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

Saliency Cut: an Automatic Approach ...

Wang, Yilin.

Linked to FindBook

Google Book

Amazon

博客來

Saliency Cut: an Automatic Approach for Video Object Segmentation Based on Saliency Energy Minimization.

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Saliency Cut: an Automatic Approach for Video Object Segmentation Based on Saliency Energy Minimization./
Author:	Wang, Yilin.
Description:	73 p.
Notes:	Source: Masters Abstracts International, Volume: 52-02.
Contained By:	Masters Abstracts International52-02(E).
Subject:	Computer Science. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=1543721
ISBN:	9781303312878

Saliency Cut: an Automatic Approach for Video Object Segmentation Based on Saliency Energy Minimization.
Wang, Yilin.

Saliency Cut: an Automatic Approach for Video Object Segmentation Based on Saliency Energy Minimization. - 73 p.

Source: Masters Abstracts International, Volume: 52-02.

Thesis (M.S.)--Arizona State University, 2013.

Video object segmentation (VOS) is an important task in computer vision with a lot of applications, e.g., video editing, object tracking, and object based encoding. Different from image object segmentation, video object segmentation must consider both spatial and temporal coherence for the object. Despite extensive previous work, the problem is still challenging.

ISBN: 9781303312878Subjects--Topical Terms:

626642
Computer Science.

Saliency Cut: an Automatic Approach for Video Object Segmentation Based on Saliency Energy Minimization.
LDR:02908nam a2200277 4500 001 1966156
005 20141106122624.5
008 150210s2013 ||||||||||||||||| ||eng d
020 $a 9781303312878
035 $a (MiAaPQ)AAI1543721
035 $a AAI1543721
040 $a MiAaPQ $c MiAaPQ
100 1 $a Wang, Yilin. $3 2102952
245 1 0 $a Saliency Cut: an Automatic Approach for Video Object Segmentation Based on Saliency Energy Minimization.
300 $a 73 p.
500 $a Source: Masters Abstracts International, Volume: 52-02.
500 $a Adviser: Baoxin Li.
502 $a Thesis (M.S.)--Arizona State University, 2013.
520 $a Video object segmentation (VOS) is an important task in computer vision with a lot of applications, e.g., video editing, object tracking, and object based encoding. Different from image object segmentation, video object segmentation must consider both spatial and temporal coherence for the object. Despite extensive previous work, the problem is still challenging.
520 $a Usually, foreground object in the video draws more attention from humans, i.e. it is salient. In this thesis we tackle the problem from the aspect of saliency, where saliency means a certain subset of visual information selected by a visual system (human or machine). We present a novel unsupervised method for video object segmentation that considers both low level vision cues and high level motion cues. In our model, video object segmentation can be formulated as a unified energy minimization problem and solved in polynomial time by employing the min-cut algorithm. Specifically, our energy function comprises the unary term and pair-wise interaction energy term respectively, where unary term measures region saliency and interaction term smooths the mutual effects between object saliency and motion saliency. Object saliency is computed in spatial domain from each discrete frame using multi-scale context features, e.g., color histogram, gradient, and graph based manifold ranking. Meanwhile, motion saliency is calculated in temporal domain by extracting phase information of the video. In the experimental section of this thesis, our proposed method has been evaluated on several benchmark datasets. In MSRA 1000 dataset the result demonstrates that our spatial object saliency detection is superior to the state-of-art methods. Moreover, our temporal motion saliency detector can achieve better performance than existing motion detection approaches in UCF sports action analysis dataset and Weizmann dataset respectively. Finally, we show the attractive empirical result and quantitative evaluation of our approach on two benchmark video object segmentation datasets.
590 $a School code: 0010.
650 4 $a Computer Science. $3 626642
690 $a 0984
710 2 $a Arizona State University. $b Computer Science. $3 1676136
773 0 $t Masters Abstracts International $g 52-02(E).
790 $a 0010
791 $a M.S.
792 $a 2013
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=1543721