Situation-based dynamic frame-rate control for on-line object tracking

Yusuke Inoue, Takatsuau Ono, Koji Inouer

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

Abstract

On-line object tracking is an essential technology in computer vision. Object tracking systems need to reduce their energy consumption because the technology is increasingly being utilized for battery-operated systems, e.g., driving assist systems, smartphones, drones and so on. To tackle this problem, dynamic frame-rate optimization has been proposed. This approach optimizes the frame-rate on the basis of target object speed by taking into account the energy trade-off between the image capturing and tracking processes. In order to improve tracking accuracy, the approach selects a frame-rate based on a specific fixed value. However, the required parameters are different depending on the scene and content of the input video. In this paper, we propose a method to adaptively select parameters. Simulation results show the energy consumption is reduced by up to about 65.0%, and 45.0 % on average without critical tracking accuracy degradation.

Original languageEnglish
Title of host publication2018 Proceedings of the Japan-Africa Conference on Electronics, Communications, and Computations, JAC-ECC 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages119-122
Number of pages4
ISBN (Electronic)9781538692301
DOIs
Publication statusPublished - Apr 1 2019
Event2018 Japan-Africa Conference on Electronics, Communications, and Computations, JAC-ECC 2018 - Alexandria, Egypt
Duration: Dec 17 2018Dec 19 2018

Publication series

Name2018 Proceedings of the Japan-Africa Conference on Electronics, Communications, and Computations, JAC-ECC 2018

Conference

Conference2018 Japan-Africa Conference on Electronics, Communications, and Computations, JAC-ECC 2018
CountryEgypt
CityAlexandria
Period12/17/1812/19/18

Fingerprint

Energy utilization
Smartphones
Computer vision
Degradation
Drones

All Science Journal Classification (ASJC) codes

  • Computational Theory and Mathematics
  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Cite this

Inoue, Y., Ono, T., & Inouer, K. (2019). Situation-based dynamic frame-rate control for on-line object tracking. In 2018 Proceedings of the Japan-Africa Conference on Electronics, Communications, and Computations, JAC-ECC 2018 (pp. 119-122). [8679545] (2018 Proceedings of the Japan-Africa Conference on Electronics, Communications, and Computations, JAC-ECC 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/JEC-ECC.2018.8679545

Situation-based dynamic frame-rate control for on-line object tracking. / Inoue, Yusuke; Ono, Takatsuau; Inouer, Koji.

2018 Proceedings of the Japan-Africa Conference on Electronics, Communications, and Computations, JAC-ECC 2018. Institute of Electrical and Electronics Engineers Inc., 2019. p. 119-122 8679545 (2018 Proceedings of the Japan-Africa Conference on Electronics, Communications, and Computations, JAC-ECC 2018).

