FPGA implementation of a change-driven image processing architecture for optical flow computation

Julio C. Sosa; Rocío Gómez-Fabela; José A. Boluda; Fernando Pardo

doi:10.1109/FPL.2006.311285

FPGA implementation of a change-driven image processing architecture for optical flow computation

Julio C. Sosa, Rocío Gómez-Fabela, José A. Boluda, Fernando Pardo

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

1 Scopus citations

Abstract

Optical flow computation has been extensively used for object motion estimation in image sequences. However, the results obtained by most optical flow techniques are as accurate as computationally intensive due to the large amount of data involved. A new strategy for image sequence processing has been developed; pixels of the image sequence that significantly change fire the execution of the operations related to the image processing algorithm. The data reduction achieved with this strategy allows a significant optical flow computation speed up. Furthermore, FPGAs allow the implementation of a custom data-flow architecture specially suited for this strategy. The bases of the change-driven image processing are presented, as well as the hardware custom implementation.

Original language	English
Title of host publication	Proceedings - 2006 International Conference on Field Programmable Logic and Applications, FPL
Pages	663-666
Number of pages	4
DOIs	https://doi.org/10.1109/FPL.2006.311285
State	Published - 2006
Externally published	Yes
Event	2006 International Conference on Field Programmable Logic and Applications, FPL - Madrid, Spain Duration: 28 Aug 2006 → 30 Aug 2006

Publication series

Name	Proceedings - 2006 International Conference on Field Programmable Logic and Applications, FPL

Conference

Conference	2006 International Conference on Field Programmable Logic and Applications, FPL
Country/Territory	Spain
City	Madrid
Period	28/08/06 → 30/08/06

Access to Document

10.1109/FPL.2006.311285

Cite this

Sosa, J. C., Gómez-Fabela, R., Boluda, J. A., & Pardo, F. (2006). FPGA implementation of a change-driven image processing architecture for optical flow computation. In Proceedings - 2006 International Conference on Field Programmable Logic and Applications, FPL (pp. 663-666). Article 4101047 (Proceedings - 2006 International Conference on Field Programmable Logic and Applications, FPL). https://doi.org/10.1109/FPL.2006.311285

Sosa, Julio C. ; Gómez-Fabela, Rocío ; Boluda, José A. et al. / FPGA implementation of a change-driven image processing architecture for optical flow computation. Proceedings - 2006 International Conference on Field Programmable Logic and Applications, FPL. 2006. pp. 663-666 (Proceedings - 2006 International Conference on Field Programmable Logic and Applications, FPL).

@inproceedings{22fc6bbe4b7e4fc1adfa6251bf97d286,

title = "FPGA implementation of a change-driven image processing architecture for optical flow computation",

abstract = "Optical flow computation has been extensively used for object motion estimation in image sequences. However, the results obtained by most optical flow techniques are as accurate as computationally intensive due to the large amount of data involved. A new strategy for image sequence processing has been developed; pixels of the image sequence that significantly change fire the execution of the operations related to the image processing algorithm. The data reduction achieved with this strategy allows a significant optical flow computation speed up. Furthermore, FPGAs allow the implementation of a custom data-flow architecture specially suited for this strategy. The bases of the change-driven image processing are presented, as well as the hardware custom implementation.",

author = "Sosa, {Julio C.} and Roc{\'i}o G{\'o}mez-Fabela and Boluda, {Jos{\'e} A.} and Fernando Pardo",

year = "2006",

doi = "10.1109/FPL.2006.311285",

language = "Ingl{\'e}s",

isbn = "142440312X",

series = "Proceedings - 2006 International Conference on Field Programmable Logic and Applications, FPL",

pages = "663--666",

booktitle = "Proceedings - 2006 International Conference on Field Programmable Logic and Applications, FPL",

note = "2006 International Conference on Field Programmable Logic and Applications, FPL ; Conference date: 28-08-2006 Through 30-08-2006",

}

Sosa, JC, Gómez-Fabela, R, Boluda, JA & Pardo, F 2006, FPGA implementation of a change-driven image processing architecture for optical flow computation. in Proceedings - 2006 International Conference on Field Programmable Logic and Applications, FPL., 4101047, Proceedings - 2006 International Conference on Field Programmable Logic and Applications, FPL, pp. 663-666, 2006 International Conference on Field Programmable Logic and Applications, FPL, Madrid, Spain, 28/08/06. https://doi.org/10.1109/FPL.2006.311285

FPGA implementation of a change-driven image processing architecture for optical flow computation. / Sosa, Julio C.; Gómez-Fabela, Rocío; Boluda, José A. et al.
Proceedings - 2006 International Conference on Field Programmable Logic and Applications, FPL. 2006. p. 663-666 4101047 (Proceedings - 2006 International Conference on Field Programmable Logic and Applications, FPL).

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

TY - GEN

T1 - FPGA implementation of a change-driven image processing architecture for optical flow computation

AU - Sosa, Julio C.

AU - Gómez-Fabela, Rocío

AU - Boluda, José A.

AU - Pardo, Fernando

PY - 2006

Y1 - 2006

N2 - Optical flow computation has been extensively used for object motion estimation in image sequences. However, the results obtained by most optical flow techniques are as accurate as computationally intensive due to the large amount of data involved. A new strategy for image sequence processing has been developed; pixels of the image sequence that significantly change fire the execution of the operations related to the image processing algorithm. The data reduction achieved with this strategy allows a significant optical flow computation speed up. Furthermore, FPGAs allow the implementation of a custom data-flow architecture specially suited for this strategy. The bases of the change-driven image processing are presented, as well as the hardware custom implementation.

AB - Optical flow computation has been extensively used for object motion estimation in image sequences. However, the results obtained by most optical flow techniques are as accurate as computationally intensive due to the large amount of data involved. A new strategy for image sequence processing has been developed; pixels of the image sequence that significantly change fire the execution of the operations related to the image processing algorithm. The data reduction achieved with this strategy allows a significant optical flow computation speed up. Furthermore, FPGAs allow the implementation of a custom data-flow architecture specially suited for this strategy. The bases of the change-driven image processing are presented, as well as the hardware custom implementation.

UR - http://www.scopus.com/inward/record.url?scp=46249116251&partnerID=8YFLogxK

U2 - 10.1109/FPL.2006.311285

DO - 10.1109/FPL.2006.311285

M3 - Contribución a la conferencia

AN - SCOPUS:46249116251

SN - 142440312X

SN - 9781424403127

T3 - Proceedings - 2006 International Conference on Field Programmable Logic and Applications, FPL

SP - 663

EP - 666

BT - Proceedings - 2006 International Conference on Field Programmable Logic and Applications, FPL

T2 - 2006 International Conference on Field Programmable Logic and Applications, FPL

Y2 - 28 August 2006 through 30 August 2006

ER -

Sosa JC, Gómez-Fabela R, Boluda JA, Pardo F. FPGA implementation of a change-driven image processing architecture for optical flow computation. In Proceedings - 2006 International Conference on Field Programmable Logic and Applications, FPL. 2006. p. 663-666. 4101047. (Proceedings - 2006 International Conference on Field Programmable Logic and Applications, FPL). doi: 10.1109/FPL.2006.311285

FPGA implementation of a change-driven image processing architecture for optical flow computation

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this