Object Tracking Using Vision on Raspberry Pi

Document Type : Original Article

Authors

1 Egyptian Armed Forces.

2 Dr., Computer Engineering Dept., New Cairo Academy.

3 Prof., Computer Engineering Dept.

Abstract

Object tracking is an important task in several computer vision applications. Optical flow is one of the most widely used techniques in the image processing and video analysis fields. This paper implements an object tracking algorithm based on optical flow method to be computed by Raspberry Pi microcomputer. A Lucas–Kanade method has been used to calculate the velocity vector of the moving object between two consecutive frames. Two experiments are performed to evaluate the robustness of the proposed algorithm by the new computing device. The results were encouraging to use the proposed framework on wide variety of real time application.

Keywords