FPGA Based High Accuracy Optical Flow Algorithm

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Motion estimation of a scene is an interesting problem in computer vision since it is the basis for the dynamic analysis of a scene. However this task is computationally intensive for conventional processors. In this work, an FPGA-based hardware architecture for real-time motion estimation is proposed. The algorithm implemented in hardware is a gradient based inverse finite element method for optical flow computation.It manages the motion estimation of the image by calculating the Gradient, Laplacian, and Velocities of each pixel in a parallel design which improves computational speed. The algorithm used in this paper has been benchmarked against many of the well known algorithms and shows superior performance in terms of average angular error and standard deviation. The FPGA design is presented with preliminary results and discussed.
LanguageEnglish
Title of host publicationUnknown Host Publication
Number of pages6
Publication statusPublished - Jun 2010
EventISSC 2010, UCC, Cork, June 23–24 -
Duration: 1 Jun 2010 → …

Conference

ConferenceISSC 2010, UCC, Cork, June 23–24
Period1/06/10 → …

Fingerprint

Optical flows
Motion estimation
Field programmable gate arrays (FPGA)
Dynamic analysis
Computer hardware
Computer vision
Pixels
Hardware
Finite element method

Cite this

@inproceedings{8c2c67a81770471eae518c7e667204ac,
title = "FPGA Based High Accuracy Optical Flow Algorithm",
abstract = "Motion estimation of a scene is an interesting problem in computer vision since it is the basis for the dynamic analysis of a scene. However this task is computationally intensive for conventional processors. In this work, an FPGA-based hardware architecture for real-time motion estimation is proposed. The algorithm implemented in hardware is a gradient based inverse finite element method for optical flow computation.It manages the motion estimation of the image by calculating the Gradient, Laplacian, and Velocities of each pixel in a parallel design which improves computational speed. The algorithm used in this paper has been benchmarked against many of the well known algorithms and shows superior performance in terms of average angular error and standard deviation. The FPGA design is presented with preliminary results and discussed.",
author = "Alan Browne and TM McGinnity and G Prasad and Joan Condell",
year = "2010",
month = "6",
language = "English",
booktitle = "Unknown Host Publication",

}

Browne, A, McGinnity, TM, Prasad, G & Condell, J 2010, FPGA Based High Accuracy Optical Flow Algorithm. in Unknown Host Publication. ISSC 2010, UCC, Cork, June 23–24, 1/06/10.

FPGA Based High Accuracy Optical Flow Algorithm. / Browne, Alan; McGinnity, TM; Prasad, G; Condell, Joan.

Unknown Host Publication. 2010.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - FPGA Based High Accuracy Optical Flow Algorithm

AU - Browne, Alan

AU - McGinnity, TM

AU - Prasad, G

AU - Condell, Joan

PY - 2010/6

Y1 - 2010/6

N2 - Motion estimation of a scene is an interesting problem in computer vision since it is the basis for the dynamic analysis of a scene. However this task is computationally intensive for conventional processors. In this work, an FPGA-based hardware architecture for real-time motion estimation is proposed. The algorithm implemented in hardware is a gradient based inverse finite element method for optical flow computation.It manages the motion estimation of the image by calculating the Gradient, Laplacian, and Velocities of each pixel in a parallel design which improves computational speed. The algorithm used in this paper has been benchmarked against many of the well known algorithms and shows superior performance in terms of average angular error and standard deviation. The FPGA design is presented with preliminary results and discussed.

AB - Motion estimation of a scene is an interesting problem in computer vision since it is the basis for the dynamic analysis of a scene. However this task is computationally intensive for conventional processors. In this work, an FPGA-based hardware architecture for real-time motion estimation is proposed. The algorithm implemented in hardware is a gradient based inverse finite element method for optical flow computation.It manages the motion estimation of the image by calculating the Gradient, Laplacian, and Velocities of each pixel in a parallel design which improves computational speed. The algorithm used in this paper has been benchmarked against many of the well known algorithms and shows superior performance in terms of average angular error and standard deviation. The FPGA design is presented with preliminary results and discussed.

M3 - Conference contribution

BT - Unknown Host Publication

ER -