A GPU accelerated Fast Directional Chamfer Matching algorithm and a detailed comparison with a highly optimized CPU implementation

In this work we present an efficient GPU implementation of the Fast Directional Chamfer Matching (FDCM) algorithm [10]. We propose some extensions to the original FDCM algorithm. In particular, we extend the algorithm to handle templates with variable size, to account for perspective effects. To the best of our knowledge, our work is the first to present a full implementation of a shape based matching algorithm on a GPU. Further contributions of our work consist of implementing a highly optimized CPU version of the algorithm (via multi-threading and SSE2), as well as a thorough comparison between pure GPU, pure CPU, and a hybrid version. The hybrid CPU-GPU version which turns out to be the fastest, achieves run-time of 44 fps on PAL resolution images.

[1]  Hans-Joachim Wünsche,et al.  Efficient keypoint matching for robot vision using GPUs , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.

[2]  Laurie A. Smith King,et al.  Efficient template matching with variable size templates in CUDA , 2010, 2010 IEEE 8th Symposium on Application Specific Processors (SASP).

[3]  Yakup Genc,et al.  GPU-based Video Feature Tracking And Matching , 2006 .

[4]  Björn Stenger,et al.  Shape context and chamfer matching in cluttered scenes , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[5]  Tomio Hirata,et al.  A Unified Linear-Time Algorithm for Computing Distance Maps , 1996, Inf. Process. Lett..

[6]  Mark Billinghurst,et al.  Accelerating Template-Based Matching on the GPU for AR Applications , 2007, 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality.

[7]  Tiow Seng Tan,et al.  Parallel Banding Algorithm to compute exact distance transform with the GPU , 2010, I3D '10.

[8]  Raúl Cabido,et al.  Hardware-Accelerated Template Matching , 2005, IbPRIA.

[9]  Renaud Keriven,et al.  GPU-boosted online image matching , 2008, ICPR.

[10]  David Schreiber,et al.  A CPU-GPU hybrid people counting system for real-world airport scenarios using arbitrary oblique view cameras , 2012, 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[11]  Robert C. Bolles,et al.  Parametric Correspondence and Chamfer Matching: Two New Techniques for Image Matching , 1977, IJCAI.

[12]  Rama Chellappa,et al.  Fast directional chamfer matching , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[13]  H. Bischof,et al.  Fast human detection in crowded scenes by contour integration and local shape estimation , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  Eric Royer,et al.  Efficient planar features matching for robot localization using GPU , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops.