Object tracking with template matching method and its high speed fpga implementation

Image processing algoritms are widely used in many application areas, such as object tracking systems. The object tracking systems are mainly used in security and defence applications. Unmanned Air Vehicles which are used widely nowadays, have the major functions of object tracking applications. There are many techniques for object tracking systems and one of them is Template Matching technique. Although the accuracy is very high in this technique, it has very big computationalcost. As the aim is to track the object, the system has to be operated in real time. To achieve a real time operation the algorithm and logic sources must be optimized. In this study, to decrease the computational cost and number of cycles in Template Matching Algorithm, a novel two-stage algorithm is proposed. The Sum of Absolute Differences method is used for matching. The proposed algorithm is implemented on Field-Programmable-Gate-Array (FPGA). The algorithm is accelerated with the effective usage of Block RAMs distributed on FPGA. Thus, the proposed algorithm has become fast enough for real time object tracking applications on UAVs.