Stereo matching with occlusion detection using cost relaxation

Abstract

This paper presents a new stereo algorithm for computing dense disparity maps from stereo image pairs by a global cost relaxation, realized as an optimization problem, where the disparity map is the momentary state of a dynamic process. Following the natural role model of the human visual system, we assign a set of possible disparities to each image pixel described by cooperating probability variables. In the first step a correlation-based similarity measure is performed to initialize the relaxation process. The relaxation itself is formulated as an optimization of a global cost function taking into account both the stereoscopic continuity constraint and considerations of the pixel similarity. A special formulation guarantees the existence of a unique cost minimum which can be easily and rapidly found by standard numerical procedures. In a post-processing step, occluded areas are detected and a sub-pixel precise disparity map is computed.

Cooperative Stereo Matching with Color-Based Adaptive Local Support

“…For efficiency reasons, the cooperative optimization is formulated as an iterative cost minimization approach with a global cost function containing only squared cost terms (cp. [11]). To simplify equations, all labels in the disparity space are ordered in a single order parameter vector…”

“…Because of the squared cost terms, equation 7 has only one minimum, characterizing the global solution for the optimization problem (cp. [11]). It is calculated numerically with the gradient descent method, where the update function for the iteration is defined as:…”

“…[11]). To calculate sub-pixel precise disparities, the relaxation process is applied once again to the 2D pixel-precise disparity map similar to [11].…”

Anisotropic Diffusion by Quadratic Regularization

“…This is the classic case of isotropic linear diffusion. The isotropic diffusion as well as anisotropic diffusion with symmetric weights, i. e. w i j = w ji , was already used by us in the context of stereoscopic depth estimation ( (Hund, 2002), (Brockers et al, 2005)). There, eq.…”

A Dense Disparity Estimation Method using Color Segmentation and Energy Minimization

“…Figure 2 is the overall flowchart of the proposed method. At first, the reference image is oversegmented by using the mean-shift color segmentation [2]. And segmentation ID is assigned to each segmented plane.…”