Confidence-driven architecture for real-time vision processing and its application to efficient vision-based human motion sensing

Hiromasa Yoshimoto, Naoto Date, Daisaku Arita, Rin-Ichiro Taniguchi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

In this paper, we discuss a real-time vision architecture which provides a mechanism of controlling trade-off between the accuracy and the latency of vision systems. In vision systems, to acquire accurate information from input-images, the huge amount of computation power is usually required. On the other hand, to realize real-time processing, we must reduce the latency. Therefore, under given hardware resources, we must make difficult trade-off between the accuracy and the latency so that the quality of the system's output keeps appropriate. To solve the problem, we propose confidence-driven scheme, which enables us to control the trade-off dynamically and easily without rebuilding vision systems. In the confidence-driven architecture, the trade-off can be controlled by specifying a generalized parameter called confidence, which relatively indicates how accurate the analysis should be. Here, we present the concept of confidence-driven architecture, and then, we show a shared memory which uses confidence-driven scheme. Using confidence-driven memory, we can use imprecise computation model to reduce the latency without a large decrease of accuracy.

Original languageEnglish
Title of host publicationProceedings of the 17th International Conference on Pattern Recognition, ICPR 2004
EditorsJ. Kittler, M. Petrou, M. Nixon
Pages736-740
Number of pages5
Volume1
DOIs
Publication statusPublished - 2004
EventProceedings of the 17th International Conference on Pattern Recognition, ICPR 2004 - Cambridge, United Kingdom
Duration: Aug 23 2004Aug 26 2004

Other

OtherProceedings of the 17th International Conference on Pattern Recognition, ICPR 2004
CountryUnited Kingdom
CityCambridge
Period8/23/048/26/04

Fingerprint

Processing
Data storage equipment
Hardware

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Computer Vision and Pattern Recognition
  • Hardware and Architecture

Cite this

Yoshimoto, H., Date, N., Arita, D., & Taniguchi, R-I. (2004). Confidence-driven architecture for real-time vision processing and its application to efficient vision-based human motion sensing. In J. Kittler, M. Petrou, & M. Nixon (Eds.), Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004 (Vol. 1, pp. 736-740) https://doi.org/10.1109/ICPR.2004.1334294

Confidence-driven architecture for real-time vision processing and its application to efficient vision-based human motion sensing. / Yoshimoto, Hiromasa; Date, Naoto; Arita, Daisaku; Taniguchi, Rin-Ichiro.

Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004. ed. / J. Kittler; M. Petrou; M. Nixon. Vol. 1 2004. p. 736-740.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yoshimoto, H, Date, N, Arita, D & Taniguchi, R-I 2004, Confidence-driven architecture for real-time vision processing and its application to efficient vision-based human motion sensing. in J Kittler, M Petrou & M Nixon (eds), Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004. vol. 1, pp. 736-740, Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004, Cambridge, United Kingdom, 8/23/04. https://doi.org/10.1109/ICPR.2004.1334294
Yoshimoto H, Date N, Arita D, Taniguchi R-I. Confidence-driven architecture for real-time vision processing and its application to efficient vision-based human motion sensing. In Kittler J, Petrou M, Nixon M, editors, Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004. Vol. 1. 2004. p. 736-740 https://doi.org/10.1109/ICPR.2004.1334294
Yoshimoto, Hiromasa ; Date, Naoto ; Arita, Daisaku ; Taniguchi, Rin-Ichiro. / Confidence-driven architecture for real-time vision processing and its application to efficient vision-based human motion sensing. Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004. editor / J. Kittler ; M. Petrou ; M. Nixon. Vol. 1 2004. pp. 736-740
@inproceedings{05f77448d25a4e53a22ce2769fb635ab,
title = "Confidence-driven architecture for real-time vision processing and its application to efficient vision-based human motion sensing",
abstract = "In this paper, we discuss a real-time vision architecture which provides a mechanism of controlling trade-off between the accuracy and the latency of vision systems. In vision systems, to acquire accurate information from input-images, the huge amount of computation power is usually required. On the other hand, to realize real-time processing, we must reduce the latency. Therefore, under given hardware resources, we must make difficult trade-off between the accuracy and the latency so that the quality of the system's output keeps appropriate. To solve the problem, we propose confidence-driven scheme, which enables us to control the trade-off dynamically and easily without rebuilding vision systems. In the confidence-driven architecture, the trade-off can be controlled by specifying a generalized parameter called confidence, which relatively indicates how accurate the analysis should be. Here, we present the concept of confidence-driven architecture, and then, we show a shared memory which uses confidence-driven scheme. Using confidence-driven memory, we can use imprecise computation model to reduce the latency without a large decrease of accuracy.",
author = "Hiromasa Yoshimoto and Naoto Date and Daisaku Arita and Rin-Ichiro Taniguchi",
year = "2004",
doi = "10.1109/ICPR.2004.1334294",
language = "English",
isbn = "0769521282",
volume = "1",
pages = "736--740",
editor = "J. Kittler and M. Petrou and M. Nixon",
booktitle = "Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004",

}

TY - GEN

T1 - Confidence-driven architecture for real-time vision processing and its application to efficient vision-based human motion sensing

AU - Yoshimoto, Hiromasa

AU - Date, Naoto

AU - Arita, Daisaku

AU - Taniguchi, Rin-Ichiro

PY - 2004

Y1 - 2004

N2 - In this paper, we discuss a real-time vision architecture which provides a mechanism of controlling trade-off between the accuracy and the latency of vision systems. In vision systems, to acquire accurate information from input-images, the huge amount of computation power is usually required. On the other hand, to realize real-time processing, we must reduce the latency. Therefore, under given hardware resources, we must make difficult trade-off between the accuracy and the latency so that the quality of the system's output keeps appropriate. To solve the problem, we propose confidence-driven scheme, which enables us to control the trade-off dynamically and easily without rebuilding vision systems. In the confidence-driven architecture, the trade-off can be controlled by specifying a generalized parameter called confidence, which relatively indicates how accurate the analysis should be. Here, we present the concept of confidence-driven architecture, and then, we show a shared memory which uses confidence-driven scheme. Using confidence-driven memory, we can use imprecise computation model to reduce the latency without a large decrease of accuracy.

AB - In this paper, we discuss a real-time vision architecture which provides a mechanism of controlling trade-off between the accuracy and the latency of vision systems. In vision systems, to acquire accurate information from input-images, the huge amount of computation power is usually required. On the other hand, to realize real-time processing, we must reduce the latency. Therefore, under given hardware resources, we must make difficult trade-off between the accuracy and the latency so that the quality of the system's output keeps appropriate. To solve the problem, we propose confidence-driven scheme, which enables us to control the trade-off dynamically and easily without rebuilding vision systems. In the confidence-driven architecture, the trade-off can be controlled by specifying a generalized parameter called confidence, which relatively indicates how accurate the analysis should be. Here, we present the concept of confidence-driven architecture, and then, we show a shared memory which uses confidence-driven scheme. Using confidence-driven memory, we can use imprecise computation model to reduce the latency without a large decrease of accuracy.

UR - http://www.scopus.com/inward/record.url?scp=10044270062&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=10044270062&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2004.1334294

DO - 10.1109/ICPR.2004.1334294

M3 - Conference contribution

AN - SCOPUS:10044270062

SN - 0769521282

VL - 1

SP - 736

EP - 740

BT - Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004

A2 - Kittler, J.

A2 - Petrou, M.

A2 - Nixon, M.

ER -