大葉大學圖書館 |

Optical flow and trajectory estimation methods[electronic resource] /

紀錄類型:	書目-電子資源 : Monograph/item
杜威分類號:	681.25
書名/作者:	Optical flow and trajectory estimation methods/ by Joel Gibson, Oge Marques.
作者:	Gibson, Joel.
其他作者:	Marques, Oge.
出版者:	Cham : : Springer International Publishing :, 2016.
面頁冊數:	x, 49 p. : : ill., digital ;; 24 cm.
Contained By:	Springer eBooks
標題:	Computer Science.
標題:	Computer Imaging, Vision, Pattern Recognition and Graphics.
標題:	Optical measurements.
ISBN:	9783319449418
ISBN:	9783319449401
內容註:	Optical Flow Fundamentals -- Optical Flow and Trajectory Methods in Context -- Sparse Regularization of TV-L Optical Flow -- Robust Low Rank Trajectories.
摘要、提要註:	This 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.
電子資源:	http://dx.doi.org/10.1007/978-3-319-44941-8

Optical flow and trajectory estimation methods[electronic resource] /
Gibson, Joel.

Optical flow and trajectory estimation methods[electronic resource] /by Joel Gibson, Oge Marques. - Cham :Springer International Publishing :2016. - x, 49 p. :ill., digital ;24 cm. - SpringerBriefs in computer science,2191-5768. - SpringerBriefs in computer science..

Optical Flow Fundamentals -- Optical Flow and Trajectory Methods in Context -- Sparse Regularization of TV-L Optical Flow -- Robust Low Rank Trajectories.

This 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.

ISBN: 9783319449418

Standard No.: 10.1007/978-3-319-44941-8doiSubjects--Topical Terms:

423143
Computer Science.

LC Class. No.: QC367

Dewey Class. No.: 681.25

Optical flow and trajectory estimation methods[electronic resource] /
LDR:02563nmm a2200325 a 4500 001 466200
003 DE-He213
005 20160901141242.0
006 m d
007 cr nn 008maaau
008 170415s2016 gw s 0 eng d
020 $a 9783319449418 $q (electronic bk.)
020 $a 9783319449401 $q (paper)
024 7 $a 10.1007/978-3-319-44941-8 $2 doi
035 $a 978-3-319-44941-8
040 $a GP $c GP
041 0 $a eng
050 4 $a QC367
072 7 $a UYQV $2 bicssc
072 7 $a COM016000 $2 bisacsh
082 0 4 $a 681.25 $2 23
090 $a QC367 $b .G449 2016
100 1 $a Gibson, Joel. $3 670860
245 1 0 $a Optical flow and trajectory estimation methods $h [electronic resource] / $c by Joel Gibson, Oge Marques.
260 $a Cham : $b Springer International Publishing : $b Imprint: Springer, $c 2016.
300 $a x, 49 p. : $b ill., digital ; $c 24 cm.
490 1 $a SpringerBriefs in computer science, $x 2191-5768
505 0 $a Optical Flow Fundamentals -- Optical Flow and Trajectory Methods in Context -- Sparse Regularization of TV-L Optical Flow -- Robust Low Rank Trajectories.
520 $a This 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.
650 1 4 $a Computer Science. $3 423143
650 2 4 $a Computer Imaging, Vision, Pattern Recognition and Graphics. $3 465964
650 0 $a Optical measurements. $3 174032
700 1 $a Marques, Oge. $3 600685
710 2 $a SpringerLink (Online service) $3 463450
773 0 $t Springer eBooks
830 0 $a SpringerBriefs in computer science. $3 466946
856 4 0 $u http://dx.doi.org/10.1007/978-3-319-44941-8
950 $a Computer Science (Springer-11645)