Scale and rotation invariant detection of singular patterns in vector flow fields. Liu, W. & Ribeiro, E. 2010.
Scale and rotation invariant detection of singular patterns in vector flow fields [link]Website  doi  abstract   bibtex   
We present a method for detecting and describing features in vector flow fields. Our method models flow fields locally using a linear combination of complex monomials. These monomials form an orthogonal basis for analytic flows with respect to a correlation-based inner-product. We investigate the invariance properties of the coefficients of the approximation polynomials under both rotation and scaling operators. We then propose a descriptor for local flow patterns, and developed a method for comparing them invariantly against rigid transformations. Additionally, we propose a SIFT-like detector that can automatically detect singular flow patterns at different scales and orientations. Promising detection results are obtained on different fluid flow data.
@misc{
 title = {Scale and rotation invariant detection of singular patterns in vector flow fields},
 type = {misc},
 year = {2010},
 source = {Structural, Syntactic, and Statistical Pattern Recognition},
 pages = {522-531},
 volume = {6218},
 websites = {http://link.springer.com/10.1007/978-3-642-14980-1_51},
 publisher = {Springer, Berlin, Heidelberg},
 id = {87624f2f-71c5-35a8-8049-4b22ce15c2a2},
 created = {2021-04-09T15:24:19.096Z},
 file_attached = {false},
 profile_id = {75799766-8e2d-3c98-81f9-e3efa41233d0},
 group_id = {c9329632-2a50-3043-b803-cadc8dbdfc3f},
 last_modified = {2021-04-09T15:24:19.096Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 source_type = {book_section},
 private_publication = {false},
 abstract = {We present a method for detecting and describing features in vector flow fields. Our method models flow fields locally using a linear combination of complex monomials. These monomials form an orthogonal basis for analytic flows with respect to a correlation-based inner-product. We investigate the invariance properties of the coefficients of the approximation polynomials under both rotation and scaling operators. We then propose a descriptor for local flow patterns, and developed a method for comparing them invariantly against rigid transformations. Additionally, we propose a SIFT-like detector that can automatically detect singular flow patterns at different scales and orientations. Promising detection results are obtained on different fluid flow data.},
 bibtype = {misc},
 author = {Liu, Wei and Ribeiro, Eraldo},
 doi = {10.1007/978-3-642-14980-1_51}
}

Downloads: 0