Parameterizable FPGA Framework for Particle Filter Based Object Tracking in Video

Abstract

Real-time particle filter based object tracking in videos on embedded platforms (FPGA) is challenging because of its resource usage and computational complexity. Furthermore, minor changes to the algorithm will need changes in the hardware. To address these issues, we propose a parametrizable FPGA framework for particle filter based object tracking algorithm. This parametrizable implementation can be used for various image sequences, object sizes and number of particles. By changing few parameters, this parametrization leads to appropriate changes in hardware resources resulting in efficient real-time operation of the algorithm. Experimental results show better tracking from the implementation and the proposed architecture can run particle filter algorithm for a color video sequence with 650 fps on average.

Evaluation of an OpenCL-Based FPGA Platform for Particle Filter

“…. (10) When the selected index i para is given, we compute the index r (i) of the drawn particle from Eq. (10).…”

“…However, in the simple parallel implementation, exchanging data among processing elements become a bottleneck. Moreover, to enhance the flexibility, some parameterizable FPGA implementations have been proposed and are easy to change their parameters such as the number of particles, image size, and object size [10]. However, changing the FPGA design for different applications, i.e., state space models, requires much design effort in the HDLbased design even though particle filter is flexible.…”