Video Stabilization using Hybrid of SIFT and SURF Algorithm

Abstract

Video stabilization is an important enhancement techniques used to remove undesired motion in a video. The sphere of photo forensics is expanding hastily. Many passive photograph tamper detection techniques were presented techniques have been presented. Some of those techniques use characteristic extraction methods for tamper detection and localization. This work is based totally on extracting Mean Square Error (MSE) regions features for cloning detection, observed by using okmeans clustering for cloning localization. Then for contrast functions, we put into effect the speeded-up robust features (SURF) and Scale-Invariant feature transform (SIFT).In this paper, we gift a singular video stabilization and transferring object detection system primarily based on digital camera movement estimation. Local feature extraction is used and matching to estimate global motion and we demonstrate that Scale Invariant Feature Transform (SIFT) key points are suitable for the stabilization task. After estimating the global camera motion parameters using affine transformation, we detect moving object by filtering. Combination of global camera motion estimation along with motion separation determines the undesired motion, which is to be compensated to produce a stable video sequence. A novel method for robust video stabilization is proposed which uses Speeded Up Robust Features (SURF) as stable feature points to be tracked between frames for global motion estimation. Different measures are taken to select the most appropriate feature point trajectories. The usability and efficacy of our approach is verified by comparing with recent state-of-the-art approaches