feature-based laser data simplification for low polygon visualization

15
Feature-based laser data simplification for low polygon visualization Pamela Fox, [email protected] Shirish Doshi, [email protected] Suya You, [email protected] Ulrich Neumann, [email protected] Integrated Media Systems Center University of Southern California

Upload: wuzziwug

Post on 14-Oct-2014

83 views

Category:

Documents


1 download

DESCRIPTION

Presented at AAG. Programming done in MEL.

TRANSCRIPT

Page 1: Feature-based laser data simplification for low polygon visualization

Feature-based laser data simplification for low polygon visualization

Pamela Fox, [email protected] Doshi, [email protected]

Suya You, [email protected] Neumann, [email protected]

Integrated Media Systems CenterUniversity of Southern California

Page 2: Feature-based laser data simplification for low polygon visualization

Overview

• Objective• Related Work• Our Approach

– Pre-processing: Polygon Reduction– Simplification into Primitives

• Results• Extension to outdoor/mixed scenes• Future Work• Conclusion

Page 3: Feature-based laser data simplification for low polygon visualization

Objective

• Simplified representation of scanned laser (range) data from indoor scenes

• Problems: Too many triangles, too many holes, not enough memory!

• Original application for RFID tracking

Page 4: Feature-based laser data simplification for low polygon visualization

Applications

• urban planning• virtual reality based geographics

information system (VRGIS)• environment monitoring• military missions• Video game mods

Page 5: Feature-based laser data simplification for low polygon visualization

Related Work – Polygon Reduction

• Tim Garthwaite, Jason Reposa. “Mesh Decimation.”

• Mathieu Desbruin. “Variational Shape Approximation.” University of Southern California

Page 6: Feature-based laser data simplification for low polygon visualization

Related Work – Indoor Scenes

• Rui Wang, David Luebke. “Efficient Reconstruction of Indoor Scenes with Color” Department of Computer Science, University of Virginia

• R.T. Whitaker, J. Gregor, P.F. Chen . “Indoor Scene Reconstruction from Sets of Noisy Range Images” University of Tennessee

Page 7: Feature-based laser data simplification for low polygon visualization

Related Work – Laser Data Simplification

• “Urban Site Modeling from LiDAR” – Suya You, Jinhui Hu, Ulrich Neumann, Pamela Fox

• Designed for buildings on land, laser data taken from aerial view, less dimensions

Page 8: Feature-based laser data simplification for low polygon visualization

Our Approach – 2 Steps

• Polygon Reduction for Corner/Edge (Feature) retention

• Further simplification of pre-processed scenes into geometric primitives based on indoor constraints and user-selected features

Page 9: Feature-based laser data simplification for low polygon visualization

1) Pre-processing: Polygon Reduction

• Standard Region Growing Algorithm

• Retain neighbors near corners & edges so we can use corner-finding algorithm in next step

planar area

non-planar area and neighbors

Page 10: Feature-based laser data simplification for low polygon visualization

2) Simplification into Primitives

• Indoor Constraints:• Standard components of indoor scene:

– floor, ceiling, walls• User firsts selects ground, ceiling, walls

– Least squares plane fitting algorithm, points

•When creating other objects in room, user can project to ground, ceiling, walls, or any pre-created object (e.g. a table)

•This means you often need only to select points on the frontal view of objects.

Page 11: Feature-based laser data simplification for low polygon visualization

2) Simplification into Primitives

• Primitive Creation:– User selects minimally necessary

points– Depends on type of primitive and

available data

• Corner locating:– If user can’t determine exact

corner, they can select a nearby corner and let program use K-means clustering algorithm to determine most likely corner

Page 12: Feature-based laser data simplification for low polygon visualization

Results

• 99.9% lossy “compression”– 520,000 to 1,200 triangles

• Texturing, lighting

Page 13: Feature-based laser data simplification for low polygon visualization

Extension to Outdoor/Mixed Scenes

• The user is not forced to tell the program a ground or ceiling or walls – so they can bypass those steps and simply use the primitive creation tools. So you can use the program to make simplified representations of any scenes that can be reduced to geometric primitives or customized preset objects.

• For example, if you’re reducing a scene with trees, there could be two preset tree primitives – evergreen, deciduous. Then when you see a tree in the laser data you’d select the height, the end of the greenery, radius, and project it to the ground.

Page 14: Feature-based laser data simplification for low polygon visualization

Future Work

• add on increased automation – like advanced primitive fitting where the user would have to select less points and the program would search the surrounding points to fit it.

• Other extensions could use intensity data as well to help with user or program segmentation – currently all triangles colored the same.

Page 15: Feature-based laser data simplification for low polygon visualization

Conclusion

• Fast loading and visualization• Semiautomated method• Built off existing graphics software