Tracking of moving objects using neural network

K. C. Chan; S. S. Leong; J. Xie; G. C.L. Lin; B. Shirinzadeh

Tracking of moving objects using neural network

K. C. Chan, S. S. Leong, J. Xie, G. C.L. Lin, B. Shirinzadeh

Research output: Contribution to conference › Paper

Abstract

This paper presents a new technique for tracking of two dimensional moving objects. The approach is a hybrid consisting of an algorithm for next position prediction using an estimated jerk, and a neural network for pose (position and orientation) determination. A three layer feed-forward perceptron with back-propagation is implemented as a mapping approximator to determine the object pose from the area information contained in a localized processing window. Objects with arbitrary shapes can be tracked after the network is properly trained. The experimental result of the implementation of this algorithm is also presented.

Original language	English
Pages	231-234
Number of pages	4
Publication status	Published - 1 Dec 1992
Externally published	Yes
Event	Proceedings of the 1992 Japan - USA Symposium on Flexible Automation Part 1 (of 2) - San Francisco, United States of America Duration: 13 Jul 1992 → 15 Jul 1992

Conference

Conference	Proceedings of the 1992 Japan - USA Symposium on Flexible Automation Part 1 (of 2)
Country/Territory	United States of America
City	San Francisco
Period	13/07/92 → 15/07/92

Cite this

@conference{c6e8a1e5e5ac494783cc3a33b74a7821,

title = "Tracking of moving objects using neural network",

abstract = "This paper presents a new technique for tracking of two dimensional moving objects. The approach is a hybrid consisting of an algorithm for next position prediction using an estimated jerk, and a neural network for pose (position and orientation) determination. A three layer feed-forward perceptron with back-propagation is implemented as a mapping approximator to determine the object pose from the area information contained in a localized processing window. Objects with arbitrary shapes can be tracked after the network is properly trained. The experimental result of the implementation of this algorithm is also presented.",

author = "Chan, \{K. C.\} and Leong, \{S. S.\} and J. Xie and Lin, \{G. C.L.\} and B. Shirinzadeh",

year = "1992",

month = dec,

day = "1",

language = "English",

pages = "231--234",

note = "Proceedings of the 1992 Japan - USA Symposium on Flexible Automation Part 1 (of 2) ; Conference date: 13-07-1992 Through 15-07-1992",

}

TY - CONF

T1 - Tracking of moving objects using neural network

AU - Chan, K. C.

AU - Leong, S. S.

AU - Xie, J.

AU - Lin, G. C.L.

AU - Shirinzadeh, B.

PY - 1992/12/1

Y1 - 1992/12/1

N2 - This paper presents a new technique for tracking of two dimensional moving objects. The approach is a hybrid consisting of an algorithm for next position prediction using an estimated jerk, and a neural network for pose (position and orientation) determination. A three layer feed-forward perceptron with back-propagation is implemented as a mapping approximator to determine the object pose from the area information contained in a localized processing window. Objects with arbitrary shapes can be tracked after the network is properly trained. The experimental result of the implementation of this algorithm is also presented.

AB - This paper presents a new technique for tracking of two dimensional moving objects. The approach is a hybrid consisting of an algorithm for next position prediction using an estimated jerk, and a neural network for pose (position and orientation) determination. A three layer feed-forward perceptron with back-propagation is implemented as a mapping approximator to determine the object pose from the area information contained in a localized processing window. Objects with arbitrary shapes can be tracked after the network is properly trained. The experimental result of the implementation of this algorithm is also presented.

UR - https://www.scopus.com/pages/publications/0026964207

M3 - Paper

AN - SCOPUS:0026964207

SP - 231

EP - 234

T2 - Proceedings of the 1992 Japan - USA Symposium on Flexible Automation Part 1 (of 2)

Y2 - 13 July 1992 through 15 July 1992

ER -

Tracking of moving objects using neural network

Abstract

Conference

Other files and links

Cite this