建國科技大學圖書館 |

語系: 繁體中文

說明(常見問題)

圖書館個人資料蒐集告知聲明

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Data association for multi-object vi...

Betke, Margrit.

Data association for multi-object visual tracking

紀錄類型:	書目-語言資料,印刷品 : 單行本
作者:	BetkeMargrit.,
其他作者:	WuZheng,
出版地:	[San Rafael, California]
出版者:	Morgan & Claypool;
出版年:	2017.
面頁冊數:	ix, 110 p.ill. : 24 cm.;
集叢名:	Synthesis lectures on computer vision# 9
標題:	Automatic tracking - Mathematical models. -
標題:	Computer vision - Mathematical models. -
標題:	Data integration (Computer science) -
附註:	Part of: Synthesis digital library of engineering and computer science.
摘要註:	This book serves as a tutorial on data association methods, intended for both students and experts in computer vision. We describe the basic research problems, review the current state ofthe art, and present some recently developed approaches. The bookcovers multi-object tracking in two and three dimensions. We consider two imaging scenarios involving either single cameras ormultiple cameras with overlapping fields of view, and requiring across-time and across-view data association methods. In additionto methods that match new measurements to already established tracks, we describe methods that match trajectory segments, also called tracklets. The book presents a principled application of data association to solve two interesting tasks: first, analyzingthe movements of groups of free-flying animals and second, reconstructing the movements of groups of pedestrians. We conclude by discussing exciting directions for future research--Page [4] of cover.
ISBN:	9781627059558
內容註:	Preface 1. An introduction to data association in computer vision: 1.1. Challenges; 1.2. Related topics beyond the scope of this book; 1.3. Application domains; 1.4. Simulation testbeds; 1.5. Experimental benchmarks; 1.6. Organization of the book 2.Classic sequential data association approaches: 2.1. Advantages of Kalman filters for use in multi-object tracking; 2.2. Gating; 2.3. Global nearest neighbor standard filter (GNNSF); 2.4. Joint probabilistic data association (JPDA); 2.5. Multiple hypotheses tracking (MHT); 2.6. Discussion 3. Classic batch data association approaches: 3.1. Markov chain Monte Carlo data association (MCMCDA); 3.2. Network flow data association (NFDA); 3.3. Probabilistic multiple hypothesis tracking (PMHT); 3.4. Discussion 4. Evaluation criteria: 4.1. Definitions; 4.2. Discussion 5. Tracking with multiple cameras: 5.1. The reconstruction-tracking approach; 5.2. The tracking-reconstruction approach; 5.3. An example of spatial data association; 5.4. Discussion 6. The tracklet linking approach:6.1. Review of existing work; 6.2. An example of tracklet linkingusing a track graph 7. Advanced techniques for data association: 7.1. Data association for merged or split measurements; 7.2. Learning-based data association; 7.3. Couplingdata association 8. Application to animal group tracking in 3D:8.1. Two sample systems for analyzing bat and bird flight; 8.2. Impact of multi-animal tracking systems 9. Benchmarks for human tracking: 9.1. PETS-2009; 9.2. Beyond PETS-2009: the MOT-challenge benchmark 10. Concluding remarks Bibliography Authors' biographies.

Data association for multi-object visual tracking
Betke, Margrit.

Data association for multi-object visual tracking / Margrit Betke, Zheng Wu. - [San Rafael, California] : Morgan & Claypool, 2017.. - ix, 110 p. ; ill. ; 24 cm.. - (Synthesis lectures on computer vision ; # 9).
Preface.
Part of: Synthesis digital library of engineering and computer science..
Includes bibliographical references (p. 85-108).
ISBN 9781627059558ISBN 1627059555
Automatic trackingComputer visionData integration (Computer science) -- Mathematical models. -- Mathematical models.

