Napredna pretraga

Pregled bibliografske jedinice broj: 55651

Optical Flow Estimation over Extended Image Sequence


Stanisavljević, Vladimir; Kalafatić, Zoran; Ribarić, Slobodan
Optical Flow Estimation over Extended Image Sequence // Proceedings of the 10th Mediterranean Electrotechnical Conference : MELECON 2000 ; Vol. II : Signal and Image Processing / Constantinos, Pattichis S. ; Stathis, Panis (ur.).
Limassol: IEEE, 2000. str. 546-550 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)


Naslov
Optical Flow Estimation over Extended Image Sequence

Autori
Stanisavljević, Vladimir ; Kalafatić, Zoran ; Ribarić, Slobodan

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of the 10th Mediterranean Electrotechnical Conference : MELECON 2000 ; Vol. II : Signal and Image Processing / Constantinos, Pattichis S. ; Stathis, Panis - Limassol : IEEE, 2000, 546-550

Skup
Mediterranean Electrotechnical Conference (10 ; 2000)

Mjesto i datum
Limassol, Cipar, 29-31. 05.2000

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Computer vision; optical flow; temporal refinement

Sažetak
A number of proposed optical flow estimation algorithms for image motion analysis use only a few subsequent frames from an image sequence to perform calculation. Others, that use many frames, as is case in frequency and energy based, as well as in stochastic optical flow algorithms, are better suited for off-line work. In this work we present our approach in adopting a classic gradient optical flow algorithm for on-line work over extended image sequence. Our experiments on usual optical flow testing image sequences, consisting of few dozens of image frames show significant improvements in accuracy of estimated velocity flow fields and in speed of computation. This is achieved by modification and integration of three basic processing phases: preparation of a limited spatio-temporal volume, estimation of velocity flow fields and post filtering of the flow fields. In the preparation phase we use efficient spatio-temporal filters for image smoothing. In estimation phase a modified iterative solution that propagates results from previous calculation steps is used. Linear and nonlinear post filtering additionally improve optical flow estimates. Whole process is less sensitive to apperture problem and produces more accurate flow field estimates then original algorithm. It better copes with motion discontinuities as well. We evidence our achievements by a number of experiments on extended image sequences.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo



POVEZANOST RADA


Projekt / tema
036022
036023

Ustanove
Fakultet elektrotehnike i računarstva, Zagreb

Citiraj ovu publikaciju

Stanisavljević, Vladimir; Kalafatić, Zoran; Ribarić, Slobodan
Optical Flow Estimation over Extended Image Sequence // Proceedings of the 10th Mediterranean Electrotechnical Conference : MELECON 2000 ; Vol. II : Signal and Image Processing / Constantinos, Pattichis S. ; Stathis, Panis (ur.).
Limassol: IEEE, 2000. str. 546-550 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
Stanisavljević, V., Kalafatić, Z. & Ribarić, S. (2000) Optical Flow Estimation over Extended Image Sequence. U: Constantinos, P. & Stathis, P. (ur.)Proceedings of the 10th Mediterranean Electrotechnical Conference : MELECON 2000 ; Vol. II : Signal and Image Processing.
@article{article, year = {2000}, pages = {546-550}, keywords = {computer vision, optical flow, temporal refinement}, title = {Optical Flow Estimation over Extended Image Sequence}, keyword = {computer vision, optical flow, temporal refinement}, publisher = {IEEE}, publisherplace = {Limassol, Cipar} }