Fourier Vision : Segmentation and Velocity Measurement Using the Fourier Transform

David Vernon

ISBN 10: 0792374134 / ISBN 13: 9780792374138

Editore: Springer Us Jun 2001, 2001

Riguardo questo articolo

Neuware - Fourier Vision provides a new treatment of figure-ground segmentation in scenes comprising transparent, translucent, or opaque objects. Exploiting the relative motion between figure and ground, this technique deals explicitly with the separation of additive signals and makes no assumptions about the spatial or spectral content of the images, with segmentation being carried out phasor by phasor in the Fourier domain. It works with several camera configurations, such as camera motion and short-baseline binocular stereo, and performs best on images with small velocities/displacements, typically one to ten pixels per frame. The book also addresses the use of Fourier techniques to estimate stereo disparity and optical flow. Numerous examples are provided throughout. Fourier Vision will be of value to researchers in image processing & computer vision and, especially, to those who have to deal with superimposed transparent or translucent objects. Researchers in application areas such as medical imaging and acoustic signal processing will also find this of interest.

Codice articolo 9780792374138

Dati bibliografici

• Titolo: Fourier Vision : Segmentation and Velocity Measurement Using the Fourier Transform
• Editore: Springer Us Jun 2001
• Data di pubblicazione: 2001
• Lingua: Inglese
• ISBN 10: 0792374134
• ISBN 13: 9780792374138
• Rilegatura: Buch
• Condizione: Neu
• Dimensioni: 240 L x 158 A x 17 P (millimetri) 240 millimetri di larghezza per 158 millimetri di altezza per 17 millimetri di profondità
• Peso: 467 grammi

Descrizione articolo

Riassunto

"Fourier Vision" provides a new treatment of figure-ground segmentation in scenes comprising transparent, translucent, or opaque objects. Exploiting the relative motion between figure and ground, this technique deals explicitly with the separation of additive signals and makes no assumptions about the spatial or spectral content of the images, with segmentation being carried out phasor by phasor in the Fourier domain. It works with several camera configurations, such as camera motion and short-baseline binocular stereo, and performs best on images with small velocities/displacements, typically one to ten pixels per frame. The book also addresses the use of Fourier techniques to estimate stereo disparity and optical flow. Numerous examples are provided throughout."Four ier Vision" should be of value to researchers in image processing and computer vision and, especially, to those who have to deal with superimposed transparent or translucent objects. Researchers in application areas such as medical imaging and acoustic signal processing will also find this of interest.

Contenuti

Preface. 1. Introduction. 2. Mathematical Preliminaries. 3. Monocular Vision - Segmentation in Additive Images. 4. Monocular Vision - Segmentation in Occluding Images. 5. Articulated Binocular Vision. 6. Fronto-Parallel Binocular Vision. 7. Instantaneous Optical Flow. 8. Decoupled Optical Flow. 9. Epilogue.