The Challenges and Advantages with a Parallel Implementation of Feature Matching

The number of cores per cpu is predicted to double every second year. Therefore, the opportunity to parallelise currently used algorithms in computer vision and image processing needs to be addressed sooner rather than later. A parallel feature matching approach is proposed and evaluated in Matlabr. The key idea is to use different interest point detectors so that each core can work on its own subset independently of the others. However, since the image pairs are the same, the homography will be essentially the same and can therefore be distributed by the process that first finds a solution. Nevertheless, the speedup is not linear and reasons why

[1]  Matthew A. Brown,et al.  Automatic Panoramic Image Stitching using Invariant Features , 2007, International Journal of Computer Vision.

[2]  Miguel A. Vega-Rodríguez,et al.  A Comparative Study of Parallel RANSAC Implementations in 3D Space , 2014, International Journal of Parallel Programming.

[3]  Tobias Höllerer,et al.  Evaluation of Interest Point Detectors and Feature Descriptors for Visual Tracking , 2011, International Journal of Computer Vision.

[4]  B. S. Manjunath,et al.  The multiRANSAC algorithm and its application to detect planar homographies , 2005, IEEE International Conference on Image Processing 2005.

[5]  Anders Hast.  Interest Point Detection based on the Extended Structure Tensor with a Scale Space Parameter , 2015, VISAPP.

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

[7]  Keinosuke Fukunaga,et al.  A Branch and Bound Algorithm for Computing k-Nearest Neighbors , 1975, IEEE Transactions on Computers.

[8]  Anders Hast,et al.  Invariant Interest Point Detection Based on Variations of the Spinor Tensor , 2014, WSCG 2014.

[9]  Jon Louis Bentley,et al.  An Algorithm for Finding Best Matches in Logarithmic Expected Time , 1977, TOMS.

[10]  David G. Lowe,et al.  Fast Approximate Nearest Neighbors with Automatic Algorithm Configuration , 2009, VISAPP.

[11]  Andrea Marchetti,et al.  Rotation invariant feature matching-based on Gaussian filtered log polar transform and phase correlation , 2013, 2013 8th International Symposium on Image and Signal Processing and Analysis (ISPA).

[12]  Andrea Marchetti,et al.  Optimal RANSAC-Towards a Repeatable Algorithm for Finding the Optimal Set , 2013, J. WSCG.

[13]  Fredrik Kahl,et al.  Robust Optimal Pose Estimation , 2008, ECCV.

[14]  S. M. Steve.  SUSAN - a new approach to low level image processing , 1997 .

[15]  Andrs Vajda.  Programming Many-Core Chips , 2011 .

[16]  Friedrich M. Wahl,et al.  An efficient parallel approach to Random Sample Matching (pRANSAM) , 2009, 2009 IEEE International Conference on Robotics and Automation.

[17]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[18]  Hans P. Moravec.  Obstacle avoidance and navigation in the real world by a seeing robot rover , 1980 .

[19]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[20]  Jan Flusser,et al.  Image registration methods: a survey , 2003, Image Vis. Comput..

[21]  Stepán Obdrzálek,et al.  Object Recognition Using Local Affine Frames on Maximally Stable Extremal Regions , 2006, Toward Category-Level Object Recognition.

[22]  Olaf Hellwich,et al.  Genetic Algorithm SAmple Consensus (GASAC) - A Parallel Strategy for Robust Parameter Estimation , 2006, 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06).

[23]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[24]  A. Fijany,et al.  A cooperative search algorithm for highly parallel implementation of RANSAC for model estimation on Tilera MIMD architecture , 2012, 2012 IEEE Aerospace Conference.

[25]  Anders Hast.  Robust and Invariant Phase Based Local Feature Matching , 2014, 2014 22nd International Conference on Pattern Recognition.