Directional Filter and the Viterbi Algorithm for Line Following Robots

The line estimation algorithm dedicated to line following robots is proposed in this paper. The line estimation is based on the Viterbi algorithm and directional filtering using moving average filter. Two cases of system are compared using Monte Carlo approach – with proposed directional filter and without this filter. The performance is measured using comparison of cumulative errors for horizontal direction. The results shows 20% improvements for Gaussian noise standard deviation 0.3 − 0.9 range, for proposed solution in comparison to the Viterbi algorithm alone approach.

[1]  Lawrence D. Stone,et al.  Bayesian Multiple Target Tracking , 1999 .

[2]  Albert-Jan Baerveldt,et al.  A vision based row-following system for agricultural field machinery , 2005 .

[3]  Saeid Nahavandi,et al.  OzTug mobile robot for manufacturing transportation , 2011, 2011 IEEE International Conference on Systems, Man, and Cybernetics.

[4]  Jacek M. Zurada,et al.  Artificial Intelligence and Soft Computing, 10th International Conference, ICAISC 2010, Zakopane, Poland, June 13-17, 2010, Part I , 2010, International Conference on Artificial Intelligence and Soft Computing.

[5]  Scott T. Acton,et al.  Biomedical Image Analysis: Tracking , 2006, Biomedical Image Analysis: Tracking.

[6]  Ryszard S. Choras.  Image Processing and Communications Challenges 5 - 5th International Conference, IP&C 2013, Bydgoszcz, Poland, September 2013, Proceedings , 2014, IP&C.

[7]  K. M. Hasan,et al.  Implementation of autonomous line follower robot , 2012, 2012 International Conference on Informatics, Electronics & Vision (ICIEV).

[8]  Jiann-Shiou Yang,et al.  A lane departure warning system based on the integration of the optical flow and hough transform methods , 2013, 2013 10th IEEE International Conference on Control and Automation (ICCA).

[9]  P. Mazurek.  Optimization of Bayesian Track-Before-Detect algorithms for GPGPUs Implementations , 2010 .

[10]  Przemyslaw Mazurek.  Hierarchical Track-Before-Detect Algorithm for Tracking of Amplitude Modulated Signals , 2011, IP&C.

[11]  Krzysztof Okarma,et al.  A Fast Image Analysis Technique for the Line Tracking Robots , 2010, ICAISC.

[12]  Przemyslaw Mazurek.  Preprocessing Using Maximal Autocovariance for Spatio-Temporal Track-Before-Detect Algorithm , 2013, IP&C.

[13]  Samuel S. Blackman,et al.  Design and Analysis of Modern Tracking Systems , 1999 .

[14]  Ji Zhang,et al.  3D perception for accurate row following: Methodology and results , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[15]  Andrew J. Viterbi,et al.  Error bounds for convolutional codes and an asymptotically optimum decoding algorithm , 1967, IEEE Trans. Inf. Theory.

[16]  Ryszard S. Choraś.  Image Processing and Communications Challenges 3 - 3rd International Conference, IP&C 2011, Proceedings , 2011, IP&C.

[17]  Shinji Ozawa,et al.  Visual Navigation of an Autonomous Vehicle Using White Line Recognition , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Przemyslaw Mazurek,et al.  Code reordering using local random extraction and insertion (LREI) operator for GPGPU-based track-before-detect systems , 2012, Soft Computing.

[19]  Przemyslaw Mazurek,et al.  Comparison of Different Measurement Spaces for Spatio-Temporal Recurrent Track-Before-Detect Algorithm , 2011, IP&C.

[20]  D. Frejlichowski.  Application of the Curvature Scale Space Descriptor to the Problem of General Shape Analysis , 2012 .