Optical Flow Vectors Thresholding in Assisting Heading Direction Estimation

Abstract:

This paper presents a technique on how to estimate heading direction of a moving vision system such as mobile robot. The heading direction is represented by estimation angle which is generated by optical flow vectors threshold technique (OFVTT). The utilizations of optical flow field generated based on Horn-Schunck and Lucas-Kanade methods are essential in order to compute the threshold value. The performance of the proposed technique was determined through percentage of root mean square error (RMSE). Based on our experimental results, it can be ascertained that combination of Horn-Schunck method together with OFVTT shows the best performance in assisting the heading direction estimation of a moving vision system.

• Periodical: Applied Mechanics and Materials (Volume 393)
• Pages: 623-628
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.393.623
• Online since: September 2013
• Authors: Zairulazha Zainal, Rizauddin Ramli, Mohd Marzuki Mustafa
• Keywords: Angle Threshold, Heading Direction, Magnitude Threshold, Optical Flow

References

[1] M. Tomizuka, Mechatronics: from the 20th to 21st century, Control Engineering Practice 10 (2002) 877–886.

DOI: 10.1016/s0967-0661(02)00016-3

[2] D. Bradley, Mechatronics – More questions than answers, Mechatronics 20 (2010) 827–841.

DOI: 10.1016/j.mechatronics.2010.07.011

[3] V. Giurgiutiu, A. E. Bayoumi, and G. Nall, Mechatronics and smart structures : emerging engineering disciplines for the third millennium, Mechatronics 12 (2002) 169–181.

DOI: 10.1016/s0957-4158(01)00057-5

[4] J. Hewit, Autonomous mechatronics design - the key to performance enhancement, Robotics and Autonomous Systems 19 (1996) 135–142.

DOI: 10.1016/s0921-8890(96)00041-3

[5] A. Ollero, S. Boverie, R. Goodall, J. Sasiadek, H. Erbe, and D. Zuehlke, Mechatronics, robotics and components for automation and control, Annual Reviews in Control 30 (2006) 41–54.

DOI: 10.1016/j.arcontrol.2006.02.002

[6] S. B. Niku, Introduction to Robotics Analysis, Systems, Applications, New Jersey, USA: Prentice Hall Inc, (2001).

[7] K. H. Ghazali, M. M. Mustafa, and A. Hussain, Machine vision system for automatic weeding strategy using image processing technique, American-Eurasian Journal of Agricultural & Environmental Sciences 3 (2008) 451–458.

[8] N. Nourani-vatani, J. Roberts, and M. V Srinivasan, Practical visual odometry for car-like vehicles, IEEE International Conference on Robotics and Automation 2009 (ICRA '09) (2009) 3551 – 3557.

DOI: 10.1109/robot.2009.5152403

[9] A. Pretto, E. Menegatti, M. Bennewitz, W. Burgard, and E. Pagello, A visual odometry framework robust to motion blur, IEEE International Conference on Robotics and Automation 2009 (ICRA '09) (2009) 2250 – 2257.

DOI: 10.1109/robot.2009.5152447

[10] K. Konolige, M. Agrawal, and J. Solà, Large scale visual odometry for rough terrain, Springer Tracts in Advanced Robotics 66 (2011) 201–212.

DOI: 10.1007/978-3-642-14743-2_18

[11] D. Hyun, H. Seok, H. Ri, and H. Park, Differential optical navigation sensor for mobile robots, Sensors and Actuators A: Physical 156 (2009) 296–301.

DOI: 10.1016/j.sna.2009.10.007

[12] A. M. Tekalp, Digital Video Processing, Prentice Hall Inc, (1995).