Name
Abstract | ||
|---|---|---|
In this work, we describe a frequency domain technique for the estimation of multiple superimposed motions in an image sequence. The least-squares optimum approach involves the computation of the three-dimensional (3-D) Fourier transform of the sequence, followed by the detection of one or more planes in this domain with high energy concentration. We present a more efficient algorithm, based on the properties of the Radon transform and the two-dimensional (2-D) fast Fourier transform, which can sacrifice little performance for significant computational savings. We accomplish the motion detection and estimation by designing appropriate matched filters. The performance is demonstrated on two image sequences. |
Year | DOI | Venue |
|---|---|---|
1999 | 10.1109/83.748900 | IEEE Transactions on Image Processing |
Keywords | Field | DocType |
frequency domain technique,index terms— discrete fourier transform,motion detection,estimation,high energy concentration,motion estimation,efficient algorithm,matched filters.,image sequence,least-squares optimum approach,significant computational saving,image line pat- tern analysis,image motion analysis,performance,fourier transforms,fourier transform,filtering,discrete fourier transform,fast fourier transform,indexing terms,frequency domain,frequency domain analysis,matched filters,fast fourier transforms,matched filter,radon transform,least square,three dimensional | Computer vision,Non-uniform discrete Fourier transform,Spectral density estimation,Harmonic wavelet transform,Pattern recognition,Short-time Fourier transform,Fourier transform,Artificial intelligence,Motion estimation,Discrete Fourier transform,Radon transform,Mathematics | Journal |
Volume | Issue | ISSN |
8 | 3 | 1057-7149 |
Citations | PageRank | References |
19 | 1.29 | 13 |
Authors | ||
1 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Peyman Milanfar | 1 | 700 | 52.20 |