Feature points to detect motion

Camera motion is one of the types of video motion. For large motions feature based techniques perform better. Here, a robust feature-based camera motion estimation method is proposed. The algorithm uses the motion vectors obtained from a set of selected points to calculate the parameters of the camera motion model. It comprises three steps: the detection of feature points, the computation of correspondences between two sets of features, and the motion parameter estimation. This whole process ensures that only the motion model that had the largest number of inliners is returned as result.