Language:
English
繁體中文
Help
回圖書館首頁
手機版館藏查詢
Login
Back
Switch To:
Labeled
|
MARC Mode
|
ISBD
Appearance methods of solving recogn...
~
Liu, Ping.
Linked to FindBook
Google Book
Amazon
博客來
Appearance methods of solving recognition and estimation problems in robotics .
Record Type:
Electronic resources : Monograph/item
Title/Author:
Appearance methods of solving recognition and estimation problems in robotics ./
Author:
Liu, Ping.
Description:
73 p.
Notes:
Source: Dissertation Abstracts International, Volume: 65-07, Section: B, page: 3682.
Contained By:
Dissertation Abstracts International65-07B.
Subject:
Engineering, System Science. -
Online resource:
http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3140693
ISBN:
0496878336
Appearance methods of solving recognition and estimation problems in robotics .
Liu, Ping.
Appearance methods of solving recognition and estimation problems in robotics .
- 73 p.
Source: Dissertation Abstracts International, Volume: 65-07, Section: B, page: 3682.
Thesis (D.Sc.)--Washington University, 2004.
This dissertation focuses on utilizing appearance methods to solve the recognition and estimation problems in robotics. As an intelligent robot scouts in an environment, it continuously captures images of various objects and scenes. Suppose the models of some objects and scenes are already encoded in the brain of the robot, then one fundamental task for the robot is to process this continuously absorbed visual information, recognize the observed objects and scenes. Geometrically, a continuous test curve is to be detected among perturbed model hypercurves or hypersurfaces after the KL decomposition is applied. Mathematically, the detection theory is used to solve this problem of detection in colored noises having nonidentical distributions. The result of scene recogntion is also extended to detect an intruder trepassing a modeled scene.
ISBN: 0496878336Subjects--Topical Terms:
1018128
Engineering, System Science.
Appearance methods of solving recognition and estimation problems in robotics .
LDR
:02090nmm 2200289 4500
001
1850670
005
20051207082640.5
008
130614s2004 eng d
020
$a
0496878336
035
$a
(UnM)AAI3140693
035
$a
AAI3140693
040
$a
UnM
$c
UnM
100
1
$a
Liu, Ping.
$3
1938587
245
1 0
$a
Appearance methods of solving recognition and estimation problems in robotics .
300
$a
73 p.
500
$a
Source: Dissertation Abstracts International, Volume: 65-07, Section: B, page: 3682.
500
$a
Director: Bijoy K. Ghosh.
502
$a
Thesis (D.Sc.)--Washington University, 2004.
520
$a
This dissertation focuses on utilizing appearance methods to solve the recognition and estimation problems in robotics. As an intelligent robot scouts in an environment, it continuously captures images of various objects and scenes. Suppose the models of some objects and scenes are already encoded in the brain of the robot, then one fundamental task for the robot is to process this continuously absorbed visual information, recognize the observed objects and scenes. Geometrically, a continuous test curve is to be detected among perturbed model hypercurves or hypersurfaces after the KL decomposition is applied. Mathematically, the detection theory is used to solve this problem of detection in colored noises having nonidentical distributions. The result of scene recogntion is also extended to detect an intruder trepassing a modeled scene.
520
$a
In addition, a new concept appearance flow is also described by revealing the relationship among the articulated motion dynamics, optical flow and appearance flow. As an example of using the derived appearance flow equation, an Extended Kalman Filter problem is formulated to estimate the joint angle parameters of a three-link planar arm.
590
$a
School code: 0252.
650
4
$a
Engineering, System Science.
$3
1018128
650
4
$a
Engineering, Mechanical.
$3
783786
690
$a
0790
690
$a
0548
710
2 0
$a
Washington University.
$3
1250147
773
0
$t
Dissertation Abstracts International
$g
65-07B.
790
1 0
$a
Ghosh, Bijoy K.,
$e
advisor
790
$a
0252
791
$a
D.Sc.
792
$a
2004
856
4 0
$u
http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3140693
based on 0 review(s)
Location:
ALL
電子資源
Year:
Volume Number:
Items
1 records • Pages 1 •
1
Inventory Number
Location Name
Item Class
Material type
Call number
Usage Class
Loan Status
No. of reservations
Opac note
Attachments
W9200184
電子資源
11.線上閱覽_V
電子書
EB
一般使用(Normal)
On shelf
0
1 records • Pages 1 •
1
Multimedia
Reviews
Add a review
and share your thoughts with other readers
Export
pickup library
Processing
...
Change password
Login