A numerical comparison between Feature Correlation and Phase Correlation for motion estimation relat

Abstract The article compares the performance of Feature Correlation and Phase Correlation algorithms for the motion estimation of an underwater vehicle. While feature correlation relies on the extraction and matching of features templates, Phase Correlation is a featureless approach, relying instead on the overall properties of the image. Three versions of Feature Correlation algorithm and two different implementations of the Phase Correlation algorithm are compared, on data collected by the HCMR Thetis submersible during the Nautilos Project in 2004; since the mission focused on different research priorities, the recordings are suboptimal regarding sea bottom mosaicking, featuring motion blurs, roll sweeps, geometric distortions and optical axis non-perpendicular to the bottom. The results show the effectiveness of feature correlation in dealing with blurred images, while in terms of computational time, both implementations of the phase correlation algorithm outperform any of the feature correlation algorithms by a large margin.

[1]  R. L. Marks,et al.  Real-time video mosaicking of the ocean floor , 1995 .

[2]  Francesco Orsenigo,et al.  Tornado: An Application for on-the-Fly Mosaicking through Phase Correlation , 2009 .

[3]  Stephen A Gibson.  An optimal FFT-based algorithm for mosaicking images , 1999 .

[4]  G. Bruzzone,et al.  Comparison between feature-based and phase correlation methods for ROV vision-based speed estimation , 2010 .

[5]  O. Pizarro,et al.  Visually Augmented Navigation for Autonomous Underwater Vehicles , 2008, IEEE Journal of Oceanic Engineering.

[6]  Shahriar Negahdaripour,et al.  Positioning and photo-mosaicking with long image sequences; comparison of selected methods , 2001, MTS/IEEE Oceans 2001. An Ocean Odyssey. Conference Proceedings (IEEE Cat. No.01CH37295).

[7]  Vladik Kreinovich,et al.  An IDL/ENVI Implementation of the FFT Based Algorithm for Automatic Image Registration , 2003 .

[8]  M. Caccia,et al.  Laser-Triangulation Optical-Correlation Sensor for ROV Slow Motion Estimation , 2006, IEEE Journal of Oceanic Engineering.

[9]  Keiken Ninomiya,et al.  Optical guidance for autonomous landing of spacecraft , 1999 .

[10]  Steven G. Johnson,et al.  The Design and Implementation of FFTW3 , 2005, Proceedings of the IEEE.

[11]  G. Bruzzone,et al.  Online video mosaicing through SLAM for ROVs , 2009, OCEANS 2009-EUROPE.

[12]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[13]  Vasileios Argyriou,et al.  Extrapolation-free arbitrary-shape motion estimation using phase correlation , 2006, J. Electronic Imaging.

[14]  O. Pizarro,et al.  Large Area 3-D Reconstructions From Underwater Optical Surveys , 2009, IEEE Journal of Oceanic Engineering.

[15]  Joan Batlle,et al.  Positioning an underwater vehicle through image mosaicking , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

[16]  Hanumant Singh,et al.  Toward large-area mosaicing for underwater scientific applications , 2003 .

[17]  Stephen M. Rock,et al.  Demonstration of a vision-based dead-reckoning system for navigation of an underwater vehicle , 1998, Proceedings of the 1998 Workshop on Autonomous Underwater Vehicles (Cat. No.98CH36290).

[18]  C. Morandi,et al.  Registration of Translated and Rotated Images Using Finite Fourier Transforms , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Massimo Caccia,et al.  Speeded Up Robust Features for vision-based underwater motion estimation and SLAM: comparison with c , 2009 .

[20]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[21]  B. N. Chatterji,et al.  An FFT-based technique for translation, rotation, and scale-invariant image registration , 1996, IEEE Trans. Image Process..