A two stage template matching algorithm and its İmplementation on FPGA

In this paper, to decrease the computational cost and number of cycles in Template Matching Algorithm, a novel two-stage algorithm is proposed. The Sum of Absolute Differences method is used for matching. The proposed algorithm is implemented on Field-Programmable-Gate-Array (FPGA). The algorithm is accelerated with the effective usage of Block RAMs distributed on FPGA. Thus, the proposed algorithm became fast enough for real time object tracking applications on UAVs.

[1]  Federico Tombari,et al.  Performance Evaluation of Full Search Equivalent Pattern Matching Algorithms , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Lisa M. Brown,et al.  A survey of image registration techniques , 1992, CSUR.

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

[4]  Arif Mahmood,et al.  Correlation-Coefficient-Based Fast Template Matching Through Partial Elimination , 2012, IEEE Transactions on Image Processing.

[5]  Kunio Kashino,et al.  A fast template matching algorithm with adaptive skipping using inner-subtemplates' distances , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[6]  Liang-Gee Chen,et al.  Survey on Block Matching Motion Estimation Algorithms and Architectures with New Results , 2006, J. VLSI Signal Process..

[7]  Sheng Zhong,et al.  A fast template matching method based on context prediction , 2011, International Symposium on Multispectral Image Processing and Pattern Recognition.

[8]  Federico Tombari,et al.  Fast Full-Search Equivalent Template Matching by Enhanced Bounded Correlation , 2008, IEEE Transactions on Image Processing.