Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.
The effect of angles and distance on image-
based three-dimensional reconstructions
Siyuan Chen, Debra F. Laefer,
Universi...
Outline
• Background
• Methodology
• Problems
• Experiment Setting
• Result & Conclusion
1
Background – Road and Bridge Inspection
High Cost
Time consuming
Unsafe
Limited Data
Subjective
Image From:http: mntr...
Background - UAV-Based Inspection
Unmanned Aerial Vehicle (UAV)
3
Background – Image Acquisition
4
Methodology – Structure From Motion (SFM)
5
Images form: Prof. Rob Fergus, Computer science, NYU
Methodology – Structure From Motion (SFM)
6
Methodology – Structure From Motion (SFM)
7
Problem – Noise
8
Problem – Incomplete
9
Problem – Solution
Two Solutions:
• Better reconstruction algorithm
• Better data acquisition strategies
10
Experiment Setting - camera
Cannon IXUS 175
11
Experiment Setting - camera
12
Experiment Setting – Laser Scanner
Leica ScanStation P20
13
Result & Conclusion
Point cloud sets from different angles 14
Result & Conclusion
15
Result & Conclusion
16
Result & Conclusion
17
Siyuan.chen@ucd.ie
Thank you!
Upcoming SlideShare
Loading in …5
×

"The effect of angles and distance on image-based three-dimensional reconstructions" presented at ESREL2017 by Siyuan Chen

236 views

Published on

Abstract: This paper introduces a three-dimensional reconstruction experiment based on a physical laboratory-based experiment on a brick wall. Using controlled shooting distances and angles, different images sets were captured and processed with a structure from motion based technique, which can reconstruct 3D models based on multi-view, Two-Dimensional (2D) images. Those 2D geometries are shown to generate significant deformations within the resulting point cloud, especially where there were large angles (with respect the camera position and the wall’s normal direction) and at close distances to the wall’s surface. This paper demonstrates that by overlapping different flawed image sets, the deformation problem can be minimised.

Published in: Engineering
  • Be the first to comment

  • Be the first to like this

"The effect of angles and distance on image-based three-dimensional reconstructions" presented at ESREL2017 by Siyuan Chen

  1. 1. The effect of angles and distance on image- based three-dimensional reconstructions Siyuan Chen, Debra F. Laefer, University College Dublin ESREL 2017, June 18-22, 2017, Portorož, Slovenia This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No. 642453
  2. 2. Outline • Background • Methodology • Problems • Experiment Setting • Result & Conclusion 1
  3. 3. Background – Road and Bridge Inspection High Cost Time consuming Unsafe Limited Data Subjective Image From:http: mntransportationresearch.org/ Image From: http://blog.arthurdomagala.com/ 2
  4. 4. Background - UAV-Based Inspection Unmanned Aerial Vehicle (UAV) 3
  5. 5. Background – Image Acquisition 4
  6. 6. Methodology – Structure From Motion (SFM) 5
  7. 7. Images form: Prof. Rob Fergus, Computer science, NYU Methodology – Structure From Motion (SFM) 6
  8. 8. Methodology – Structure From Motion (SFM) 7
  9. 9. Problem – Noise 8
  10. 10. Problem – Incomplete 9
  11. 11. Problem – Solution Two Solutions: • Better reconstruction algorithm • Better data acquisition strategies 10
  12. 12. Experiment Setting - camera Cannon IXUS 175 11
  13. 13. Experiment Setting - camera 12
  14. 14. Experiment Setting – Laser Scanner Leica ScanStation P20 13
  15. 15. Result & Conclusion Point cloud sets from different angles 14
  16. 16. Result & Conclusion 15
  17. 17. Result & Conclusion 16
  18. 18. Result & Conclusion 17
  19. 19. Siyuan.chen@ucd.ie Thank you!

×