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

Learning models for multi-viewpoint ...

University of Illinois at Urbana-Champaign.

FindBook

Google Book

Amazon

博客來

Learning models for multi-viewpoint object detection.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Learning models for multi-viewpoint object detection./
作者:	Kushal Akash M.
面頁冊數:	135 p.
附註:	Adviser: Jean Ponce.
Contained By:	Dissertation Abstracts International69-11B.
標題:	Artificial Intelligence. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3337833
ISBN:	9780549909552

Learning models for multi-viewpoint object detection.
Kushal Akash M.

Learning models for multi-viewpoint object detection. - 135 p.

Adviser: Jean Ponce.

Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2008.

This dissertation addresses the task of detecting instances of object categories in photographs. We propose modeling an object category as a collection of object parts linked together in a deformable configuration. We propose two different approaches to model the appearance of object parts that provide robustness to intra-class variations and viewpoint change. The first approach models object parts as locally rigid assemblies of dense feature points and part detection proceeds by incrementally matching the feature points between the model image and the test image. The second approach employs a discriminative classifier (Support Vector Machine) based on a descriptor that consists of a combination of a sparse visual word histogram pyramid and a dense gradient and edge histogram pyramid.

ISBN: 9780549909552Subjects--Topical Terms:

769149
Artificial Intelligence.

Learning models for multi-viewpoint object detection.
LDR:02135nmm 2200301 a 45 001 891448
005 20101111
008 101111s2008 ||||||||||||||||| ||eng d
020 $a 9780549909552
035 $a (UMI)AAI3337833
035 $a AAI3337833
040 $a UMI $c UMI
100 1 $a Kushal Akash M. $3 1065445
245 1 0 $a Learning models for multi-viewpoint object detection.
300 $a 135 p.
500 $a Adviser: Jean Ponce.
500 $a Source: Dissertation Abstracts International, Volume: 69-11, Section: B, page: 6922.
502 $a Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2008.
520 $a This dissertation addresses the task of detecting instances of object categories in photographs. We propose modeling an object category as a collection of object parts linked together in a deformable configuration. We propose two different approaches to model the appearance of object parts that provide robustness to intra-class variations and viewpoint change. The first approach models object parts as locally rigid assemblies of dense feature points and part detection proceeds by incrementally matching the feature points between the model image and the test image. The second approach employs a discriminative classifier (Support Vector Machine) based on a descriptor that consists of a combination of a sparse visual word histogram pyramid and a dense gradient and edge histogram pyramid.
520 $a We also propose two different approaches for modeling the inter-part relations and algorithms for efficiently learning the model parameters. The first approach uses a generative model that models the joint probability distribution over the locations and visibility of all the object parts. The second approach employs a discriminative Conditional Random Field based model to encode the relative geometry and co-occurrence constraints.
590 $a School code: 0090.
650 4 $a Artificial Intelligence. $3 769149
650 4 $a Computer Science. $3 626642
650 4 $a Engineering, Robotics. $3 1018454
690 $a 0771
690 $a 0800
690 $a 0984
710 2 $a University of Illinois at Urbana-Champaign. $3 626646
773 0 $t Dissertation Abstracts International $g 69-11B.
790 $a 0090
790 1 0 $a Ponce, Jean, $e advisor
791 $a Ph.D.
792 $a 2008
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3337833