Wu, Zheng

Data association for multi-object visual tracking
LDR:03584nam0a2200265 4500 001 378769
010 1 $a 9781627059558 $b pbk. $d NT1361
010 1 $a 1627059555 $b pbk.
100 $a 20180528d2017 y0engy01 b
101 0 $a eng
102 $a us $b ca
105 $a a a 000yy
200 1 $a Data association for multi-object visual tracking $f Margrit Betke, Zheng Wu.
210 $a [San Rafael, California] $c Morgan & Claypool $d 2017.
215 1 $a ix, 110 p. $c ill. $d 24 cm.
225 2 $a Synthesis lectures on computer vision $v # 9 $x 2153-1056
300 $a Part of: Synthesis digital library of engineering and computer science.
320 $a Includes bibliographical references (p. 85-108)
327 1 $a Preface $a 1. An introduction to data association in computer vision: 1.1. Challenges; 1.2. Related topics beyond the scope of this book; 1.3. Application domains; 1.4. Simulation testbeds; 1.5. Experimental benchmarks; 1.6. Organization of the book $a 2.Classic sequential data association approaches: 2.1. Advantages of Kalman filters for use in multi-object tracking; 2.2. Gating; 2.3. Global nearest neighbor standard filter (GNNSF); 2.4. Joint probabilistic data association (JPDA); 2.5. Multiple hypotheses tracking (MHT); 2.6. Discussion $a 3. Classic batch data association approaches: 3.1. Markov chain Monte Carlo data association (MCMCDA); 3.2. Network flow data association (NFDA); 3.3. Probabilistic multiple hypothesis tracking (PMHT); 3.4. Discussion $a 4. Evaluation criteria: 4.1. Definitions; 4.2. Discussion $a 5. Tracking with multiple cameras: 5.1. The reconstruction-tracking approach; 5.2. The tracking-reconstruction approach; 5.3. An example of spatial data association; 5.4. Discussion $a 6. The tracklet linking approach:6.1. Review of existing work; 6.2. An example of tracklet linkingusing a track graph $a 7. Advanced techniques for data association: 7.1. Data association for merged or split measurements; 7.2. Learning-based data association; 7.3. Couplingdata association $a 8. Application to animal group tracking in 3D:8.1. Two sample systems for analyzing bat and bird flight; 8.2. Impact of multi-animal tracking systems $a 9. Benchmarks for human tracking: 9.1. PETS-2009; 9.2. Beyond PETS-2009: the MOT-challenge benchmark $a 10. Concluding remarks $a Bibliography $a Authors' biographies.
330 $a This book serves as a tutorial on data association methods, intended for both students and experts in computer vision. We describe the basic research problems, review the current state ofthe art, and present some recently developed approaches. The bookcovers multi-object tracking in two and three dimensions. We consider two imaging scenarios involving either single cameras ormultiple cameras with overlapping fields of view, and requiring across-time and across-view data association methods. In additionto methods that match new measurements to already established tracks, we describe methods that match trajectory segments, also called tracklets. The book presents a principled application of data association to solve two interesting tasks: first, analyzingthe movements of groups of free-flying animals and second, reconstructing the movements of groups of pedestrians. We conclude by discussing exciting directions for future research--Page [4] of cover.
410 0 $1 2001 $a Synthesis digital library of engineering and computer science.
410 0 $1 2001 $a Synthesis lectures on computer vision $v #9 $1 0111 $a 2153-1056.
410 0 $1 2001 $a Synthesis lectures on computer vision $v # 9 $x 2153-1056
606 $a Automatic tracking $x Mathematical models. $2 lc $3 366131
606 $a Computer vision $x Mathematical models. $2 lc $3 366132
606 $a Data integration (Computer science) $2 lc $3 366133
676 $a 005.7 $2 23
680 $a QA76.9.Q36 $b B485 2017b
700 1 $a Betke $b Margrit. $3 366129
702 1 $a Wu $b Zheng $c Computer scientist $3 366130
801 0 $a cw $b CTU $c 20180529 $g AACR2