01147nam a2200121Ia 4500 231221s9999 xx 000 0 und d English Fatima Zohra. SOC For Object Tracking Rajeshwari, B. 2018-2019 PES University Bengaluru Object tracking has been one of the most researched topics in computer vision. A drastic improvement has been seen in the field of object tracking over past few decades. However, it still remains a complex problem to be solved. In this project a SoC is designed by integrating designed and customized IPs from library. Application program is written for the SoC to detect and track moving objects. Optical flow approach is used to detect the objects. Lucas- Kanade dense optical flow is used to obtain the information of movement of the object. Median filtering removes the unwanted noise, thresholding and morphological operations are used to track only the object of interest. Blob analysis sets the object type restrictions. The hardware implementation has been achieved on ZedBoard platform which is an All- Programmable SoC by Xilinx CD 237078 237078 2024-01-26 00:00:00 0 CD7205 2024-01-26 CD 0 0 0 0 ML ML 0000-00-00 EC/PG RS 1 0