Prediction and Tracking of Moving Objects in Image Sequences

A G Bors; I Pitas

doi:10.1109/83.855440

Prediction and Tracking of Moving Objects in Image Sequences

A G Bors, I Pitas

Computer Science

Research output: Contribution to journal › Article › peer-review

Abstract

We employ a prediction model for moving object velocity and location estimation derived from Bayesian theory. The optical flow of a certain moving object depends on the history of its previous values. A joint optical flow estimation and moving object segmentation algorithm is used for the initialization of the tracking algorithm. The segmentation of the moving objects is determined by appropriately classifying the unlabeled and the occluding regions. Segmentation and optical flow tracking is used for predicting future frames.

Original language	English
Pages (from-to)	1441-1445
Number of pages	5
Journal	IEEE Transactions on Image Processing
Volume	9
Issue number	8
DOIs	https://doi.org/10.1109/83.855440
Publication status	Published - Aug 2000

Bibliographical note

Copyright © 2000 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

Keywords

Bayes procedures
image sequence analysis
tracking
OPTICAL-FLOW
SEGMENTATION
NETWORK

Access to Document

10.1109/83.855440

borsag4.pdf

http://dx.doi.org/10.1109/83.855440

Cite this

@article{c1de642728eb430982a875025f568ca6,

title = "Prediction and Tracking of Moving Objects in Image Sequences",

abstract = "We employ a prediction model for moving object velocity and location estimation derived from Bayesian theory. The optical flow of a certain moving object depends on the history of its previous values. A joint optical flow estimation and moving object segmentation algorithm is used for the initialization of the tracking algorithm. The segmentation of the moving objects is determined by appropriately classifying the unlabeled and the occluding regions. Segmentation and optical flow tracking is used for predicting future frames.",

keywords = "Bayes procedures, image sequence analysis, tracking, OPTICAL-FLOW, SEGMENTATION, NETWORK",

author = "Bors, {A G} and I Pitas",

note = "Copyright {\textcopyright} 2000 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.",

year = "2000",

month = aug,

doi = "10.1109/83.855440",

language = "English",

volume = "9",

pages = "1441--1445",

journal = "IEEE Transactions on Image Processing",

issn = "1057-7149",

publisher = "IEEE",

number = "8",

}

TY - JOUR

T1 - Prediction and Tracking of Moving Objects in Image Sequences

AU - Bors, A G

AU - Pitas, I

N1 - Copyright © 2000 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

PY - 2000/8

Y1 - 2000/8

N2 - We employ a prediction model for moving object velocity and location estimation derived from Bayesian theory. The optical flow of a certain moving object depends on the history of its previous values. A joint optical flow estimation and moving object segmentation algorithm is used for the initialization of the tracking algorithm. The segmentation of the moving objects is determined by appropriately classifying the unlabeled and the occluding regions. Segmentation and optical flow tracking is used for predicting future frames.

AB - We employ a prediction model for moving object velocity and location estimation derived from Bayesian theory. The optical flow of a certain moving object depends on the history of its previous values. A joint optical flow estimation and moving object segmentation algorithm is used for the initialization of the tracking algorithm. The segmentation of the moving objects is determined by appropriately classifying the unlabeled and the occluding regions. Segmentation and optical flow tracking is used for predicting future frames.

KW - Bayes procedures

KW - image sequence analysis

KW - tracking

KW - OPTICAL-FLOW

KW - SEGMENTATION

KW - NETWORK

U2 - 10.1109/83.855440

DO - 10.1109/83.855440

M3 - Article

SN - 1057-7149

VL - 9

SP - 1441

EP - 1445

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

IS - 8

ER -