Recently, embedded systems have become popular because of the rising demand\nfor portable, low-power devices. A common task for these devices is object tracking,\nwhich is an essential part of various applications. Until now, object tracking in video\nsequences remains a challenging problem because of the visual properties of objects\nand their surrounding environments. Among the common approaches, particle filter\nhas been proven effective in dealing with difficulties in object tracking. In this research,\nwe develop a particle filter based object tracking method using color distributions of\nvideo frames as features, and deploy it in an embedded system. Because particle filter\nis a high-complexity algorithm, we utilize computing power of embedded systems\nby implementing a parallel version of the algorithm. The experimental results show\nthat parallelization can enhance the performance of particle filter when deployed in\nembedded systems.
Loading....