Hardware Acceleration For Tracking By Computing Low-Order Geometrical Moments

J.A. Vijverberg; P.H.N. With, de

Hardware Acceleration For Tracking By Computing Low-Order Geometrical Moments

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

With the growing number of video content analysis applications, efficient implementation has become increasingly important. Video-object tracking using image moments is an important subtask in video-content analysis content algorithms. In this paper, we will present a method of accelerating the computation of geometrical moments and the resulting moment engine to a throughput of 130-fps. Furthermore, the effect of the accelerator on the performance of two object-tracking applications in a multi-processor platform will be evaluated. The conclusion is that the moment engine is relatively inexpensive in terms of required gate area, but its integration efficiency into a domain-specific multi-processor platform remains to be further analyzed.

Original language	English
Title of host publication	Proceedings of the IEEE Workshop On Signal Processing Systems
Place of Publication	Piscataway
Publisher	Institute of Electrical and Electronics Engineers
Pages	43-48
Publication status	Published - 2008
Event	conference; IEEE Workshop On Signal Processing Systems - Duration: 1 Jan 2008 → …

Conference

Conference	conference; IEEE Workshop On Signal Processing Systems
Period	1/01/08 → …
Other	IEEE Workshop On Signal Processing Systems

Cite this

@inproceedings{c6e4174f31ae47aea8cd1b277e845a80,

title = "Hardware Acceleration For Tracking By Computing Low-Order Geometrical Moments",

abstract = "With the growing number of video content analysis applications, efficient implementation has become increasingly important. Video-object tracking using image moments is an important subtask in video-content analysis content algorithms. In this paper, we will present a method of accelerating the computation of geometrical moments and the resulting moment engine to a throughput of 130-fps. Furthermore, the effect of the accelerator on the performance of two object-tracking applications in a multi-processor platform will be evaluated. The conclusion is that the moment engine is relatively inexpensive in terms of required gate area, but its integration efficiency into a domain-specific multi-processor platform remains to be further analyzed.",

author = "J.A. Vijverberg and {With, de}, P.H.N.",

year = "2008",

language = "English",

pages = "43--48",

booktitle = "Proceedings of the IEEE Workshop On Signal Processing Systems",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "conference; IEEE Workshop On Signal Processing Systems ; Conference date: 01-01-2008",

}

Hardware Acceleration For Tracking By Computing Low-Order Geometrical Moments. / Vijverberg, J.A.; With, de, P.H.N.
Proceedings of the IEEE Workshop On Signal Processing Systems. Piscataway: Institute of Electrical and Electronics Engineers, 2008. p. 43-48.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Hardware Acceleration For Tracking By Computing Low-Order Geometrical Moments

AU - Vijverberg, J.A.

AU - With, de, P.H.N.

PY - 2008

Y1 - 2008

N2 - With the growing number of video content analysis applications, efficient implementation has become increasingly important. Video-object tracking using image moments is an important subtask in video-content analysis content algorithms. In this paper, we will present a method of accelerating the computation of geometrical moments and the resulting moment engine to a throughput of 130-fps. Furthermore, the effect of the accelerator on the performance of two object-tracking applications in a multi-processor platform will be evaluated. The conclusion is that the moment engine is relatively inexpensive in terms of required gate area, but its integration efficiency into a domain-specific multi-processor platform remains to be further analyzed.

AB - With the growing number of video content analysis applications, efficient implementation has become increasingly important. Video-object tracking using image moments is an important subtask in video-content analysis content algorithms. In this paper, we will present a method of accelerating the computation of geometrical moments and the resulting moment engine to a throughput of 130-fps. Furthermore, the effect of the accelerator on the performance of two object-tracking applications in a multi-processor platform will be evaluated. The conclusion is that the moment engine is relatively inexpensive in terms of required gate area, but its integration efficiency into a domain-specific multi-processor platform remains to be further analyzed.

M3 - Conference contribution

SP - 43

EP - 48

BT - Proceedings of the IEEE Workshop On Signal Processing Systems

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

T2 - conference; IEEE Workshop On Signal Processing Systems

Y2 - 1 January 2008

ER -

Hardware Acceleration For Tracking By Computing Low-Order Geometrical Moments

Abstract

Conference

Fingerprint

Cite this