國立虎尾科技大學 |

Vision-based map-to-image correspondence for attitude estimation in augmented reality applications.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Vision-based map-to-image correspondence for attitude estimation in augmented reality applications./
Author:	Proffitt, Richard Patrick.
Description:	1 online resource (119 pages)
Notes:	Source: Dissertation Abstracts International, Volume: 78-01(E), Section: B.
Contained By:	Dissertation Abstracts International78-01B(E).
Subject:	Mechanical engineering. -
Online resource:	click for full text (PQDT)
ISBN:	9781369096781

Vision-based map-to-image correspondence for attitude estimation in augmented reality applications.
Proffitt, Richard Patrick.

Vision-based map-to-image correspondence for attitude estimation in augmented reality applications. - 1 online resource (119 pages)

Source: Dissertation Abstracts International, Volume: 78-01(E), Section: B.

Thesis (Ph.D.)

Includes bibliographical references

This dissertation proposes a methodology for attitude correction by matching two different representations of the same environment. This is accomplished by match- ing features extracted from an image of the driving environment (measurement) to a pre-defined expectation of how the environment should look (map). A mobile mapping system (MMS) is developed as a platform for collecting the data necessary to conduct these tests. Using sample images, features are investigated for proper- ties that generalize easily between the virtual and physical worlds. This problem is formulated specifically for cases in which mountains are visible, allowing for the use of the horizon contour as a low-dimensional waveform in which to search for features. Once processes for achieving alignment using feature-based methods are developed, they are applied to data-sets consisting of images taken while the MSS moves through an environment. System performance is enhanced by the use of Kalman filtering to predict the dynamic motion of the system and mathematically account for it in estimation of attitude. The system developed in this dissertation is proven to work for orientation correction on a vehicle traveling approximately 35 mph in a rural environment.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9781369096781Subjects--Topical Terms:

557493
Mechanical engineering.
Index Terms--Genre/Form:

554714
Electronic books.

Vision-based map-to-image correspondence for attitude estimation in augmented reality applications.
LDR:02547ntm a2200349Ki 4500 001 909459
005 20180426100011.5
006 m o u
007 cr mn||||a|a||
008 190606s2016 xx obm 000 0 eng d
020 $a 9781369096781
035 $a (MiAaPQ)AAI10154585
035 $a AAI10154585
040 $a MiAaPQ $b eng $c MiAaPQ
099 $a TUL $f hyy $c available through World Wide Web
100 1 $a Proffitt, Richard Patrick. $3 1180256
245 1 0 $a Vision-based map-to-image correspondence for attitude estimation in augmented reality applications.
264 0 $c 2016
300 $a 1 online resource (119 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertation Abstracts International, Volume: 78-01(E), Section: B.
500 $a Adviser: Sean Brennan.
502 $a Thesis (Ph.D.) $c The Pennsylvania State University $d 2016.
504 $a Includes bibliographical references
520 $a This dissertation proposes a methodology for attitude correction by matching two different representations of the same environment. This is accomplished by match- ing features extracted from an image of the driving environment (measurement) to a pre-defined expectation of how the environment should look (map). A mobile mapping system (MMS) is developed as a platform for collecting the data necessary to conduct these tests. Using sample images, features are investigated for proper- ties that generalize easily between the virtual and physical worlds. This problem is formulated specifically for cases in which mountains are visible, allowing for the use of the horizon contour as a low-dimensional waveform in which to search for features. Once processes for achieving alignment using feature-based methods are developed, they are applied to data-sets consisting of images taken while the MSS moves through an environment. System performance is enhanced by the use of Kalman filtering to predict the dynamic motion of the system and mathematically account for it in estimation of attitude. The system developed in this dissertation is proven to work for orientation correction on a vehicle traveling approximately 35 mph in a rural environment.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Mechanical engineering. $3 557493
650 4 $a Robotics. $3 561941
650 4 $a Electrical engineering. $3 596380
655 7 $a Electronic books. $2 local $3 554714
690 $a 0548
690 $a 0771
690 $a 0544
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a The Pennsylvania State University. $3 845556
773 0 $t Dissertation Abstracts International $g 78-01B(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10154585 $z click for full text (PQDT)