Real-Time Motion Tracking Using the CELL BE

Object tracking is an important computer vision problem with many civilian and military applications including surveillance, robotics and intelligent vehicle design. Most of these applications require fast processing due to their real time nature. The Cell processor is a cost-efficient commodity architecture intended for video gaming and provides new opportunities for parallel processing. This paper provides a costefficient motion detection using the Cell processor. The results have shown that this solution can meet the real time processing requirements of realistic motion detection applications.

[1]  Chandrika Kamath,et al.  Block Matching for Object Tracking , 2003 .

[2]  Larry S. Davis,et al.  Fast multiple object tracking via a hierarchical particle filter , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[3]  Luciano Oliveira,et al.  On Using Cell Broadband Engine for Object Detection in ITS , 2008 .

[4]  S. Asano,et al.  The design and implementation of a first-generation CELL processor , 2005, ISSCC. 2005 IEEE International Digest of Technical Papers. Solid-State Circuits Conference, 2005..

[5]  Fadi N. Sibai,et al.  Parallel Video Processing Performance Evaluation on the IBM Cell Broadband Engine Processor , 2016, Int. J. Comput. Sci. Appl..

[6]  H. Peter Hofstee,et al.  Power efficient processor architecture and the cell processor , 2005, 11th International Symposium on High-Performance Computer Architecture.