Real-Time frame-rate control for energy-efficient on-line object tracking

Yusuke Inoue, Takatsugu Ono, Inoue Koji

Research output: Contribution to journalArticle

Abstract

On-line object tracking (OLOT) has been a core technology in computer vision, and its importance has been increasing rapidly. Because this technology is utilized for battery-operated products, energy consumption must be minimized. This paper describes a method of adaptive frame-rate optimization to satisfy that requirement. An energy trade-off occurs between image capturing and object tracking. Therefore, the method optimizes the frame-rate based on always changed object speed for minimizing the total energy while taking into account the trade-off. Simulation results show a maximum energy reduction of 50.0%, and an average reduction of 35.9% without serious tracking accuracy degradation.

Original languageEnglish
Pages (from-to)2297-2307
Number of pages11
JournalIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
VolumeE101A
Issue number12
DOIs
Publication statusPublished - Dec 1 2018

Fingerprint

Rate Control
Object Tracking
Energy Efficient
Real-time
Trade-offs
Energy
Computer vision
Energy utilization
Degradation
Battery
Computer Vision
Energy Consumption
Optimise
Optimization
Requirements
Simulation

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Computer Graphics and Computer-Aided Design
  • Electrical and Electronic Engineering
  • Applied Mathematics

Cite this

@article{359a96b808a043fca033ae78eda8b004,
title = "Real-Time frame-rate control for energy-efficient on-line object tracking",
abstract = "On-line object tracking (OLOT) has been a core technology in computer vision, and its importance has been increasing rapidly. Because this technology is utilized for battery-operated products, energy consumption must be minimized. This paper describes a method of adaptive frame-rate optimization to satisfy that requirement. An energy trade-off occurs between image capturing and object tracking. Therefore, the method optimizes the frame-rate based on always changed object speed for minimizing the total energy while taking into account the trade-off. Simulation results show a maximum energy reduction of 50.0{\%}, and an average reduction of 35.9{\%} without serious tracking accuracy degradation.",
author = "Yusuke Inoue and Takatsugu Ono and Inoue Koji",
year = "2018",
month = "12",
day = "1",
doi = "10.1587/transfun.E101.A.2297",
language = "English",
volume = "E101A",
pages = "2297--2307",
journal = "IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences",
issn = "0916-8508",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "12",

}

TY - JOUR

T1 - Real-Time frame-rate control for energy-efficient on-line object tracking

AU - Inoue, Yusuke

AU - Ono, Takatsugu

AU - Koji, Inoue

PY - 2018/12/1

Y1 - 2018/12/1

N2 - On-line object tracking (OLOT) has been a core technology in computer vision, and its importance has been increasing rapidly. Because this technology is utilized for battery-operated products, energy consumption must be minimized. This paper describes a method of adaptive frame-rate optimization to satisfy that requirement. An energy trade-off occurs between image capturing and object tracking. Therefore, the method optimizes the frame-rate based on always changed object speed for minimizing the total energy while taking into account the trade-off. Simulation results show a maximum energy reduction of 50.0%, and an average reduction of 35.9% without serious tracking accuracy degradation.

AB - On-line object tracking (OLOT) has been a core technology in computer vision, and its importance has been increasing rapidly. Because this technology is utilized for battery-operated products, energy consumption must be minimized. This paper describes a method of adaptive frame-rate optimization to satisfy that requirement. An energy trade-off occurs between image capturing and object tracking. Therefore, the method optimizes the frame-rate based on always changed object speed for minimizing the total energy while taking into account the trade-off. Simulation results show a maximum energy reduction of 50.0%, and an average reduction of 35.9% without serious tracking accuracy degradation.

UR - http://www.scopus.com/inward/record.url?scp=85057500292&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85057500292&partnerID=8YFLogxK

U2 - 10.1587/transfun.E101.A.2297

DO - 10.1587/transfun.E101.A.2297

M3 - Article

AN - SCOPUS:85057500292

VL - E101A

SP - 2297

EP - 2307

JO - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

JF - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

SN - 0916-8508

IS - 12

ER -