An intensity-based cooperative bidirectional stereo matching with simultaneous detection of discontinuities and occlusions

Segmentation framework based on label field fusion

In this paper, we put forward a novel fusion framework that mixes together label fields instead of observation data as is usually the case. Our framework takes as input two label fields: a quickly estimated and to-be-refined segmentation map and a spatial region map that exhibits the shape of the main objects of the scene. These two label fields are fused together with a global energy function that is minimized with a deterministic iterative conditional mode algorithm. As explained in the paper, the energy function may implement a pure fusion strategy or a fusion-reaction function. In the latter case, a data-related term is used to make the optimization problem well posed. We believe that the conceptual simplicity, the small number of parameters, the use of a simple and fast deterministic optimizer that admits a natural implementation on a parallel architecture are among the main advantages of our approach. Our fusion framework is adapted to various computer vision applications among which are motion segmentation, motion estimation and occlusion detection.

Archetypal oscillator for smooth and discontinuous dynamics

We propose an archetypal system to investigate transitions from smooth to discontinuous dynamics. In the smooth regime, the system bears significant similarities to the Duffing oscillator, exhibiting the standard dynamics governed by the hyperbolic structure associated with the stationary state of the double well. At the discontinuous limit, however, there is a substantial departure in the dynamics from the standard one. In particular, the velocity flow suffers a jump in crossing from one well to another, caused by the loss of local hyperbolicity due to the collapse of the stable and unstable manifolds of the stationary state. In the presence of damping and external excitation, the system has coexisting attractors and also a chaotic saddle which becomes a chaotic attractor when a smoothness parameter drops to zero. This attractor can bifurcate to a high-period periodic attractor or a chaotic sea with islands of quasiperiodic attractors depending on the strength of damping.

Stereo using monocular cues within the tensor voting framework

We address the fundamental problem of matching in two static images. The remaining challenges are related to occlusion and lack of texture. Our approach addresses these difficulties within a perceptual organization framework, considering both binocular and monocular cues. Initially, matching candidates for all pixels are generated by a combination of matching techniques. The matching candidates are then embedded in disparity space, where perceptual organization takes place in 3D neighborhoods and, thus, does not suffer from problems associated with scanline or image neighborhoods. The assumption is that correct matches produce salient, coherent surfaces, while wrong ones do not. Matching candidates that are consistent with the surfaces are kept and grouped into smooth layers. Thus, we achieve surface segmentation based on geometric and not photometric properties. Surface overextensions, which are due to occlusion, can be corrected by removing matches whose projections are not consistent in color with their neighbors of the same surface in both images. Finally, the projections of the refined surfaces on both images are used to obtain disparity hypotheses for unmatched pixels. The final disparities are selected after a second tensor voting stage, during which information is propagated from more reliable pixels to less reliable ones. We present results on widely used benchmark stereo pairs.