The Application of Normalized Covariance in Video Mosaicing

Considering the mismatch and the high computational complexity of video mosaicing, a fast stitching method based on the normalized covariance is proposed. Firstly, the image corner features are extracted using the SURF algorithm and the corresponding matching points are found using the nearest neighbor method. The least square method is used to filter the matching points and accurately match the point-pair. And then, the homography matrix is got and can be used in finding the overlapping area of two images. The optimal homography matrix is obtained according to the normalization covariance and the bidirectional matching by which the video mosaicing is finished. Finally, the bilinear interpolation algorithm and the weighted average method are used to get a realistic and seamless image that retains high image resolution. The experimental results show that this algorithm can obtain better parameters estimation values and has smaller calculations as well as good robustness so as to stitch the video fast and seamlessly.