國立虎尾科技大學 |

Long-Term Tracking by Decision Making.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Long-Term Tracking by Decision Making./
作者:	Supancic, James, III.
面頁冊數:	1 online resource (193 pages)
附註:	Source: Dissertation Abstracts International, Volume: 79-03(E), Section: B.
Contained By:	Dissertation Abstracts International79-03B(E).
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9780355307252

Long-Term Tracking by Decision Making.
Supancic, James, III.

Long-Term Tracking by Decision Making. - 1 online resource (193 pages)

Source: Dissertation Abstracts International, Volume: 79-03(E), Section: B.

Thesis (Ph.D.)

Includes bibliographical references

Cameras can naturally capture sequences of images, or videos, and for computers to understand videos, they must track to connect the past with the present. We focus on two problems which challenge current state-of-the-art trackers. First, we address the challenge of long-term occlusion. For this challenge, a tracker must know when it has lost track and how to reinitialize tracking when the target reappears. We tackle reinitialization by building good appearance models for humans and hands, with a particular emphasis on robustness and occlusion. For the second challenge, appearance variation, the tracker must know when and how to re-learn (or update) an appearance model. Common solutions to this challenge encounter the classic problem of drift: aggressively learning putative appearance changes allows small errors to compound, as elements of the background environment pollute the appearance model. We propose two solutions. First, we consider self-paced learning, wherein a tracker begins by learning from frames it finds easy. As the tracker becomes better at recognizing the target, it begins to learn from harder frames. We also develop a data-driven approach in which we train a tracking policy to decide when and how to update an appearance model. To take this direct approach to "learning when to learn", we exploit large-scale Internet data through reinforcement learning. We interpret the resulting policy and conclude with extensions for tracking multiple objects. By solving these tracking challenges, we advance applications in augmented reality, vehicle automation, healthcare, and security.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9780355307252Subjects--Topical Terms:

573171
Computer science.
Index Terms--Genre/Form:

554714
Electronic books.

Long-Term Tracking by Decision Making.
LDR:02904ntm a2200349Ki 4500 001 910776
005 20180517112610.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9780355307252
035 $a (MiAaPQ)AAI10286470
035 $a (MiAaPQ)uci:14497
035 $a AAI10286470
040 $a MiAaPQ $b eng $c MiAaPQ
099 $a TUL $f hyy $c available through World Wide Web
100 1 $a Supancic, James, III. $3 1182230
245 1 0 $a Long-Term Tracking by Decision Making.
264 0 $c 2017
300 $a 1 online resource (193 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertation Abstracts International, Volume: 79-03(E), Section: B.
500 $a Includes supplementary digital materials.
500 $a Adviser: Deva K. Ramanan.
502 $a Thesis (Ph.D.) $c University of California, Irvine $d 2017.
504 $a Includes bibliographical references
520 $a Cameras can naturally capture sequences of images, or videos, and for computers to understand videos, they must track to connect the past with the present. We focus on two problems which challenge current state-of-the-art trackers. First, we address the challenge of long-term occlusion. For this challenge, a tracker must know when it has lost track and how to reinitialize tracking when the target reappears. We tackle reinitialization by building good appearance models for humans and hands, with a particular emphasis on robustness and occlusion. For the second challenge, appearance variation, the tracker must know when and how to re-learn (or update) an appearance model. Common solutions to this challenge encounter the classic problem of drift: aggressively learning putative appearance changes allows small errors to compound, as elements of the background environment pollute the appearance model. We propose two solutions. First, we consider self-paced learning, wherein a tracker begins by learning from frames it finds easy. As the tracker becomes better at recognizing the target, it begins to learn from harder frames. We also develop a data-driven approach in which we train a tracking policy to decide when and how to update an appearance model. To take this direct approach to "learning when to learn", we exploit large-scale Internet data through reinforcement learning. We interpret the resulting policy and conclude with extensions for tracking multiple objects. By solving these tracking challenges, we advance applications in augmented reality, vehicle automation, healthcare, and security.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of California, Irvine. $b Computer Science - Ph.D.. $3 1182073
773 0 $t Dissertation Abstracts International $g 79-03B(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10286470 $z click for full text (PQDT)