Journal article
Online multi-object tracking with efficient track drift and fragmentation handling
Journal of the Optical Society of America. A, Optics, image science, and vision, v 34(2), pp 280-293
01 Feb 2017
PMID: 28157856
Featured in Collection : UN Sustainable Development Goals @ Drexel
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 handlingmethod 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. (C) 2017 Optical Society of America
Metrics
Details
- Title
- Online multi-object tracking with efficient track drift and fragmentation handling
- Creators
- Jaeyong Ju - Korea UniversityDaehun Kim - Korea UniversityBonhwa Ku - Korea UniversityDavid K. Han - Office of the Secretary of DefenseHanseok Ko - Korea University
- Publication Details
- Journal of the Optical Society of America. A, Optics, image science, and vision, v 34(2), pp 280-293
- Publisher
- Optica Publishing Group
- Number of pages
- 14
- Grant note
- Korea University (KU) Brain Korea 21 Plus Project N62909-16-1-2185 / Office of Naval Research Global (ONRG); Office of Naval Research
- Resource Type
- Journal article
- Language
- English
- Academic Unit
- Electrical and Computer Engineering
- Web of Science ID
- WOS:000394032400016
- Scopus ID
- 2-s2.0-85011909709
- Other Identifier
- 991021931087204721
UN Sustainable Development Goals (SDGs)
This publication has contributed to the advancement of the following goals:
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- International collaboration
- Web of Science research areas
- Optics