A novel module of tracking vehicles with occlusion

Lin Zhu; Jingyan Song; Qiao Huang; Ming Zhang; Hongchao Liu

doi:10.1109/IVS.2005.1505219

A novel module of tracking vehicles with occlusion

Lin Zhu, Jingyan Song, Qiao Huang, Ming Zhang, Hongchao Liu

Civil Environ Construct Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Scopus citations

Abstract

Video surveillance technology has been widely used in Intelligent Transportation System (ITS) to measure traffic flow parameters and detect accidents. Occlusion of moving objects by stationary or other moving foreground objects always causes tracking errors. This paper presents a novel module for vehicle tracking under the condition of occlusion, which can be conveniently added to the existing video surveillance systems as a complementary part. The appearance information of the object (shape and texture) is combined with the spatial-temporal Markov Random Field (MRF) based tracking model through a kind of special structuring elements in Mathematical Morphology (MM) theory. As a result, the sites in MRF are reduced, which saves computational cost greatly, and the assumption on the vehicle shape model in prior is not needed. Experiments on various kinds of image sequences show that the proposed module can effectively track vehicles with severe occlusion.

Original language	English
Title of host publication	2005 IEEE Intelligent Vehicles Symposium, Proceedings
Pages	894-899
Number of pages	6
DOIs	https://doi.org/10.1109/IVS.2005.1505219
State	Published - 2005
Event	2005 IEEE Intelligent Vehicles Symposium - Las Vegas, NV, United States Duration: Jun 6 2005 → Jun 8 2005

Publication series

Name	IEEE Intelligent Vehicles Symposium, Proceedings
Volume	2005

Conference

Conference	2005 IEEE Intelligent Vehicles Symposium
Country	United States
City	Las Vegas, NV
Period	06/6/05 → 06/8/05

Access to Document

10.1109/IVS.2005.1505219

Link to publication in Scopus

Fingerprint Dive into the research topics of 'A novel module of tracking vehicles with occlusion'. Together they form a unique fingerprint.

Cite this

Zhu, L., Song, J., Huang, Q., Zhang, M., & Liu, H. (2005). A novel module of tracking vehicles with occlusion. In 2005 IEEE Intelligent Vehicles Symposium, Proceedings (pp. 894-899). [1505219] (IEEE Intelligent Vehicles Symposium, Proceedings; Vol. 2005). https://doi.org/10.1109/IVS.2005.1505219

@inproceedings{1e272ae9b9c64514a321614c4c933997,

title = "A novel module of tracking vehicles with occlusion",

abstract = "Video surveillance technology has been widely used in Intelligent Transportation System (ITS) to measure traffic flow parameters and detect accidents. Occlusion of moving objects by stationary or other moving foreground objects always causes tracking errors. This paper presents a novel module for vehicle tracking under the condition of occlusion, which can be conveniently added to the existing video surveillance systems as a complementary part. The appearance information of the object (shape and texture) is combined with the spatial-temporal Markov Random Field (MRF) based tracking model through a kind of special structuring elements in Mathematical Morphology (MM) theory. As a result, the sites in MRF are reduced, which saves computational cost greatly, and the assumption on the vehicle shape model in prior is not needed. Experiments on various kinds of image sequences show that the proposed module can effectively track vehicles with severe occlusion.",

author = "Lin Zhu and Jingyan Song and Qiao Huang and Ming Zhang and Hongchao Liu",

year = "2005",

doi = "10.1109/IVS.2005.1505219",

language = "English",

isbn = "0780389611",

series = "IEEE Intelligent Vehicles Symposium, Proceedings",

pages = "894--899",

booktitle = "2005 IEEE Intelligent Vehicles Symposium, Proceedings",

note = "null ; Conference date: 06-06-2005 Through 08-06-2005",

}

TY - GEN

T1 - A novel module of tracking vehicles with occlusion

AU - Zhu, Lin

AU - Song, Jingyan

AU - Huang, Qiao

AU - Zhang, Ming

AU - Liu, Hongchao

PY - 2005

Y1 - 2005

N2 - Video surveillance technology has been widely used in Intelligent Transportation System (ITS) to measure traffic flow parameters and detect accidents. Occlusion of moving objects by stationary or other moving foreground objects always causes tracking errors. This paper presents a novel module for vehicle tracking under the condition of occlusion, which can be conveniently added to the existing video surveillance systems as a complementary part. The appearance information of the object (shape and texture) is combined with the spatial-temporal Markov Random Field (MRF) based tracking model through a kind of special structuring elements in Mathematical Morphology (MM) theory. As a result, the sites in MRF are reduced, which saves computational cost greatly, and the assumption on the vehicle shape model in prior is not needed. Experiments on various kinds of image sequences show that the proposed module can effectively track vehicles with severe occlusion.

AB - Video surveillance technology has been widely used in Intelligent Transportation System (ITS) to measure traffic flow parameters and detect accidents. Occlusion of moving objects by stationary or other moving foreground objects always causes tracking errors. This paper presents a novel module for vehicle tracking under the condition of occlusion, which can be conveniently added to the existing video surveillance systems as a complementary part. The appearance information of the object (shape and texture) is combined with the spatial-temporal Markov Random Field (MRF) based tracking model through a kind of special structuring elements in Mathematical Morphology (MM) theory. As a result, the sites in MRF are reduced, which saves computational cost greatly, and the assumption on the vehicle shape model in prior is not needed. Experiments on various kinds of image sequences show that the proposed module can effectively track vehicles with severe occlusion.

UR - http://www.scopus.com/inward/record.url?scp=33745934256&partnerID=8YFLogxK

U2 - 10.1109/IVS.2005.1505219

DO - 10.1109/IVS.2005.1505219

M3 - Conference contribution

AN - SCOPUS:33745934256

SN - 0780389611

SN - 9780780389618

T3 - IEEE Intelligent Vehicles Symposium, Proceedings

SP - 894

EP - 899

BT - 2005 IEEE Intelligent Vehicles Symposium, Proceedings

Y2 - 6 June 2005 through 8 June 2005

ER -