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

A probabilistic approach to human mo...

Song, Yang.

FindBook

Google Book

Amazon

博客來

A probabilistic approach to human motion detection and labeling.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	A probabilistic approach to human motion detection and labeling./
作者:	Song, Yang.
面頁冊數:	121 p.
附註:	Source: Dissertation Abstracts International, Volume: 64-02, Section: B, page: 0817.
Contained By:	Dissertation Abstracts International64-02B.
標題:	Computer Science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3081252

A probabilistic approach to human motion detection and labeling.
Song, Yang.

A probabilistic approach to human motion detection and labeling. - 121 p.

Source: Dissertation Abstracts International, Volume: 64-02, Section: B, page: 0817.

Thesis (Ph.D.)--California Institute of Technology, 2003.

Human motion analysis is a very important task for computer vision with many potential applications. There are several problems in human motion analysis: detection, tracking, and activity interpretation. Detection is the most fundamental problem of the three, but remains untackled due to its inherent difficulty. This thesis develops a solution to the problem. It is based on a learned probabilistic model of the joint positions and velocities of the body parts, where detection and labeling are performed by hypothesis testing on the maximum a posterior estimate of the pose and motion of the body. To achieve efficiency in learning and testing, a graphical model is used to approximate the conditional independence of human motion. This model is also shown to provide a natural way to deal with clutter and occlusion.Subjects--Topical Terms:

626642
Computer Science.

A probabilistic approach to human motion detection and labeling.
LDR:02987nmm 2200289 4500 001 1854509
005 20040615083617.5
008 130614s2003 eng d
035 $a (UnM)AAI3081252
035 $a AAI3081252
040 $a UnM $c UnM
100 1 $a Song, Yang. $3 1265217
245 1 0 $a A probabilistic approach to human motion detection and labeling.
300 $a 121 p.
500 $a Source: Dissertation Abstracts International, Volume: 64-02, Section: B, page: 0817.
500 $a Adviser: Pietro Perona.
502 $a Thesis (Ph.D.)--California Institute of Technology, 2003.
520 $a Human motion analysis is a very important task for computer vision with many potential applications. There are several problems in human motion analysis: detection, tracking, and activity interpretation. Detection is the most fundamental problem of the three, but remains untackled due to its inherent difficulty. This thesis develops a solution to the problem. It is based on a learned probabilistic model of the joint positions and velocities of the body parts, where detection and labeling are performed by hypothesis testing on the maximum a posterior estimate of the pose and motion of the body. To achieve efficiency in learning and testing, a graphical model is used to approximate the conditional independence of human motion. This model is also shown to provide a natural way to deal with clutter and occlusion.
520 $a One key factor in the proposed method is the probabilistic model of human motion. In this thesis, an unsupervised learning algorithm that can obtain the probabilistic model automatically from unlabeled training data is presented. The training data include useful foreground features as well as features that arise from irrelevant background clutter. The correspondence between parts and detected features is also unknown in the training data. To learn the best model structure as well as model parameters, a variant of the EM algorithm is developed where the labeling of the data (part assignments) is treated as hidden variables. We explore two classes of graphical models: trees and decomposable triangulated graphs and find that the later are superior for our application. To better model human motion, we also consider the case when the model consists of mixtures of decomposable triangulated graphs.
520 $a The efficiency and effectiveness of the algorithm have been demonstrated by applying it to generate models of human motion automatically from unlabeled image sequences, and testing the learned models on a variety of sequences. We find detection rates of over 95% on pairs of frames. This is very promising for building a real-life system, for example, a pedestrian detector.
590 $a School code: 0037.
650 4 $a Computer Science. $3 626642
650 4 $a Engineering, Electronics and Electrical. $3 626636
690 $a 0984
690 $a 0544
710 2 0 $a California Institute of Technology. $3 726902
773 0 $t Dissertation Abstracts International $g 64-02B.
790 1 0 $a Perona, Pietro, $e advisor
790 $a 0037
791 $a Ph.D.
792 $a 2003
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3081252