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

Efficient human pose estimation with...

Sapp, Benjamin John.

FindBook

Google Book

Amazon

博客來

Efficient human pose estimation with image-dependent interactions.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Efficient human pose estimation with image-dependent interactions./
作者:	Sapp, Benjamin John.
面頁冊數:	185 p.
附註:	Source: Dissertation Abstracts International, Volume: 74-06(E), Section: B.
Contained By:	Dissertation Abstracts International74-06B(E).
標題:	Applied Mathematics. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3551551
ISBN:	9781267894045

Efficient human pose estimation with image-dependent interactions.
Sapp, Benjamin John.

Efficient human pose estimation with image-dependent interactions. - 185 p.

Source: Dissertation Abstracts International, Volume: 74-06(E), Section: B.

Thesis (Ph.D.)--University of Pennsylvania, 2012.

Human pose estimation from 2D images is one of the most challenging and computationally-demanding problems in computer vision. Standard models such as Pictorial Structures consider interactions between kinematically connected joints or limbs, leading to inference cost that is quadratic in the number of pixels. As a result, researchers and practitioners have restricted themselves to simple models which only measure the quality of limb-pair possibilities by their 2D geometric plausibility.

ISBN: 9781267894045Subjects--Topical Terms:

1669109
Applied Mathematics.

Efficient human pose estimation with image-dependent interactions.
LDR:02790nam 2200361 4500 001 1957624
005 20140122121752.5
008 150210s2012 ||||||||||||||||| ||eng d
020 $a 9781267894045
035 $a (UMI)AAI3551551
035 $a AAI3551551
040 $a UMI $c UMI
100 1 $a Sapp, Benjamin John. $3 2092572
245 1 0 $a Efficient human pose estimation with image-dependent interactions.
300 $a 185 p.
500 $a Source: Dissertation Abstracts International, Volume: 74-06(E), Section: B.
500 $a Adviser: Ben Taskar.
502 $a Thesis (Ph.D.)--University of Pennsylvania, 2012.
520 $a Human pose estimation from 2D images is one of the most challenging and computationally-demanding problems in computer vision. Standard models such as Pictorial Structures consider interactions between kinematically connected joints or limbs, leading to inference cost that is quadratic in the number of pixels. As a result, researchers and practitioners have restricted themselves to simple models which only measure the quality of limb-pair possibilities by their 2D geometric plausibility.
520 $a In this talk, we propose novel methods which allow for efficient inference in richer models with data-dependent interactions. First, we introduce structured prediction cascades, a structured analog of binary cascaded classifiers, which learn to focus computational effort where it is needed, filtering out many states cheaply while ensuring the correct output is unfiltered. Second, we propose a way to decompose models of human pose with cyclic dependencies into a collection of tree models, and provide novel methods to impose model agreement. Finally, we develop a local linear approach that learns bases centered around modes in the training data, giving us image-dependent local models which are fast and accurate.
520 $a These techniques allow for sparse and efficient inference on the order of minutes or seconds per image. As a result, we can afford to model pairwise interaction potentials much more richly with data-dependent features such as contour continuity, segmentation alignment, color consistency, optical flow and multiple modes. We show empirically that these richer models are worthwhile, obtaining significantly more accurate pose estimation on popular datasets.
590 $a School code: 0175.
650 4 $a Applied Mathematics. $3 1669109
650 4 $a Statistics. $3 517247
650 4 $a Computer Science. $3 626642
690 $a 0364
690 $a 0463
690 $a 0984
710 2 $a University of Pennsylvania. $b Computer and Information Science. $3 2092564
773 0 $t Dissertation Abstracts International $g 74-06B(E).
790 1 0 $a Taskar, Ben, $e advisor
790 1 0 $a Daniilidis, Kostas $e committee member
790 1 0 $a Shi, Jianbo $e committee member
790 1 0 $a Taylor, Camillo J. $e committee member
790 1 0 $a Forsyth, David $e committee member
790 $a 0175
791 $a Ph.D.
792 $a 2012
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3551551