A comparison of different computer vision methods for real time 3D reconstruction for the use in mobile robots

ABSTRACT

In this paper a general algorithm for a computer vision unit for supporting a Micro Unmanned Aerial Vehicle's autonomous flight through an unknown environment is presented. It is shown that the data generated from an image sequence taken by a single camera can be used as a supplementary measurement for an inertial measurement unit.

This work also includes an examination of two different techniques of generating point correspondences in a recorded image sequence. A combination of Harris Corner Detection and Normalized Cross Correlation is compared with Optical Flow in respect to run time and accuracy properties. An assessment for real time applications is given afterwards.

REFERENCES

• 1: Hans Peter Moravec, Obstacle avoidance and navigation in the real world by a seeing robot rover, Stanford University, Stanford, CA, 1980
• 2: Harris, C., and Stephens, M., A combined corner and edge detection. In Proceedings of The Fourth Alvey Vision Conference, pages 147--151, 1988.
• 3: Lucas, B. D., and Kanade, T., An iterative image registration technique with an application to stereo vision. Proceedings of Imaging understanding workshop, pp 121--130, 1981.
• 4: Briechle, K. and Hanebeck, U. D., Template Matching Using Fast Normalized Cross Correlation, Proceedings of SPIE Vol. 4387, AeroSense Symposium, Orlando, Florida, 2001
• 5: Stavens, D., The OpenCV Library: Computing Optical Flow, Stanford Artificial Intelligence Lab, CS223b, 2005
• 6: Richard Hartley , Andrew Zisserman, Multiple view geometry in computer visiond, Cambridge University Press, New York, NY, 2001
• 7: Schlaile, C., Meister O., Wendel J., Trommer G. F., Vision Based Navigation of a Four Rotor Helicopter in Unprepared Indoor Environment, European Micro Air Vehicle Conference and Flight Competition 2006, 25 --26. 07.2006, Braunschweig
• 8: Philip H. S. Torr , Andrew W. Fitzgibbon , Andrew Zisserman, The Problem of Degeneracy in Structure and Motion Recovery from Uncalibrated Image Sequences, International Journal of Computer Vision, v.32 n.1, p.27-44, Aug. 1. 1999 [doi>10.1023/A:1008140928553]
• 9: Horn, B. K. P., Recovering Baseline and Orientation from 'Essential' Matrix; http://www.ai.mit.edu/people/bkph/papers/essential.pdf, 1990.
• 10: Lourakis M. I. A., Argyros A. A., The Design and Implementation of a Generic Sparse Bundle Adjustment Software Package Based on the Levenberg-Marquardt Algorithm, 2004.
• 11: S. S. Beauchemin , J. L. Barron, The computation of optical flow, ACM Computing Surveys (CSUR), v.27 n.3, p.433-466, Sept. 1995 [doi>10.1145/212094.212141]

INDEX TERMS

General Terms:
Algorithms, Performance

Keywords:
computer vision, mobile computing, real time requirements, unmanned flying vehicles