Abstract | ||
---|---|---|
We introduce the concept of complementarity between data and smoothness term in modern variational optic flow methods. First we design a sophisticated data term that incorporates HSV colour rep- resentation with higher order constancy assumptions, completely sepa- rate robust penalisation, and constraint normalisation. Our anisotropic smoothness term reduces smoothing in the data constraint direction in- stead of the image edge direction, while enforcing a strong filling-in ef- fect orthogonal to it. This allows optimal complementarity between both terms and avoids undesirable interference. The high quality of our com- plementary optic flow (COF) approach is demonstrated by the current top ranking result at the Middlebury benchmark. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1007/978-3-642-03641-5_16 | Energy Minimization Methods in Computer Vision and Pattern Recognition |
Keywords | Field | DocType |
complementary optic flow,hsv colour representation,constraint normalisation,data constraint direction,modern variational optic flow,image edge direction,optimal complementarity,anisotropic smoothness term,smoothness term,sophisticated data term,higher order,optical flow | Complementarity (molecular biology),Mathematical optimization,Ranking,Computer science,Flow (psychology),Algorithm,Smoothing,Interference (wave propagation),Structure tensor,Smoothness | Conference |
Volume | ISSN | Citations |
5681 | 0302-9743 | 39 |
PageRank | References | Authors |
2.32 | 18 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Henning Zimmer | 1 | 530 | 21.88 |
Andrés Bruhn | 2 | 1558 | 82.42 |
Joachim Weickert | 3 | 5489 | 391.03 |
Levi Valgaerts | 4 | 470 | 15.88 |
Agust ´ in Salgado | 5 | 68 | 7.80 |
Bodo Rosenhahn | 6 | 1733 | 137.77 |
Hans-Peter Seidel | 7 | 12532 | 801.49 |