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

Inoue, Y, Ono, T & Inouer, K 2019, Situation-based dynamic frame-rate control for on-line object tracking. in 2018 Proceedings of the Japan-Africa Conference on Electronics, Communications, and Computations, JAC-ECC 2018., 8679545, 2018 Proceedings of the Japan-Africa Conference on Electronics, Communications, and Computations, JAC-ECC 2018, Institute of Electrical and Electronics Engineers Inc., pp. 119-122, 2018 Japan-Africa Conference on Electronics, Communications, and Computations, JAC-ECC 2018, Alexandria, Egypt, 12/17/18. https://doi.org/10.1109/JEC-ECC.2018.8679545
Inoue Y, Ono T, Inouer K. Situation-based dynamic frame-rate control for on-line object tracking. In 2018 Proceedings of the Japan-Africa Conference on Electronics, Communications, and Computations, JAC-ECC 2018. Institute of Electrical and Electronics Engineers Inc. 2019. p. 119-122. 8679545. (2018 Proceedings of the Japan-Africa Conference on Electronics, Communications, and Computations, JAC-ECC 2018). https://doi.org/10.1109/JEC-ECC.2018.8679545
Inoue, Yusuke ; Ono, Takatsuau ; Inouer, Koji. / Situation-based dynamic frame-rate control for on-line object tracking. 2018 Proceedings of the Japan-Africa Conference on Electronics, Communications, and Computations, JAC-ECC 2018. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 119-122 (2018 Proceedings of the Japan-Africa Conference on Electronics, Communications, and Computations, JAC-ECC 2018).
@inproceedings{221cbd4b8a9e4d6c889985adbf739d7f,
title = "Situation-based dynamic frame-rate control for on-line object tracking",
abstract = "On-line object tracking is an essential technology in computer vision. Object tracking systems need to reduce their energy consumption because the technology is increasingly being utilized for battery-operated systems, e.g., driving assist systems, smartphones, drones and so on. To tackle this problem, dynamic frame-rate optimization has been proposed. This approach optimizes the frame-rate on the basis of target object speed by taking into account the energy trade-off between the image capturing and tracking processes. In order to improve tracking accuracy, the approach selects a frame-rate based on a specific fixed value. However, the required parameters are different depending on the scene and content of the input video. In this paper, we propose a method to adaptively select parameters. Simulation results show the energy consumption is reduced by up to about 65.0{\%}, and 45.0 {\%} on average without critical tracking accuracy degradation.",
author = "Yusuke Inoue and Takatsuau Ono and Koji Inouer",
year = "2019",
month = "4",
day = "1",
doi = "10.1109/JEC-ECC.2018.8679545",
language = "English",
series = "2018 Proceedings of the Japan-Africa Conference on Electronics, Communications, and Computations, JAC-ECC 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "119--122",
booktitle = "2018 Proceedings of the Japan-Africa Conference on Electronics, Communications, and Computations, JAC-ECC 2018",
address = "United States",

}

TY - GEN

T1 - Situation-based dynamic frame-rate control for on-line object tracking

AU - Inoue, Yusuke

AU - Ono, Takatsuau

AU - Inouer, Koji

PY - 2019/4/1

Y1 - 2019/4/1

N2 - On-line object tracking is an essential technology in computer vision. Object tracking systems need to reduce their energy consumption because the technology is increasingly being utilized for battery-operated systems, e.g., driving assist systems, smartphones, drones and so on. To tackle this problem, dynamic frame-rate optimization has been proposed. This approach optimizes the frame-rate on the basis of target object speed by taking into account the energy trade-off between the image capturing and tracking processes. In order to improve tracking accuracy, the approach selects a frame-rate based on a specific fixed value. However, the required parameters are different depending on the scene and content of the input video. In this paper, we propose a method to adaptively select parameters. Simulation results show the energy consumption is reduced by up to about 65.0%, and 45.0 % on average without critical tracking accuracy degradation.

AB - On-line object tracking is an essential technology in computer vision. Object tracking systems need to reduce their energy consumption because the technology is increasingly being utilized for battery-operated systems, e.g., driving assist systems, smartphones, drones and so on. To tackle this problem, dynamic frame-rate optimization has been proposed. This approach optimizes the frame-rate on the basis of target object speed by taking into account the energy trade-off between the image capturing and tracking processes. In order to improve tracking accuracy, the approach selects a frame-rate based on a specific fixed value. However, the required parameters are different depending on the scene and content of the input video. In this paper, we propose a method to adaptively select parameters. Simulation results show the energy consumption is reduced by up to about 65.0%, and 45.0 % on average without critical tracking accuracy degradation.

UR - http://www.scopus.com/inward/record.url?scp=85064611239&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064611239&partnerID=8YFLogxK

U2 - 10.1109/JEC-ECC.2018.8679545

DO - 10.1109/JEC-ECC.2018.8679545

M3 - Conference contribution

AN - SCOPUS:85064611239

T3 - 2018 Proceedings of the Japan-Africa Conference on Electronics, Communications, and Computations, JAC-ECC 2018

SP - 119

EP - 122

BT - 2018 Proceedings of the Japan-Africa Conference on Electronics, Communications, and Computations, JAC-ECC 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -