Tools

LEADER 03288cam a2200541Ii 4500

001 ocn957491633;

003 OCoLC;

005 20161027015235.0;

006 m o d ;

007 cr unu||||||||;

008 160829s2016 ncua obm 000 0 eng d;

035 a| (Sirsi) o957491633;

035 a| (OCoLC)957491633;

049 a| EREE;

090 a| TA1634;

100 1 a| Dellana, Ryan,e| author.?| UNAUTHORIZED;

245 10 a| Back-projective priming :b| toward efficient 3d model-based object recognition via preemptive top-down constraints /c| by Ryan Dellana.;

246 3 a| Back-projective priming toward efficient 3d model-based object recognition via preemptive top-down constraints.;

264 1 a| [Greenville, N.C.] :b| [East Carolina University],c| 2016.;

300 a| 55 pages :b| illustrations (some color);

336 a| textb| txt2| rdacontent;

337 a| computerb| c2| rdamedia;

338 a| online resourceb| cr2| rdacarrier;

347 a| text fileb| PDFc| 2.88 MB2| rda;

538 a| System requirements: Adobe Reader.;

538 a| Mode of access: World Wide Web.;

502 b| M.S.c| East Carolina Universityd| 2016.;

500 a| Presented to the faculty of the Department of Computer Science.;

500 a| Advisor: Ronnie W. Smith.;

500 a| Title from PDF t.p. (viewed September 27, 2016).;

520 3 a| This thesis introduces back-projective priming, a computer vision technique that synergistically fuses object recognition and pose estimation by augmenting 3D models with geometric constraints. It also enables the use of image features too indistinct for use by other model fitting algorithms such as geometric hashing. To efficiently accommodate features that do not provide a scale attribute, we've developed a "match pair" finding heuristic called second-order similarity that reduces model fitting time complexity from a worst case of O(N^2) to O(N*Log(N)). An object recognition problem that is simple, practical, and well explored by other researchers is the problem of locating electrical outlets from the vantage point of a mobile robot. To demonstrate the relative merits of back-projective priming, we use it to build a system capable of locating generic electrical outlets in unmapped environments. Compared to our baseline algorithm, back-projective priming is shown to provide superior sensitivity when dealing with the challenges of low contrast, perspective distortion, partial occlusion, and decoys.;

504 a| Includes bibliographical references.;

650 0 a| Computer vision.=| ^A162076;

650 0 a| Three-dimensional modeling.=| ^A1318460;

653 a| Object Recognition;

653 a| Pose Estimation;

653 a| Perception;

653 a| Robotics;

700 1 a| Smith, Ronnie W.,e| degree supervisor.=| ^A360584;

710 2 a| East Carolina University.b| Department of Computer Science.?| UNAUTHORIZED;

856 40 z| Access via ScholarShipu| http://hdl.handle.net/10342/5940;

949 o| wjh;

994 a| C0b| ERE;

596 a| 1 4;

998 a| 4511356;

999 a| CLICK ON WEB ADDRESSw| ASISc| 1i| 4511356-1001l| JNETm| JOYNERr| Ys| Yt| JNE3ETDu| 8/29/2016x| ETDz| JERESOURCE;

999 a| CLICK ON WEB ADDRESSw| ASISc| 1i| 4511356-2001l| HSLELECm| HSLr| Ys| Yt| HEETDu| 8/29/2016x| ETDz| HERESOURCE;

Back-projective priming : toward efficient 3d model-based object recognition via preemptive top-down constraints / by Ryan Dellana.

Author/creator	Dellana, Ryan author.
Other author	Smith, Ronnie W., degree supervisor.
Other author	East Carolina University. Department of Computer Science.
Format	Theses and dissertations
Publication	[Greenville, N.C.] : [East Carolina University], 2016.
Description	55 pages : illustrations (some color)
Supplemental Content	Access via ScholarShip
Subjects	Computer vision. Three-dimensional modeling.

Variant title	Back-projective priming toward efficient 3d model-based object recognition via preemptive top-down constraints.
Summary	This thesis introduces back-projective priming, a computer vision technique that synergistically fuses object recognition and pose estimation by augmenting 3D models with geometric constraints. It also enables the use of image features too indistinct for use by other model fitting algorithms such as geometric hashing. To efficiently accommodate features that do not provide a scale attribute, we've developed a "match pair" finding heuristic called second-order similarity that reduces model fitting time complexity from a worst case of O(N^2) to O(N*Log(N)). An object recognition problem that is simple, practical, and well explored by other researchers is the problem of locating electrical outlets from the vantage point of a mobile robot. To demonstrate the relative merits of back-projective priming, we use it to build a system capable of locating generic electrical outlets in unmapped environments. Compared to our baseline algorithm, back-projective priming is shown to provide superior sensitivity when dealing with the challenges of low contrast, perspective distortion, partial occlusion, and decoys.
General note	Presented to the faculty of the Department of Computer Science.
General note	Advisor: Ronnie W. Smith.
General note	Title from PDF t.p. (viewed September 27, 2016).
Dissertation note	M.S. East Carolina University 2016.
Bibliography note	Includes bibliographical references.
Technical details	System requirements: Adobe Reader.
Technical details	Mode of access: World Wide Web.

Back-projective priming : toward efficient 3d model-based object recognition via preemptive top-down constraints / by Ryan Dellana.

Click here for more information about this title