Real-time tracking of multiple objects in space-variant vision based on magnocellular visual pathway

Seonghoon Kang, Seong Whan Lee

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

In this paper, we propose a space-variant image representation model based on properties of magnocellular visual pathway, which perform motion analysis, in human retina. Then, we present an algorithm for the tracking of multiple objects in the proposed space-variant model. The proposed space-variant model has two effective image representations for object recognition and motion analysis, respectively. Each image representation is based on properties of two types of ganglion cell, which are the beginning of two basic visual pathways; one is parvocellular and the other is magnocellular. Through this model, we can get the efficient data reduction capability with no great loss of important information. And, the proposed multiple objects tracking method is restricted in space-variant image. Typically, an object-tracking algorithm consists of several processes such as detection, prediction, matching, and updating. In particular, the matching process plays an important role in multiple objects tracking. In traditional vision, the matching process is simple when the target objects are rigid. In space-variant vision, however, it is very complicated although the target is rigid, because there may be deformation of an object region in the space-variant coordinate system when the target moves to another position. Therefore, we propose a deformation formula in order to solve the matching problem in space-variant vision. By solving this problem, we can efficiently implement multiple objects tracking in space-variant vision.

Original languageEnglish
Pages (from-to)2031-2040
Number of pages10
JournalPattern Recognition
Volume35
Issue number10
DOIs
Publication statusPublished - 2002 Oct 1

Fingerprint

Object recognition
Data reduction
Motion analysis

Keywords

  • Biologically motivated vision
  • Multiple objects tracking
  • Space-variant vision

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Real-time tracking of multiple objects in space-variant vision based on magnocellular visual pathway. / Kang, Seonghoon; Lee, Seong Whan.

In: Pattern Recognition, Vol. 35, No. 10, 01.10.2002, p. 2031-2040.

Research output: Contribution to journalArticle

@article{ea1792359ebf47fea3ed49d7ce668928,
title = "Real-time tracking of multiple objects in space-variant vision based on magnocellular visual pathway",
abstract = "In this paper, we propose a space-variant image representation model based on properties of magnocellular visual pathway, which perform motion analysis, in human retina. Then, we present an algorithm for the tracking of multiple objects in the proposed space-variant model. The proposed space-variant model has two effective image representations for object recognition and motion analysis, respectively. Each image representation is based on properties of two types of ganglion cell, which are the beginning of two basic visual pathways; one is parvocellular and the other is magnocellular. Through this model, we can get the efficient data reduction capability with no great loss of important information. And, the proposed multiple objects tracking method is restricted in space-variant image. Typically, an object-tracking algorithm consists of several processes such as detection, prediction, matching, and updating. In particular, the matching process plays an important role in multiple objects tracking. In traditional vision, the matching process is simple when the target objects are rigid. In space-variant vision, however, it is very complicated although the target is rigid, because there may be deformation of an object region in the space-variant coordinate system when the target moves to another position. Therefore, we propose a deformation formula in order to solve the matching problem in space-variant vision. By solving this problem, we can efficiently implement multiple objects tracking in space-variant vision.",
keywords = "Biologically motivated vision, Multiple objects tracking, Space-variant vision",
author = "Seonghoon Kang and Lee, {Seong Whan}",
year = "2002",
month = "10",
day = "1",
doi = "10.1016/S0031-3203(01)00200-X",
language = "English",
volume = "35",
pages = "2031--2040",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "10",

}

TY - JOUR

T1 - Real-time tracking of multiple objects in space-variant vision based on magnocellular visual pathway

AU - Kang, Seonghoon

AU - Lee, Seong Whan

PY - 2002/10/1

Y1 - 2002/10/1

N2 - In this paper, we propose a space-variant image representation model based on properties of magnocellular visual pathway, which perform motion analysis, in human retina. Then, we present an algorithm for the tracking of multiple objects in the proposed space-variant model. The proposed space-variant model has two effective image representations for object recognition and motion analysis, respectively. Each image representation is based on properties of two types of ganglion cell, which are the beginning of two basic visual pathways; one is parvocellular and the other is magnocellular. Through this model, we can get the efficient data reduction capability with no great loss of important information. And, the proposed multiple objects tracking method is restricted in space-variant image. Typically, an object-tracking algorithm consists of several processes such as detection, prediction, matching, and updating. In particular, the matching process plays an important role in multiple objects tracking. In traditional vision, the matching process is simple when the target objects are rigid. In space-variant vision, however, it is very complicated although the target is rigid, because there may be deformation of an object region in the space-variant coordinate system when the target moves to another position. Therefore, we propose a deformation formula in order to solve the matching problem in space-variant vision. By solving this problem, we can efficiently implement multiple objects tracking in space-variant vision.

AB - In this paper, we propose a space-variant image representation model based on properties of magnocellular visual pathway, which perform motion analysis, in human retina. Then, we present an algorithm for the tracking of multiple objects in the proposed space-variant model. The proposed space-variant model has two effective image representations for object recognition and motion analysis, respectively. Each image representation is based on properties of two types of ganglion cell, which are the beginning of two basic visual pathways; one is parvocellular and the other is magnocellular. Through this model, we can get the efficient data reduction capability with no great loss of important information. And, the proposed multiple objects tracking method is restricted in space-variant image. Typically, an object-tracking algorithm consists of several processes such as detection, prediction, matching, and updating. In particular, the matching process plays an important role in multiple objects tracking. In traditional vision, the matching process is simple when the target objects are rigid. In space-variant vision, however, it is very complicated although the target is rigid, because there may be deformation of an object region in the space-variant coordinate system when the target moves to another position. Therefore, we propose a deformation formula in order to solve the matching problem in space-variant vision. By solving this problem, we can efficiently implement multiple objects tracking in space-variant vision.

KW - Biologically motivated vision

KW - Multiple objects tracking

KW - Space-variant vision

UR - http://www.scopus.com/inward/record.url?scp=0036779073&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036779073&partnerID=8YFLogxK

U2 - 10.1016/S0031-3203(01)00200-X

DO - 10.1016/S0031-3203(01)00200-X

M3 - Article

VL - 35

SP - 2031

EP - 2040

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 10

ER -