Anisotropic motion estimation on edge preserving Riesz wavelets for robust video mosaicing. (March 2016)

• Record Type: Journal Article
• Authors: Ali, Sharib; Daul, Christian; Galbrun, Ernest; Guillemin, François; Blondel, Walter
• Is Part Of: Pattern recognition. Volume 51(2016:Mar.)
• Page Start: 425
• Page End: 442
• Publication Date: 2016-03
• Subjects: Image registration -- Image sequence mosaicing -- Optical flow -- Anisotropic regularizer -- Weighted median filtering -- Endoscopy; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2015.09.021
• Languages: English
• ISSNs: 0031-3203

Abstract

Abstract: Image mosaicing is a technique widely used for extending the field of view of industrial, medical, outdoor or indoor scenes. However, image registration can be very challenging, e.g. due to large texture variability, illumination changes, image blur and camera perspective changes. In this paper, a total variational optical flow approach is investigated to estimate dense point correspondences between image pairs. An edge preserving Riesz wavelet scale-space combined with a novel TV-regularizer is proposed for preserving motion discontinuities along the edges of weak textures and for handling strong in-plane rotations present in image sequences. An anisotropic weighted median filtering is implemented for minimizing outliers. Quantitative evaluation of the method on the Middlebury image database and simulated sequences with known ground truth demonstrates high accuracy of the proposed method in comparison with other state-of-the-art methods, including a robust graph-cut method and a patch matching approach. Qualitative results on video-sequences of difficult real scenes demonstrate the robustness of the proposed method. Abstract : Highlights: Mosaicing of images with strong texture and illumination variability. Fast, robust and accurate optical flow computation. TV-L1 method on a second order Riesz wavelet basis for preserving texture discontinuities. Novel anisotropic TV-regularizer. Accurate results for both the Middlebury data set and various complicated scenes.