Moving object detection using image registration for a moving camera platform

Abstract

This paper proposes an accurate moving object detector from Unmanned Aerial Platform (UAV). Due to the distance of UAV to targets and the movement of the platform, object detection is a challenging task. In order to achieve the best result with low error, at first the camera motion has to be estimated; therefore, by using the Shi & Tomasi corner detector the corners are detected. Using image registration the motion is estimated and then compensated. After motion compensation, adaptive background subtraction is applied for detecting and extracting the moving objects. Experiments on different data sets show the accuracy of our approach on detecting moving objects from aerial platform with up to 85% correct detection.