Robust visual tracking framework in the presence of blurring by arbitrating appearance- and feature-based detection

Tae Koo Kang, Yung Hak Mo, Dong Sung Pae, Choon Ki Ahn, Myo Taeg Lim

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

This paper proposes a new visual tracking framework and demonstrates its merits via mobile robot experiments. An image sequence from the vision system of a mobile robot is not static when a mobile robot is moving, since slipping and vibration occur. These problems cause image blurring. Therefore, in this paper, we address the problem of robust object tracking under blurring and introduce a novel robust visual tracking framework based on the arbitration of the AdaBoost-based detection method and the appearance-based detection method to overcome the blurring problem. The proposed framework consists of three parts: (1) distortion error compensation and feature extraction using the Modified Discrete Gaussian–Hermite Moment (MDGHM) and fuzzy-based distortion error compensation, (2) object detection using arbitration of appearance- and feature-based object detection, and (3) object tracking using a Finite Impulse Response (FIR) filter. To demonstrate the performance of the proposed framework, mobile robot visual tracking experiments are carried out. The results show that the proposed framework is more robust against blurring than the conventional feature- and appearance-based methods.

Original languageEnglish
Pages (from-to)50-69
Number of pages20
JournalMeasurement: Journal of the International Measurement Confederation
Volume95
DOIs
Publication statusPublished - 2017 Jan 1

Fingerprint

optical tracking
Visual Tracking
blurring
robot
robots
Mobile robots
Mobile Robot
Error compensation
arbitration
Arbitration
Error Compensation
Object Tracking
Object Detection
FIR filters
Adaptive boosting
experiment
pattern recognition
AdaBoost
Feature extraction
Impulse Response

Keywords

  • Finite impulse response tracker
  • Mobile robot
  • Modified discrete Gaussian–Hermite moment
  • Object detection
  • Visual object tracking

ASJC Scopus subject areas

  • Statistics and Probability
  • Education
  • Condensed Matter Physics
  • Applied Mathematics

Cite this

@article{c84d03287e8d4f95ad0d1eaa3bbfbb8f,
title = "Robust visual tracking framework in the presence of blurring by arbitrating appearance- and feature-based detection",
abstract = "This paper proposes a new visual tracking framework and demonstrates its merits via mobile robot experiments. An image sequence from the vision system of a mobile robot is not static when a mobile robot is moving, since slipping and vibration occur. These problems cause image blurring. Therefore, in this paper, we address the problem of robust object tracking under blurring and introduce a novel robust visual tracking framework based on the arbitration of the AdaBoost-based detection method and the appearance-based detection method to overcome the blurring problem. The proposed framework consists of three parts: (1) distortion error compensation and feature extraction using the Modified Discrete Gaussian–Hermite Moment (MDGHM) and fuzzy-based distortion error compensation, (2) object detection using arbitration of appearance- and feature-based object detection, and (3) object tracking using a Finite Impulse Response (FIR) filter. To demonstrate the performance of the proposed framework, mobile robot visual tracking experiments are carried out. The results show that the proposed framework is more robust against blurring than the conventional feature- and appearance-based methods.",
keywords = "Finite impulse response tracker, Mobile robot, Modified discrete Gaussian–Hermite moment, Object detection, Visual object tracking",
author = "Kang, {Tae Koo} and Mo, {Yung Hak} and Pae, {Dong Sung} and Ahn, {Choon Ki} and Lim, {Myo Taeg}",
year = "2017",
month = "1",
day = "1",
doi = "10.1016/j.measurement.2016.09.032",
language = "English",
volume = "95",
pages = "50--69",
journal = "Measurement",
issn = "1536-6367",
publisher = "Elsevier",

}

TY - JOUR

T1 - Robust visual tracking framework in the presence of blurring by arbitrating appearance- and feature-based detection

AU - Kang, Tae Koo

AU - Mo, Yung Hak

AU - Pae, Dong Sung

AU - Ahn, Choon Ki

AU - Lim, Myo Taeg

PY - 2017/1/1

Y1 - 2017/1/1

N2 - This paper proposes a new visual tracking framework and demonstrates its merits via mobile robot experiments. An image sequence from the vision system of a mobile robot is not static when a mobile robot is moving, since slipping and vibration occur. These problems cause image blurring. Therefore, in this paper, we address the problem of robust object tracking under blurring and introduce a novel robust visual tracking framework based on the arbitration of the AdaBoost-based detection method and the appearance-based detection method to overcome the blurring problem. The proposed framework consists of three parts: (1) distortion error compensation and feature extraction using the Modified Discrete Gaussian–Hermite Moment (MDGHM) and fuzzy-based distortion error compensation, (2) object detection using arbitration of appearance- and feature-based object detection, and (3) object tracking using a Finite Impulse Response (FIR) filter. To demonstrate the performance of the proposed framework, mobile robot visual tracking experiments are carried out. The results show that the proposed framework is more robust against blurring than the conventional feature- and appearance-based methods.

AB - This paper proposes a new visual tracking framework and demonstrates its merits via mobile robot experiments. An image sequence from the vision system of a mobile robot is not static when a mobile robot is moving, since slipping and vibration occur. These problems cause image blurring. Therefore, in this paper, we address the problem of robust object tracking under blurring and introduce a novel robust visual tracking framework based on the arbitration of the AdaBoost-based detection method and the appearance-based detection method to overcome the blurring problem. The proposed framework consists of three parts: (1) distortion error compensation and feature extraction using the Modified Discrete Gaussian–Hermite Moment (MDGHM) and fuzzy-based distortion error compensation, (2) object detection using arbitration of appearance- and feature-based object detection, and (3) object tracking using a Finite Impulse Response (FIR) filter. To demonstrate the performance of the proposed framework, mobile robot visual tracking experiments are carried out. The results show that the proposed framework is more robust against blurring than the conventional feature- and appearance-based methods.

KW - Finite impulse response tracker

KW - Mobile robot

KW - Modified discrete Gaussian–Hermite moment

KW - Object detection

KW - Visual object tracking

UR - http://www.scopus.com/inward/record.url?scp=84988921802&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84988921802&partnerID=8YFLogxK

U2 - 10.1016/j.measurement.2016.09.032

DO - 10.1016/j.measurement.2016.09.032

M3 - Article

VL - 95

SP - 50

EP - 69

JO - Measurement

JF - Measurement

SN - 1536-6367

ER -