsprocessing unit (GPGPU) stream processing implementation ofmoment invariants using an integral image or summed area tableapproach. Summed area tables have been used to help attainreal-time performance for some classifier systems, however dueto the computational complexity of moment invariants, a highthroughput computational platform is required to obtain real-time processing. The stream programming algorithm ispresented and its performance is evaluated and compared withalternate CPU based approaches. The significant performancegains means that moment invariant classifiers can beimplemented for real-time performance on a GPGPU that wouldnot be possible on current CPU platforms.

AB - This paper introduces a general purpose graphicsprocessing unit (GPGPU) stream processing implementation ofmoment invariants using an integral image or summed area tableapproach. Summed area tables have been used to help attainreal-time performance for some classifier systems, however dueto the computational complexity of moment invariants, a highthroughput computational platform is required to obtain real-time processing. The stream programming algorithm ispresented and its performance is evaluated and compared withalternate CPU based approaches. The significant performancegains means that moment invariant classifiers can beimplemented for real-time performance on a GPGPU that wouldnot be possible on current CPU platforms.

UR - http://www.scopus.com/inward/record.url?scp=66149161806&partnerID=8YFLogxK

U2 - 10.1109/ICARA.2000.4804024

DO - 10.1109/ICARA.2000.4804024

M3 - Conference contribution

AN - SCOPUS:66149161806

SN - 9781424427130

T3 - ICARA 2009 - Proceedings of the 4th International Conference on Autonomous Robots and Agents

SP - 233

EP - 238

BT - ICARA 2009 - Proceedings of the 4th International Conference on Autonomous Robots and Agents

PB - IEEE

T2 - 4th International Conference on Autonomous Robots and Agents, ICARA 2009

Y2 - 10 February 2009 through 12 February 2009

ER -

Stream processing of moment invariants for real-time classifiers

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this