000			03156nam a22003975i 4500
001			86344
003			ES-MaUEC
005			20230207040554.0
007			cr nn 008mamaa
008			160901s2016 gw | s |||| 0|eng d
020			_a9783319449418
040			_aES-MaUEC
050		4	_aQC367 _b.G537 2016
082	0	4	_a006.6
100	1		_aGibson, Joel _0Local _999996
245	1	0	_aOptical Flow and Trajectory Estimation Methods _cby Joel Gibson, Oge Marques
260			_aCham _bSpringer International Publishing _c2016
300			_a1 recurso en línea (X, 49 páginas) _b6 ilustraciones
336			_aTexto _btxt _2rdacontent
337			_aelectrónico _bc _2rdamedia
338			_arecurso electrónico _bcr _2rdacarrier
490	0		_aSpringerBriefs in Computer Science _x2191-5768
505	0		_aOptical Flow Fundamentals -- Optical Flow and Trajectory Methods in Context -- Sparse Regularization of TV-L Optical Flow -- Robust Low Rank Trajectories.
520	3		_aThis brief focuses on two main problems in the domain of optical flow and trajectory estimation: (i) The problem of finding convex optimization methods to apply sparsity to optical flow; and (ii) The problem of how to extend sparsity to improve trajectories in a computationally tractable way. Beginning with a review of optical flow fundamentals, it discusses the commonly used flow estimation strategies and the advantages or shortcomings of each. The brief also introduces the concepts associated with sparsity including dictionaries and low rank matrices. Next, it provides context for optical flow and trajectory methods including algorithms, data sets, and performance measurement. The second half of the brief covers sparse regularization of total variation optical flow and robust low rank trajectories. The authors describe a new approach that uses partially-overlapping patches to accelerate the calculation and is implemented in a coarse-to-fine strategy. Experimental results show that combining total variation and a sparse constraint from a learned dictionary is more effective than employing total variation alone. The brief is targeted at researchers and practitioners in the fields of engineering and computer science. It caters particularly to new researchers looking for cutting edge topics in optical flow as well as veterans of optical flow wishing to learn of the latest advances in multi-frame methods.
710	2		_aSpringerLink (Online service) _0Local _9106996
942			_2lcc _cLE
988			_aEBOOK, asignarmaterias , EBSPRINGER
650	0	7	_aGráficos de ordenador _0 _2embne _9141143
650		7	_aÓptica _0(OCoLC)1046776 _2embne _0 _9139211
700	1		_aMarques, Oge. _999997 _0Local
856	4	0	_uhttps://go.openathens.net/redirector/universidadeuropea.es?url=https://link.springer.com/book/10.1007/978-3-319-44941-8 _zAcceso a este recurso digital (usuarios Universidad Europea de Madrid)
901			_ai9783319449418
907			_a.b12956223 _b10-10-17 _c21-11-16
998			_am _a_alco _a_vill _b - - _cm _dz _e- _feng _ggw _h0
945			_aQC367 .G537 2016 EB _g1 _ieBOOK _j0 _lmae _o- _pEUR0.00 _q- _r- _sb _t15 _u0 _v0 _w0 _x0 _y.i11598165 _z06-04-17
999			_c86344 _d86344 _x1