Incremental Dense Reconstruction from Sparse 3D Points with an - - PowerPoint PPT Presentation

Incremental Dense Reconstruction from Sparse 3D Points with an Integrated Level-of-Detail Concept

Jan Roters, Xiaoyi Jiang Department of Computer Science, University of Münster, Germany

Funded by the 2nd competition of the sponsoring competition Hightech.NRW

www.avigle.de

1

Outline

Motivation Incremental dense reconstruction approach Experiments and results Future work

2

Outline

Motivation Incremental dense reconstruction approach Experiments and results Future work

3

Why Incremental?

Traditional dense reconstruction Resources Computation time First result -> final result Further images

4

Project AVIGLE

Industrial research project Three universities and seven industry partners Development of a multifunctional aerial service platform One of the goals: creation of a virtual world with aerial photographs Swarm of Miniature Unmanned Aerial Vehicle (MUAV) Partly autonomous Creation MUAVs are still flying

5

Example Application

Video

6

Outline

Motivation Incremental dense reconstruction approach Experiments and results Future work

7

Traditional vs. New Approach

Traditional New Approach

8

New Approach

Handles wide-baseline images First results are processed quickly Reasonable incremental updates are delivered New images can be added to the computation process Integrates a level-of-detail concept by design

9

Incremental Dense Reconstruction

Sparse geometry, matches and cameras known 2-view reconstruction Other views used for verification 2D triangulation of feature point matches Midpoints have maximum distance to the triangle points

• > Increased visual entropy
• f those 2 images

10

Incremental Dense Reconstruction

Midpoint of the first image is matched to the second image FREAK descriptor (Alahi et. al., 2012) Guided matching using epipolar lines Limit boundary to triangle in second image

11

Triangle Filtering

Some triangles are unlikely to contain the correct match Classify the triangles using filter rules, e.g. size constraint Either reject those triangles

• r search on the whole

epipolar line Level-of-detail concept by bounding the triangle size

500 1000 1500 2000 2500 3000 3500 4000 500 1000 1500 2000 2500 3000 500 1000 1500 2000 2500 3000 3500 4000 500 1000 1500 2000 2500 3000 500 1000 1500 2000 2500 3000 3500 4000 500 1000 1500 2000 2500 3000 500 1000 1500 2000 2500 3000 3500 4000 500 1000 1500 2000 2500 3000

12

Outline

Motivation Incremental dense reconstruction approach Experiments and results Future work

13

Ground Truth Dataset

Evaluation with ground truth dataset The city of sights (Gruber et. al., 2010) 7 images (1920x1080) with additional depth image

14

1 2 3 4 5 6 7 8 9 10 1 2 3 4 5 6

reprojection error in pixels count of projections (%)

Accuracy

Accuracy measured as reprojection error Total mean accuracy about 1.5 pixels Total standard deviation about 1.49 pixels

15

Time Measurement

Decreasing computation time More triangles are rejected Images are at highest level-of-detail

1 2 3 4 5 6 7 8 9 10 0.5 1 1.5 2 2.5

number of iteration time per image (sec)

1 2 3 4 5 6 7 8 9 10 1 2 3 4 5 6 7 8

number of iteration computation time (sec)

all images “mean” images

16

Real World Scene

7 aerial images (4032 x 3024) Castle of Münster Sparse data obtained by VisualSFM (Changchang Wu)

17

Real World Scene

Video here Video

18

Further Processing Example

sparse data iteration 1 iteration 2 iteration 6

Mesh reconstruction

Vierjahn et al., sGNG: Surface Reconstruction Using Growing Neural Gas, Eurographics 2013, submitted

19

Outline

Motivation Incremental dense reconstruction approach Experiments and results Future work

20

Future Work

Close holes in the reconstruction Especially at the borders of

• bjects

Improve triangle filters Subpixel accuracy

21

Thank you for your attention!

Funded by the 2nd competition of the sponsoring competition Hightech.NRW

www.avigle.de

Questions?

22