1. Sukhum Sattaratnamai Advisor: Dr.Nattee Niparnan
Improving and Filtering Laser Data for Extrinsic Laser Range Finder/Camera Calibration
Sukhum Sattaratnamai
Advisor: Dr.Nattee Niparnan

2. Outline Introduction Related work Our Problem Scope & Work plan
LRF-Camera System, Applications
Related work
LRF-Camera Calibration Method
Our Problem
Challenge, Propose method
Scope & Work plan

3. Nice Point Cloud

4. Point Cloud Data
Hard to classify the objects without color information

5. Color Information
Give rich information about the environment

6. Laser Range Finder
Give depth data of scan plane, and can be used to generate 3D point cloud

7. Camera
Camera Model

8. LRF-Camera System

9. LRF-Camera System

10. LRF-Camera Calibration
Problem Definition [Ganhua Li, 2007]
Find the transformation [R |t ] of the camera w.r.t. LRF

11. Applications
Transportation
Surveillance
Tourism
Robotics

12. Precision?
“Stanley: The Robot that Won the DARPA Grand Challenge”

13. Precision?
Accident

14. Objective Calibration method can give most accurate result
laser data post-processing method

15. Related work
Projection Error (2D)
Point to Plane Distance (3D)

16. Related work (2D)
Wasielewski, S.; Strauss, O.;, "Calibration of a multi-sensor system laser rangefinder/camera," Intelligent Vehicles '95 Symposium., 1995

17. Related work (2D)
Mei, C.; Rives, P.;, "Calibration between a central catadioptric camera and a laser range finder for robotic applications," ICRA 2006

18. Related work (2D)
Ganhua Li; Yunhui Liu; Li Dong; Xuanping Cai; Dongxiang Zhou;, "An algorithm for extrinsic parameters calibration of a camera and a laser range finder using line features," IROS 2007

19. Related work (3D)
Qilong Zhang; Pless, R.;, "Extrinsic calibration of a camera and laser range finder (improves camera calibration)," IROS 2004

20. Related work (3D)
Dupont, R.; Keriven, R.; Fuchs, P.;, "An improved calibration technique for coupled single-row telemeter and CCD camera," 3DIM 2005

21. Comparison
2004 vs 2007

22. Our Problem
Propose an autonomous data improving and filtering method which lead to more accurate calibration result

23. LRF-Camera System
Laser Range Finder
Camera

24. Challenge Sensor Model [Kneip, L.; 2009]
Laser range finder sampling an environment discretely
Laser data are noisy : Mixed pixel

25. Challenge Laser beams are invisible Autonomous process
Point-Line constrains
No ground truth available
Autonomous process
Autonomously improve and filter the data

26. Proposed method
Data improvement : Reduce angular error

27. Proposed method Data filtering: Remove outlier
In case of mixed pixel: may select neighbor point instead
In case of moving calibration object: remove data pairs

28. Scope of the research
Propose an autonomous laser data improving and filtering method for extrinsic LRF/camera calibration
Laser range finder and camera can be placed at arbitrarily position as long as they have a common detection area
An environment is suitable for laser range finder and camera so that they can detect the calibration object

29. Work Plan Study the works in the related fields
Develop data improvement method
Develop data filtering method
Test the proposed method
Prepare and engage in a thesis defense

30. Thank you

31. Bundle adjustment
Conceived in the field of photogrammetry during 1950s and increasingly been used by computer vision researchers during recent years
Mature bundle algorithms are comparatively efficient even on very large problems
Bundle adjustment boils down to minimizing the re-projection error between the image locations of observed and predicted image points
Visual reconstruction attempts to recover a model of a 3D scene from multiple images and also recovers the poses of the cameras that took the images