Online Multi-object Tracking Based on Hierarchical Association Framework

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

Online multi-object tracking is one of the crucial tasks in time-critical computer vision applications. In this paper, the problem of online multi-object tracking in complex scenes from a single, static, un-calibrated camera is addressed. In complex scenes, it is still challenging due to frequent and prolonged occlusions, abrupt motion change of objects, unreliable detections, and so on. To handle these difficulties, this paper proposes a four-stage hierarchical association framework based on online tracking-bydetection strategy. For this framework, tracks and detections are divided into several groups depending on several cues obtained from association results with the proposed track confidence. In each association stage, different sets of tracks and detections are associated to handle the following problems simultaneously: track generation, progressive trajectory construction, track drift and fragmentation. The experimental results show the robustness and effectiveness of the proposed method compared with other state-of-the-art methods.

Original languageEnglish
Title of host publicationProceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016
PublisherIEEE Computer Society
Pages1273-1281
Number of pages9
ISBN (Electronic)9781467388504
DOIs
Publication statusPublished - 2016 Dec 16
Event29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016 - Las Vegas, United States
Duration: 2016 Jun 262016 Jul 1

Other

Other29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016
CountryUnited States
CityLas Vegas
Period16/6/2616/7/1

Fingerprint

Computer vision
Cameras
Trajectories
Object detection

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Ju, J., Kim, D., Ku, B., Ko, H., & Han, D. K. (2016). Online Multi-object Tracking Based on Hierarchical Association Framework. In Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016 (pp. 1273-1281). [7789651] IEEE Computer Society. https://doi.org/10.1109/CVPRW.2016.161

Online Multi-object Tracking Based on Hierarchical Association Framework. / Ju, Jaeyong; Kim, Daehun; Ku, Bonhwa; Ko, Hanseok; Han, David K.

Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016. IEEE Computer Society, 2016. p. 1273-1281 7789651.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ju, J, Kim, D, Ku, B, Ko, H & Han, DK 2016, Online Multi-object Tracking Based on Hierarchical Association Framework. in Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016., 7789651, IEEE Computer Society, pp. 1273-1281, 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016, Las Vegas, United States, 16/6/26. https://doi.org/10.1109/CVPRW.2016.161
Ju J, Kim D, Ku B, Ko H, Han DK. Online Multi-object Tracking Based on Hierarchical Association Framework. In Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016. IEEE Computer Society. 2016. p. 1273-1281. 7789651 https://doi.org/10.1109/CVPRW.2016.161
Ju, Jaeyong ; Kim, Daehun ; Ku, Bonhwa ; Ko, Hanseok ; Han, David K. / Online Multi-object Tracking Based on Hierarchical Association Framework. Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016. IEEE Computer Society, 2016. pp. 1273-1281
@inproceedings{289e7b9e0264427e81ea9b675092bb22,
title = "Online Multi-object Tracking Based on Hierarchical Association Framework",
abstract = "Online multi-object tracking is one of the crucial tasks in time-critical computer vision applications. In this paper, the problem of online multi-object tracking in complex scenes from a single, static, un-calibrated camera is addressed. In complex scenes, it is still challenging due to frequent and prolonged occlusions, abrupt motion change of objects, unreliable detections, and so on. To handle these difficulties, this paper proposes a four-stage hierarchical association framework based on online tracking-bydetection strategy. For this framework, tracks and detections are divided into several groups depending on several cues obtained from association results with the proposed track confidence. In each association stage, different sets of tracks and detections are associated to handle the following problems simultaneously: track generation, progressive trajectory construction, track drift and fragmentation. The experimental results show the robustness and effectiveness of the proposed method compared with other state-of-the-art methods.",
author = "Jaeyong Ju and Daehun Kim and Bonhwa Ku and Hanseok Ko and Han, {David K.}",
year = "2016",
month = "12",
day = "16",
doi = "10.1109/CVPRW.2016.161",
language = "English",
pages = "1273--1281",
booktitle = "Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Online Multi-object Tracking Based on Hierarchical Association Framework

AU - Ju, Jaeyong

AU - Kim, Daehun

AU - Ku, Bonhwa

AU - Ko, Hanseok

AU - Han, David K.

PY - 2016/12/16

Y1 - 2016/12/16

N2 - Online multi-object tracking is one of the crucial tasks in time-critical computer vision applications. In this paper, the problem of online multi-object tracking in complex scenes from a single, static, un-calibrated camera is addressed. In complex scenes, it is still challenging due to frequent and prolonged occlusions, abrupt motion change of objects, unreliable detections, and so on. To handle these difficulties, this paper proposes a four-stage hierarchical association framework based on online tracking-bydetection strategy. For this framework, tracks and detections are divided into several groups depending on several cues obtained from association results with the proposed track confidence. In each association stage, different sets of tracks and detections are associated to handle the following problems simultaneously: track generation, progressive trajectory construction, track drift and fragmentation. The experimental results show the robustness and effectiveness of the proposed method compared with other state-of-the-art methods.

AB - Online multi-object tracking is one of the crucial tasks in time-critical computer vision applications. In this paper, the problem of online multi-object tracking in complex scenes from a single, static, un-calibrated camera is addressed. In complex scenes, it is still challenging due to frequent and prolonged occlusions, abrupt motion change of objects, unreliable detections, and so on. To handle these difficulties, this paper proposes a four-stage hierarchical association framework based on online tracking-bydetection strategy. For this framework, tracks and detections are divided into several groups depending on several cues obtained from association results with the proposed track confidence. In each association stage, different sets of tracks and detections are associated to handle the following problems simultaneously: track generation, progressive trajectory construction, track drift and fragmentation. The experimental results show the robustness and effectiveness of the proposed method compared with other state-of-the-art methods.

UR - http://www.scopus.com/inward/record.url?scp=85010223618&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85010223618&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2016.161

DO - 10.1109/CVPRW.2016.161

M3 - Conference contribution

AN - SCOPUS:85010223618

SP - 1273

EP - 1281

BT - Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016

PB - IEEE Computer Society

ER -