Online multi-object tracking with efficient track drift and fragmentation handling

Jaeyong Ju, Daehun Kim, Bonhwa Ku, David K. Han, Hanseok Ko

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

This paper addresses the problem of multi-object tracking in complex scenes by a single, static, uncalibrated camera. Tracking-by-detection is a widely used approach for multi-object tracking. Challenges still remain in complex scenes, however, when this approach has to deal with occlusions, unreliable detections (e.g., inaccurate position/size, false positives, or false negatives), and sudden object motion/appearance changes, among other issues. To handle these problems, this paper presents a novel online multi-object tracking method, which can be fully applied to real-time applications. First, an object tracking process based on frame-by-frame association with a novel affinity model and an appearance update that does not rely on online learning is proposed to effectively and rapidly assign detections to tracks. Second, a two-stage drift handling method with novel track confidence is proposed to correct drifting tracks caused by the abrupt motion change of objects under occlusion and prolonged inaccurate detections. In addition, a fragmentation handling method based on a track-to-track association is proposed to solve the problem in which an object trajectory is broken into several tracks due to long-term occlusions. Based on experimental results derived from challenging public data sets, the proposed method delivers an impressive performance compared with other state-of-the-art methods. Furthermore, additional performance analysis demonstrates the effect and usefulness of each component of the proposed method.

Original languageEnglish
Pages (from-to)283-290
Number of pages8
JournalJournal of the Optical Society of America A: Optics and Image Science, and Vision
Volume34
Issue number2
DOIs
Publication statusPublished - 2017 Feb 1

Fingerprint

fragmentation
Cameras
Trajectories
occlusion
learning
affinity
confidence
cameras
trajectories

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Atomic and Molecular Physics, and Optics
  • Computer Vision and Pattern Recognition

Cite this

Online multi-object tracking with efficient track drift and fragmentation handling. / Ju, Jaeyong; Kim, Daehun; Ku, Bonhwa; Han, David K.; Ko, Hanseok.

In: Journal of the Optical Society of America A: Optics and Image Science, and Vision, Vol. 34, No. 2, 01.02.2017, p. 283-290.

Research output: Contribution to journalArticle

@article{67d028a44e364248a9d0dcc5fa1fa031,
title = "Online multi-object tracking with efficient track drift and fragmentation handling",
abstract = "This paper addresses the problem of multi-object tracking in complex scenes by a single, static, uncalibrated camera. Tracking-by-detection is a widely used approach for multi-object tracking. Challenges still remain in complex scenes, however, when this approach has to deal with occlusions, unreliable detections (e.g., inaccurate position/size, false positives, or false negatives), and sudden object motion/appearance changes, among other issues. To handle these problems, this paper presents a novel online multi-object tracking method, which can be fully applied to real-time applications. First, an object tracking process based on frame-by-frame association with a novel affinity model and an appearance update that does not rely on online learning is proposed to effectively and rapidly assign detections to tracks. Second, a two-stage drift handling method with novel track confidence is proposed to correct drifting tracks caused by the abrupt motion change of objects under occlusion and prolonged inaccurate detections. In addition, a fragmentation handling method based on a track-to-track association is proposed to solve the problem in which an object trajectory is broken into several tracks due to long-term occlusions. Based on experimental results derived from challenging public data sets, the proposed method delivers an impressive performance compared with other state-of-the-art methods. Furthermore, additional performance analysis demonstrates the effect and usefulness of each component of the proposed method.",
author = "Jaeyong Ju and Daehun Kim and Bonhwa Ku and Han, {David K.} and Hanseok Ko",
year = "2017",
month = "2",
day = "1",
doi = "10.1364/JOSAA.34.000280",
language = "English",
volume = "34",
pages = "283--290",
journal = "Journal of the Optical Society of America A: Optics and Image Science, and Vision",
issn = "1084-7529",
publisher = "The Optical Society",
number = "2",

}

TY - JOUR

T1 - Online multi-object tracking with efficient track drift and fragmentation handling

AU - Ju, Jaeyong

AU - Kim, Daehun

AU - Ku, Bonhwa

AU - Han, David K.

AU - Ko, Hanseok

PY - 2017/2/1

Y1 - 2017/2/1

N2 - This paper addresses the problem of multi-object tracking in complex scenes by a single, static, uncalibrated camera. Tracking-by-detection is a widely used approach for multi-object tracking. Challenges still remain in complex scenes, however, when this approach has to deal with occlusions, unreliable detections (e.g., inaccurate position/size, false positives, or false negatives), and sudden object motion/appearance changes, among other issues. To handle these problems, this paper presents a novel online multi-object tracking method, which can be fully applied to real-time applications. First, an object tracking process based on frame-by-frame association with a novel affinity model and an appearance update that does not rely on online learning is proposed to effectively and rapidly assign detections to tracks. Second, a two-stage drift handling method with novel track confidence is proposed to correct drifting tracks caused by the abrupt motion change of objects under occlusion and prolonged inaccurate detections. In addition, a fragmentation handling method based on a track-to-track association is proposed to solve the problem in which an object trajectory is broken into several tracks due to long-term occlusions. Based on experimental results derived from challenging public data sets, the proposed method delivers an impressive performance compared with other state-of-the-art methods. Furthermore, additional performance analysis demonstrates the effect and usefulness of each component of the proposed method.

AB - This paper addresses the problem of multi-object tracking in complex scenes by a single, static, uncalibrated camera. Tracking-by-detection is a widely used approach for multi-object tracking. Challenges still remain in complex scenes, however, when this approach has to deal with occlusions, unreliable detections (e.g., inaccurate position/size, false positives, or false negatives), and sudden object motion/appearance changes, among other issues. To handle these problems, this paper presents a novel online multi-object tracking method, which can be fully applied to real-time applications. First, an object tracking process based on frame-by-frame association with a novel affinity model and an appearance update that does not rely on online learning is proposed to effectively and rapidly assign detections to tracks. Second, a two-stage drift handling method with novel track confidence is proposed to correct drifting tracks caused by the abrupt motion change of objects under occlusion and prolonged inaccurate detections. In addition, a fragmentation handling method based on a track-to-track association is proposed to solve the problem in which an object trajectory is broken into several tracks due to long-term occlusions. Based on experimental results derived from challenging public data sets, the proposed method delivers an impressive performance compared with other state-of-the-art methods. Furthermore, additional performance analysis demonstrates the effect and usefulness of each component of the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=85011909709&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85011909709&partnerID=8YFLogxK

U2 - 10.1364/JOSAA.34.000280

DO - 10.1364/JOSAA.34.000280

M3 - Article

AN - SCOPUS:85011909709

VL - 34

SP - 283

EP - 290

JO - Journal of the Optical Society of America A: Optics and Image Science, and Vision

JF - Journal of the Optical Society of America A: Optics and Image Science, and Vision

SN - 1084-7529

IS - 2

ER -