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

Visual object tracking and segmentation.

Dong, Lan.

Linked to FindBook

Google Book

Amazon

博客來

Visual object tracking and segmentation.

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Visual object tracking and segmentation./
Author:	Dong, Lan.
Description:	174 p.
Notes:	Source: Dissertation Abstracts International, Volume: 68-09, Section: B, page: 6176.
Contained By:	Dissertation Abstracts International68-09B.
Subject:	Engineering, Electronics and Electrical. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3281301
ISBN:	9780549229575

Visual object tracking and segmentation.
Dong, Lan.

Visual object tracking and segmentation. - 174 p.

Source: Dissertation Abstracts International, Volume: 68-09, Section: B, page: 6176.

Thesis (Ph.D.)--Princeton University, 2007.

Computer vision is concerned with obtaining visual information about the world by computer, and is an important scientific discipline in digital technology. Within this general area, visual surveillance is one of the most active research topics. This thesis presents new algorithms for object tracking and segmentation problems, which constitute the majority of visual surveillance tasks.

ISBN: 9780549229575Subjects--Topical Terms:

626636
Engineering, Electronics and Electrical.

Visual object tracking and segmentation.
LDR:02875nam 2200265 a 45 001 948618
005 20110524
008 110524s2007 ||||||||||||||||| ||eng d
020 $a 9780549229575
035 $a (UMI)AAI3281301
035 $a AAI3281301
040 $a UMI $c UMI
100 1 $a Dong, Lan. $3 1243037
245 1 0 $a Visual object tracking and segmentation.
300 $a 174 p.
500 $a Source: Dissertation Abstracts International, Volume: 68-09, Section: B, page: 6176.
502 $a Thesis (Ph.D.)--Princeton University, 2007.
520 $a Computer vision is concerned with obtaining visual information about the world by computer, and is an important scientific discipline in digital technology. Within this general area, visual surveillance is one of the most active research topics. This thesis presents new algorithms for object tracking and segmentation problems, which constitute the majority of visual surveillance tasks.
520 $a We discuss a number of different object tracking algorithms. We first propose a fast tracking algorithm by efficient estimation of the probability distribution of the object states given the measurements. The central idea is to generate a candidate set which is guaranteed with high probability to contain the true state of the object we want to track. We do this by first segmenting the image space through the use of color histograms. We show that our method reduces the computational load while achieving the same optimal solution as particle filters. We then discuss tracking algorithms in compressed video. We use Motion Vectors (MV) and DCT coefficients available in MPEG-2 video for robust tracking. The robustness lies in two aspects: we try to accurately estimate the motion field by MV together with residual, spatial and textural confidence measures; we develop a mechanism to automatically detect object change and use DCT-based I frame tracking to relocate the object.
520 $a In the last part of this thesis, we discuss the crowd segmentation problem which is a preliminary step for object tracking. The goal of crowd segmentation is to estimate the number of humans and their positions from background differencing images obtained from a single camera. In contrast to complex model-based algorithms, we formulate the segmentation as an example-based problem. We build up mappings between various configurations of humans with their projected features and use locally weighted regression to interpolate the configuration of the input from best matches. We also combine our method with the popular "Markov Chain Monte Carlo" (MCMC) search and show that we can achieve improvement over MCMC search performed alone.
590 $a School code: 0181.
650 4 $a Engineering, Electronics and Electrical. $3 626636
690 $a 0544
710 2 $a Princeton University. $3 645579
773 0 $t Dissertation Abstracts International $g 68-09B.
790 $a 0181
791 $a Ph.D.
792 $a 2007
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3281301