An efficient prediction scheme for pedestrian tracking with cascade particle filter and its implementation on Cell/B.E.

Cascade Particle Filter was proposed for accurate object recognition in low frame rate video. However, Cascade Particle Filter can be expected to enhance the accuracy of recognition even in a regular frame rate video because of its run-time learning procedure. To apply such cascade particle filter for pedestrian recognition on surveillance and automotive applications, we propose an efficient prediction scheme optimized for pedestrian tracking in such applications. Moreover, we implement proposed scheme on Cell/B.E., one of the latest embedded high performance processors, to demonstrate real-time pedestrian tracking on embedded systems. Experimental result shows that proposed scheme inproves pedestrian tracking accuracy by 22% with real-time processing on 30 fps video.

[1]  Yuan Li,et al.  Vector boosting for rotation invariant multi-view face detection , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[2]  Hiroyuki Ochi,et al.  Hardware Architecture for HOG Feature Extraction , 2009, 2009 Fifth International Conference on Intelligent Information Hiding and Multimedia Signal Processing.

[3]  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..

[4]  Yuan Li,et al.  Tracking in Low Frame Rate Video: A Cascade Particle Filter with Discriminative Observers of Different Lifespans , 2007, CVPR.

[5]  Ryusuke Miyamoto,et al.  Parallel Implementation of Good Feature Extraction for Tracking on the Cell Processor with OpenCV Interface , 2009, 2009 Fifth International Conference on Intelligent Information Hiding and Multimedia Signal Processing.

[6]  B. Flachs,et al.  The microarchitecture of the synergistic processor for a cell processor , 2006, IEEE Journal of Solid-State Circuits.

[7]  R. Miyamoto,et al.  Parallel implementation of morphological processing on Cell/BE with OpenCV interface , 2008, 2008 3rd International Symposium on Communications, Control and Signal Processing.

[8]  Ryusuke Miyamoto,et al.  Partially Parallel Architecture for AdaBoost-Based Detection With Haar-Like Features , 2009, IEEE Transactions on Circuits and Systems for Video Technology.

[9]  Ryusuke Miyamoto,et al.  A Real-Time Object Recognition System on Cell Broadband Engine , 2007, PSIVT.

[10]  Ryusuke Miyamoto,et al.  Opencv implementation optimized for a cell broadband engine processor , 2009, 2009 IEEE 13th Digital Signal Processing Workshop and 5th IEEE Signal Processing Education Workshop.