東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Neural network approach to Bayesian ...

Culibrk, Dubravko.

FindBook

Google Book

Amazon

博客來

Neural network approach to Bayesian background modeling for video object segmentation.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Neural network approach to Bayesian background modeling for video object segmentation./
作者:	Culibrk, Dubravko.
面頁冊數:	121 p.
附註:	Source: Dissertation Abstracts International, Volume: 67-06, Section: B, page: 3219.
Contained By:	Dissertation Abstracts International67-06B.
標題:	Computer Science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3220670
ISBN:	9780542739422

Neural network approach to Bayesian background modeling for video object segmentation.
Culibrk, Dubravko.

Neural network approach to Bayesian background modeling for video object segmentation. - 121 p.

Source: Dissertation Abstracts International, Volume: 67-06, Section: B, page: 3219.

Thesis (Ph.D.)--Florida Atlantic University, 2006.

Object segmentation in a video sequence is an essential task in video processing and forms the foundation of content analysis, scene understanding, object-based video encoding (e.g. MPEG-4), various surveillance and 2D-to-pseudo-3D conversion applications. Popularization and availability of video sequences with increased spatial resolution requires development of new, more efficient algorithms for object detection and segmentation. This dissertation discusses a novel neural-network-based approach to background modeling for motion-based object segmentation in video sequences. In particular, we show how Probabilistic Neural Network (PNN) architecture can be extended to form an unsupervised Bayesian classifier for the domain of video object segmentation. The constructed Background Modeling Neural Network (BNN) is capable of efficiently handling segmentation in natural-scene sequences with complex background motion and changes in illumination. The weights of the proposed neural network serve as an exclusive model of the background and are temporally updated to reflect the observed background statistics. The proposed approach is designed to enable an efficient, highly-parallelized hardware implementation. Such a system would be able to achieve real-time segmentation of high-resolution image sequences.

ISBN: 9780542739422Subjects--Topical Terms:

626642
Computer Science.

Neural network approach to Bayesian background modeling for video object segmentation.
LDR:02244nmm 2200277 4500 001 1830483
005 20070430071701.5
008 130610s2006 eng d
020 $a 9780542739422
035 $a (UnM)AAI3220670
035 $a AAI3220670
040 $a UnM $c UnM
100 1 $a Culibrk, Dubravko. $3 1919311
245 1 0 $a Neural network approach to Bayesian background modeling for video object segmentation.
300 $a 121 p.
500 $a Source: Dissertation Abstracts International, Volume: 67-06, Section: B, page: 3219.
500 $a Advisers: Borko Furht; Oge Marques.
502 $a Thesis (Ph.D.)--Florida Atlantic University, 2006.
520 $a Object segmentation in a video sequence is an essential task in video processing and forms the foundation of content analysis, scene understanding, object-based video encoding (e.g. MPEG-4), various surveillance and 2D-to-pseudo-3D conversion applications. Popularization and availability of video sequences with increased spatial resolution requires development of new, more efficient algorithms for object detection and segmentation. This dissertation discusses a novel neural-network-based approach to background modeling for motion-based object segmentation in video sequences. In particular, we show how Probabilistic Neural Network (PNN) architecture can be extended to form an unsupervised Bayesian classifier for the domain of video object segmentation. The constructed Background Modeling Neural Network (BNN) is capable of efficiently handling segmentation in natural-scene sequences with complex background motion and changes in illumination. The weights of the proposed neural network serve as an exclusive model of the background and are temporally updated to reflect the observed background statistics. The proposed approach is designed to enable an efficient, highly-parallelized hardware implementation. Such a system would be able to achieve real-time segmentation of high-resolution image sequences.
590 $a School code: 0119.
650 4 $a Computer Science. $3 626642
690 $a 0984
710 2 0 $a Florida Atlantic University. $3 1017837
773 0 $t Dissertation Abstracts International $g 67-06B.
790 1 0 $a Furht, Borko, $e advisor
790 1 0 $a Marques, Oge, $e advisor
790 $a 0119
791 $a Ph.D.
792 $a 2006
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3220670