Real-time vibration reduction in UAV'S image sensors using efficient Hough transform

Abstract

This paper explores use of Hough transform to detect and track angular changes between a series of images acquired by vision sensors attached to unmanned aerial vehicles (UAV) and are used in traffic surveillance. The small size and atmospheric conditions can lead to unstable flying and this can induce vibration to the pictures. In this research it is proposed that the vibration in the acquired images can be reduced by using the angular variation as feedback to stabilize the motion of the UAV as it captures subsequent frames.