Mean shift tracker combined with online learning-based detector and Kalman filtering for real-time tracking

Jongmin Jeong, Tae Sung Yoon, Jin Bae Park

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

Color-based visual object tracking is one of the most commonly used tracking methods. Among many tracking methods, the mean shift tracker is used most often because it is simple to implement and consumes less computational time. However, mean shift trackers exhibit several limitations when used for long-term tracking. In challenging conditions that include occlusions, pose variations, scale changes, and illumination changes, the mean shift tracker does not work well. In this paper, an improved tracking algorithm based on a mean shift tracker is proposed to overcome the weaknesses of existing methods based on mean shift tracker. The main contributions of this paper are to integrate mean shift tracker with an online learning-based detector and to newly define the Kalman filter-based validation region for reducing computational burden of the detector. We combine the mean shift tracker with the online learning-based detector, and integrate the Kalman filter to develop a novel tracking algorithm. The proposed algorithm can reinitialize the target when it converges to a local minima and it can cope with scale changes, occlusions and appearance changes by using the online learning-based detector. It updates the target model for the tracker in order to ensure long-term tracking. Moreover, the validation region obtained by using the Kalman filter and the Mahalanobis distance is used in order to operate detector in real-time. Through a comparison against various mean shift tracker-based methods and other state-of-the-art methods on eight challenging video sequences, we demonstrate that the proposed algorithm is efficient and superior in terms of accuracy and speed. Hence, it is expected that the proposed method can be applied to various applications which need to detect and track an object in real-time.

Original languageEnglish
Pages (from-to)194-206
Number of pages13
JournalExpert Systems with Applications
Volume79
DOIs
Publication statusPublished - 2017 Aug 15

Fingerprint

Detectors
Kalman filters
Lighting
Color

All Science Journal Classification (ASJC) codes

  • Engineering(all)
  • Computer Science Applications
  • Artificial Intelligence

Cite this

@article{9f8bd23a7b6345fa854d5c7a14793f70,
title = "Mean shift tracker combined with online learning-based detector and Kalman filtering for real-time tracking",
abstract = "Color-based visual object tracking is one of the most commonly used tracking methods. Among many tracking methods, the mean shift tracker is used most often because it is simple to implement and consumes less computational time. However, mean shift trackers exhibit several limitations when used for long-term tracking. In challenging conditions that include occlusions, pose variations, scale changes, and illumination changes, the mean shift tracker does not work well. In this paper, an improved tracking algorithm based on a mean shift tracker is proposed to overcome the weaknesses of existing methods based on mean shift tracker. The main contributions of this paper are to integrate mean shift tracker with an online learning-based detector and to newly define the Kalman filter-based validation region for reducing computational burden of the detector. We combine the mean shift tracker with the online learning-based detector, and integrate the Kalman filter to develop a novel tracking algorithm. The proposed algorithm can reinitialize the target when it converges to a local minima and it can cope with scale changes, occlusions and appearance changes by using the online learning-based detector. It updates the target model for the tracker in order to ensure long-term tracking. Moreover, the validation region obtained by using the Kalman filter and the Mahalanobis distance is used in order to operate detector in real-time. Through a comparison against various mean shift tracker-based methods and other state-of-the-art methods on eight challenging video sequences, we demonstrate that the proposed algorithm is efficient and superior in terms of accuracy and speed. Hence, it is expected that the proposed method can be applied to various applications which need to detect and track an object in real-time.",
author = "Jongmin Jeong and Yoon, {Tae Sung} and Park, {Jin Bae}",
year = "2017",
month = "8",
day = "15",
doi = "10.1016/j.eswa.2017.02.043",
language = "English",
volume = "79",
pages = "194--206",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Limited",

}

Mean shift tracker combined with online learning-based detector and Kalman filtering for real-time tracking. / Jeong, Jongmin; Yoon, Tae Sung; Park, Jin Bae.

In: Expert Systems with Applications, Vol. 79, 15.08.2017, p. 194-206.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Mean shift tracker combined with online learning-based detector and Kalman filtering for real-time tracking

AU - Jeong, Jongmin

AU - Yoon, Tae Sung

AU - Park, Jin Bae

PY - 2017/8/15

Y1 - 2017/8/15

N2 - Color-based visual object tracking is one of the most commonly used tracking methods. Among many tracking methods, the mean shift tracker is used most often because it is simple to implement and consumes less computational time. However, mean shift trackers exhibit several limitations when used for long-term tracking. In challenging conditions that include occlusions, pose variations, scale changes, and illumination changes, the mean shift tracker does not work well. In this paper, an improved tracking algorithm based on a mean shift tracker is proposed to overcome the weaknesses of existing methods based on mean shift tracker. The main contributions of this paper are to integrate mean shift tracker with an online learning-based detector and to newly define the Kalman filter-based validation region for reducing computational burden of the detector. We combine the mean shift tracker with the online learning-based detector, and integrate the Kalman filter to develop a novel tracking algorithm. The proposed algorithm can reinitialize the target when it converges to a local minima and it can cope with scale changes, occlusions and appearance changes by using the online learning-based detector. It updates the target model for the tracker in order to ensure long-term tracking. Moreover, the validation region obtained by using the Kalman filter and the Mahalanobis distance is used in order to operate detector in real-time. Through a comparison against various mean shift tracker-based methods and other state-of-the-art methods on eight challenging video sequences, we demonstrate that the proposed algorithm is efficient and superior in terms of accuracy and speed. Hence, it is expected that the proposed method can be applied to various applications which need to detect and track an object in real-time.

AB - Color-based visual object tracking is one of the most commonly used tracking methods. Among many tracking methods, the mean shift tracker is used most often because it is simple to implement and consumes less computational time. However, mean shift trackers exhibit several limitations when used for long-term tracking. In challenging conditions that include occlusions, pose variations, scale changes, and illumination changes, the mean shift tracker does not work well. In this paper, an improved tracking algorithm based on a mean shift tracker is proposed to overcome the weaknesses of existing methods based on mean shift tracker. The main contributions of this paper are to integrate mean shift tracker with an online learning-based detector and to newly define the Kalman filter-based validation region for reducing computational burden of the detector. We combine the mean shift tracker with the online learning-based detector, and integrate the Kalman filter to develop a novel tracking algorithm. The proposed algorithm can reinitialize the target when it converges to a local minima and it can cope with scale changes, occlusions and appearance changes by using the online learning-based detector. It updates the target model for the tracker in order to ensure long-term tracking. Moreover, the validation region obtained by using the Kalman filter and the Mahalanobis distance is used in order to operate detector in real-time. Through a comparison against various mean shift tracker-based methods and other state-of-the-art methods on eight challenging video sequences, we demonstrate that the proposed algorithm is efficient and superior in terms of accuracy and speed. Hence, it is expected that the proposed method can be applied to various applications which need to detect and track an object in real-time.

UR - http://www.scopus.com/inward/record.url?scp=85014836337&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85014836337&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2017.02.043

DO - 10.1016/j.eswa.2017.02.043

M3 - Article

VL - 79

SP - 194

EP - 206

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

ER -