Moving Object Detection for Moving Cameras on Superpixel Level

In this paper, we will present a novel algorithm for detecting moving objects from relatively dynamic background in particular video sequences. To achieve our goal, we introduced a new conception called "feature super pixel". As is well known, by tracking feature points we can easily tell whether a feature point belongs to moving object or not. However, it's more difficult to obtain an optimal pixel-wise foreground and background labeling. Considering the assumption that pixels in the same super pixel belong to the same object, this paper designed a method to describe and match super pixels, which has been proved to be efficient in experiments.