東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Spatio-temporal probabilistic infere...

University of Southern California., Computer Science.

Linked to FindBook

Google Book

Amazon

博客來

Spatio-temporal probabilistic inference for persistent object detection and tracking.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Spatio-temporal probabilistic inference for persistent object detection and tracking./
Author:	Yu, Qian.
Description:	138 p.
Notes:	Adviser: Gerard Medioni.
Contained By:	Dissertation Abstracts International70-05B.
Subject:	Computer Science. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3355319
ISBN:	9781109136807

Spatio-temporal probabilistic inference for persistent object detection and tracking.
Yu, Qian.

Spatio-temporal probabilistic inference for persistent object detection and tracking. - 138 p.

Adviser: Gerard Medioni.

Thesis (Ph.D.)--University of Southern California, 2009.

Tracking is a critical component of video analysis, as it provides the description of spatio-temporal relationships between observations and moving objects required by activity recognition modules. There are two tasks that we aim to address: (1) Multiple Target Tracking (MTT); (2) Tag-and-Track. The essential problem in MTT is to recover the data association between noisy observations and an unknown number of targets. To solve this problem, we proposed a Data-Driven Markov Chain Monte Carlo method to sample the data association space for a MAP (Maximum a Posterior) estimate that maximizes the spatio-temporal smoothness in both motion and appearance. Tag-and-Track is applied to track an arbitrary type of object given limited samples. The essential problem in Tag-and-Track is to establish and update an appearance model online to capture the visual signature of targets under varying circumstances, such as illumination changes, viewpoint changes and occlusions. We pose this Tag-and-Track problem as a semi-supervised learning problem, in which we aim to label a large number of unlabeled data given very limited labeled data (user selection). We propose to use two trackers combined in a Bayesian co-training framework, which unifies the CONDENSATION algorithm and co-training seamlessly. By using co-training, our method avoids learning errors reinforce themselves. In this thesis, we present the application of our method in detection and tracking of multiple moving object in airborne videos. In this application, we combine our core tracking algorithm with a set of motion detection and tracking techniques, including motion stabilization, geo-registration, etc., and demonstrate the robustness and efficiency of our methods

ISBN: 9781109136807Subjects--Topical Terms:

626642
Computer Science.

Spatio-temporal probabilistic inference for persistent object detection and tracking.
LDR:02718nmm 2200289 a 45 001 886720
005 20101007
008 101007s2009 ||||||||||||||||| ||eng d
020 $a 9781109136807
035 $a (UMI)AAI3355319
035 $a AAI3355319
040 $a UMI $c UMI
100 1 $a Yu, Qian. $3 1058430
245 1 0 $a Spatio-temporal probabilistic inference for persistent object detection and tracking.
300 $a 138 p.
500 $a Adviser: Gerard Medioni.
500 $a Source: Dissertation Abstracts International, Volume: 70-05, Section: B, page: 3017.
502 $a Thesis (Ph.D.)--University of Southern California, 2009.
520 $a Tracking is a critical component of video analysis, as it provides the description of spatio-temporal relationships between observations and moving objects required by activity recognition modules. There are two tasks that we aim to address: (1) Multiple Target Tracking (MTT); (2) Tag-and-Track. The essential problem in MTT is to recover the data association between noisy observations and an unknown number of targets. To solve this problem, we proposed a Data-Driven Markov Chain Monte Carlo method to sample the data association space for a MAP (Maximum a Posterior) estimate that maximizes the spatio-temporal smoothness in both motion and appearance. Tag-and-Track is applied to track an arbitrary type of object given limited samples. The essential problem in Tag-and-Track is to establish and update an appearance model online to capture the visual signature of targets under varying circumstances, such as illumination changes, viewpoint changes and occlusions. We pose this Tag-and-Track problem as a semi-supervised learning problem, in which we aim to label a large number of unlabeled data given very limited labeled data (user selection). We propose to use two trackers combined in a Bayesian co-training framework, which unifies the CONDENSATION algorithm and co-training seamlessly. By using co-training, our method avoids learning errors reinforce themselves. In this thesis, we present the application of our method in detection and tracking of multiple moving object in airborne videos. In this application, we combine our core tracking algorithm with a set of motion detection and tracking techniques, including motion stabilization, geo-registration, etc., and demonstrate the robustness and efficiency of our methods
590 $a School code: 0208.
650 4 $a Computer Science. $3 626642
690 $a 0984
710 2 $a University of Southern California. $b Computer Science. $3 1023331
773 0 $t Dissertation Abstracts International $g 70-05B.
790 $a 0208
790 1 0 $a Medioni, Gerard, $e advisor
790 1 0 $a Moore, James E. $e committee member
790 1 0 $a Nevatia, Ramakant $e committee member
791 $a Ph.D.
792 $a 2009
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3355319