Object recognition with ORB and its Implementation on FPGA

Object recognition and tracking has a wide spectrum of promising applications. Feature-based algorithms are well-suited for such operations like Speeded Up Robust Features (SURF), SIFT (Scale-invariant feature transform), ORB (Oriented FAST and Rotated BRIEF) algorithm has been proved to achieve optimal results. ORB algorithm builds on the well-known FAST key point detector and the recently-developed BRIEF descriptor. This paper gives an overview of a general methods of object recognition and significance of ORB over SIFT and SURF in different cases. This paper also provides an idea to implement ORB algorithm on FPGA to increase the execution speed by utilizing the reconfigurable nature and pipelining of the FPGA.

[1]  Gary R. Bradski,et al.  ORB: An efficient alternative to SIFT or SURF , 2011, 2011 International Conference on Computer Vision.

[2]  Christopher Hunt,et al.  Notes on the OpenSURF Library , 2009 .

[3]  Varsha S. Surwase,et al.  Implementation of Image Processing Algorithms on FPGA , 2010 .

[4]  Yan Ke,et al.  PCA-SIFT: a more distinctive representation for local image descriptors , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[5]  FPGA vs. DSP Design Reliability and Maintenance , 1998 .

[6]  Krystian Mikolajczyk,et al.  Evaluation of local detectors and descriptors for fast feature matching , 2012, Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).

[7]  Mohan M. Trivedi,et al.  Human Pose Estimation and Activity Recognition From Multi-View Videos: Comparative Explorations of Recent Developments , 2012, IEEE Journal of Selected Topics in Signal Processing.