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

Models for object detection, recogni...

Carnegie Mellon University.

Linked to FindBook

Google Book

Amazon

博客來

Models for object detection, recognition, and shape alignment.

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Models for object detection, recognition, and shape alignment./
Author:	Li, Yan.
Description:	165 p.
Notes:	Adviser: Takeo Kanade.
Contained By:	Dissertation Abstracts International70-01B.
Subject:	Computer Science. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3345276

Models for object detection, recognition, and shape alignment.
Li, Yan.

Models for object detection, recognition, and shape alignment. - 165 p.

Adviser: Takeo Kanade.

Thesis (Ph.D.)--Carnegie Mellon University, 2009.

The grand goal of computer vision is to provide a complete semantic interpretation of an input image by reasoning about the 3d scene that generated it. Object detection, recognition, and alignment are three fundamental vision tasks towards this goal. In this thesis, we develop a series of efficient algorithms to address these problems. The contributions are summarized as follows. (1) We present a two-step algorithm for specific object detection in cluttered background with a few example images and unknown camera poses. Instead of enforcing metric constraints on the local features, we utilize a set of ordering constraints which are powerful enough for the detection task. At the core of this algorithm is a qualitative feature matching scheme which includes an angular ordering constraint in local scale and a graph planarity constraint in global scale. (2) We present a part-based model for object categorization and part localization. The spatial interactions among parts are modeled by Factor Analysis which can be learned from the data. Constrained by the shape prior, part localization proceeds in the image space by using a triangulated Markov random field (TMRF) model. We propose an iterative shape estimation and regularization approach for efficient computation. (3) We propose a boosting procedure for simultaneous multi-view car detection . By combining the multi-class LogitBoost and AdaBoost detectors, we decompose the original problem to view classification and view-specific detection, which can be solved independently. We study various feature representations and weak learners for the boosting algorithms. Extensive experiments demonstrate improved accuracy and detection rate over the traditional algorithms. (4) We propose a Bayesian framework for robust shape alignment. Prior models assume Gaussian observation noise and attempt to fit a regularized shape using all the observed data, such an assumption is vulnerable to outrageous local features and occlusions. We address this problem by using a hypothesis-and-test approach. A Bayesian inference algorithm is developed to generate a large number of shape hypotheses from randomly sampled partial shapes. The hypotheses are then evaluated in the robust estimation framework to find the optimal one. Our model can effectively handle outliers and recover the underlying object shape. The proposed approach is evaluated on a very challenging dataset which spans a wide variety of car types, viewpoints, background scenes, and occlusion patterns.Subjects--Topical Terms:

626642
Computer Science.

Models for object detection, recognition, and shape alignment.
LDR:03339nam 2200253 a 45 001 861271
005 20100719
008 100719s2009 ||||||||||||||||| ||eng d
035 $a (UMI)AAI3345276
035 $a AAI3345276
040 $a UMI $c UMI
100 1 $a Li, Yan. $3 1028952
245 1 0 $a Models for object detection, recognition, and shape alignment.
300 $a 165 p.
500 $a Adviser: Takeo Kanade.
500 $a Source: Dissertation Abstracts International, Volume: 70-01, Section: B, page: 0408.
502 $a Thesis (Ph.D.)--Carnegie Mellon University, 2009.
520 $a The grand goal of computer vision is to provide a complete semantic interpretation of an input image by reasoning about the 3d scene that generated it. Object detection, recognition, and alignment are three fundamental vision tasks towards this goal. In this thesis, we develop a series of efficient algorithms to address these problems. The contributions are summarized as follows. (1) We present a two-step algorithm for specific object detection in cluttered background with a few example images and unknown camera poses. Instead of enforcing metric constraints on the local features, we utilize a set of ordering constraints which are powerful enough for the detection task. At the core of this algorithm is a qualitative feature matching scheme which includes an angular ordering constraint in local scale and a graph planarity constraint in global scale. (2) We present a part-based model for object categorization and part localization. The spatial interactions among parts are modeled by Factor Analysis which can be learned from the data. Constrained by the shape prior, part localization proceeds in the image space by using a triangulated Markov random field (TMRF) model. We propose an iterative shape estimation and regularization approach for efficient computation. (3) We propose a boosting procedure for simultaneous multi-view car detection . By combining the multi-class LogitBoost and AdaBoost detectors, we decompose the original problem to view classification and view-specific detection, which can be solved independently. We study various feature representations and weak learners for the boosting algorithms. Extensive experiments demonstrate improved accuracy and detection rate over the traditional algorithms. (4) We propose a Bayesian framework for robust shape alignment. Prior models assume Gaussian observation noise and attempt to fit a regularized shape using all the observed data, such an assumption is vulnerable to outrageous local features and occlusions. We address this problem by using a hypothesis-and-test approach. A Bayesian inference algorithm is developed to generate a large number of shape hypotheses from randomly sampled partial shapes. The hypotheses are then evaluated in the robust estimation framework to find the optimal one. Our model can effectively handle outliers and recover the underlying object shape. The proposed approach is evaluated on a very challenging dataset which spans a wide variety of car types, viewpoints, background scenes, and occlusion patterns.
590 $a School code: 0041.
650 4 $a Computer Science. $3 626642
690 $a 0984
710 2 $a Carnegie Mellon University. $3 1018096
773 0 $t Dissertation Abstracts International $g 70-01B.
790 $a 0041
790 1 0 $a Kanade, Takeo, $e advisor
791 $a Ph.D.
792 $a 2009
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3345276