Online multi-object tracking via robust collaborative model and sample selection

Mohamed A. Naiel, M. Omair Ahmad, M. N.S. Swamy, Jongwoo Lim, Ming Hsuan Yang

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

The past decade has witnessed significant progress in object detection and tracking in videos. In this paper, we present a collaborative model between a pre-trained object detector and a number of single-object online trackers within the particle filtering framework. For each frame, we construct an association between detections and trackers, and treat each detected image region as a key sample, for online update, if it is associated to a tracker. We present a motion model that incorporates the associated detections with object dynamics. Furthermore, we propose an effective sample selection scheme to update the appearance model of each tracker. We use discriminative and generative appearance models for the likelihood function and data association, respectively. Experimental results show that the proposed scheme generally outperforms state-of-the-art methods.

Original languageEnglish
Pages (from-to)94-107
Number of pages14
JournalComputer Vision and Image Understanding
Volume154
DOIs
Publication statusPublished - 2017 Jan 1

Fingerprint

Detectors
Object detection

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition

Cite this

Naiel, Mohamed A. ; Ahmad, M. Omair ; Swamy, M. N.S. ; Lim, Jongwoo ; Yang, Ming Hsuan. / Online multi-object tracking via robust collaborative model and sample selection. In: Computer Vision and Image Understanding. 2017 ; Vol. 154. pp. 94-107.
@article{c4b46747abf04c3a966eb49ba2e28b04,
title = "Online multi-object tracking via robust collaborative model and sample selection",
abstract = "The past decade has witnessed significant progress in object detection and tracking in videos. In this paper, we present a collaborative model between a pre-trained object detector and a number of single-object online trackers within the particle filtering framework. For each frame, we construct an association between detections and trackers, and treat each detected image region as a key sample, for online update, if it is associated to a tracker. We present a motion model that incorporates the associated detections with object dynamics. Furthermore, we propose an effective sample selection scheme to update the appearance model of each tracker. We use discriminative and generative appearance models for the likelihood function and data association, respectively. Experimental results show that the proposed scheme generally outperforms state-of-the-art methods.",
author = "Naiel, {Mohamed A.} and Ahmad, {M. Omair} and Swamy, {M. N.S.} and Jongwoo Lim and Yang, {Ming Hsuan}",
year = "2017",
month = "1",
day = "1",
doi = "10.1016/j.cviu.2016.07.003",
language = "English",
volume = "154",
pages = "94--107",
journal = "Computer Vision and Image Understanding",
issn = "1077-3142",
publisher = "Academic Press Inc.",

}

Online multi-object tracking via robust collaborative model and sample selection. / Naiel, Mohamed A.; Ahmad, M. Omair; Swamy, M. N.S.; Lim, Jongwoo; Yang, Ming Hsuan.

In: Computer Vision and Image Understanding, Vol. 154, 01.01.2017, p. 94-107.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Online multi-object tracking via robust collaborative model and sample selection

AU - Naiel, Mohamed A.

AU - Ahmad, M. Omair

AU - Swamy, M. N.S.

AU - Lim, Jongwoo

AU - Yang, Ming Hsuan

PY - 2017/1/1

Y1 - 2017/1/1

N2 - The past decade has witnessed significant progress in object detection and tracking in videos. In this paper, we present a collaborative model between a pre-trained object detector and a number of single-object online trackers within the particle filtering framework. For each frame, we construct an association between detections and trackers, and treat each detected image region as a key sample, for online update, if it is associated to a tracker. We present a motion model that incorporates the associated detections with object dynamics. Furthermore, we propose an effective sample selection scheme to update the appearance model of each tracker. We use discriminative and generative appearance models for the likelihood function and data association, respectively. Experimental results show that the proposed scheme generally outperforms state-of-the-art methods.

AB - The past decade has witnessed significant progress in object detection and tracking in videos. In this paper, we present a collaborative model between a pre-trained object detector and a number of single-object online trackers within the particle filtering framework. For each frame, we construct an association between detections and trackers, and treat each detected image region as a key sample, for online update, if it is associated to a tracker. We present a motion model that incorporates the associated detections with object dynamics. Furthermore, we propose an effective sample selection scheme to update the appearance model of each tracker. We use discriminative and generative appearance models for the likelihood function and data association, respectively. Experimental results show that the proposed scheme generally outperforms state-of-the-art methods.

UR - http://www.scopus.com/inward/record.url?scp=84994803314&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84994803314&partnerID=8YFLogxK

U2 - 10.1016/j.cviu.2016.07.003

DO - 10.1016/j.cviu.2016.07.003

M3 - Article

AN - SCOPUS:84994803314

VL - 154

SP - 94

EP - 107

JO - Computer Vision and Image Understanding

JF - Computer Vision and Image Understanding

SN - 1077-3142

ER -