Shape From Focus refers to the inverse problem of recovering the depth in every point of a scene from a set of differently focused 2D images. Recently, some authors stated it in the variational framework and solved it by minimizing a non-convex functional. However, the global optimality on the solution is not guaranteed and evaluations are often application-specific. To overcome these limits, we propose to globally and efficiently minimize a convex functional by decomposing it into a sequence of binary problems using graph cuts. To illustrate the genericity of such a decomposition-based approach, data-driven strategies are considered, allowing us to optimize (in terms of reconstruction error) the choice of the depth values for a given number of possible depths. We provide qualitative and quantitative evaluation on Middlebury datasets and we show that, according to classic statistics on error values, the proposed approach exhibits high performance and robustness against corrupted data. proaches (where X denotes the cue to infer the shape, e.g. stereo, motion, 5 shading, focus, defocus, etc) or a mixture of them. This topic gave rise to a huge amount of papers and still represents a great interest for researchers in the computer vision community. Indeed, it has numerous applications, especially in robotics, both for localization and environment analysis, in monitoring or video-surveillance either for security or for medical technical assistance, or in 10 microscopy and chemistry [1]. More specifically, let us remind that stereovision relies on the disparities between matched pixels of an image pair [2], shape-from-shading exploits the variations of brightness of a single image [3, 4] and shape-from-motion deduces depth from matched points of interest [5]. Shape-from-focus (SFF) [6] and 15shape-from-defocus (SFD) [7] represent alternatives approaches that share the idea of using the focus to estimate the 3D structure of a scene from differently focused images acquired by a monocular camera. Thus, an object appears focused only in a limited range (depth of field) and is progressively blurred as the camera moves away from this range. For both approaches, active and passive 20 sensors exist, depending on whether or not a structured light composed of patterns is projected onto the scene to alleviate ambiguities. In this paper, we will focus on the passive device. In addition to the depth map, both approaches generally also provide an estimation of the all-in-focus image of the scene, i.e. the image obtained by selecting for each pixel, the intensity at which it appears 25 the most focused, or sharp. Now, SFF and SFD differ on one main point. SFD estimates the depth by measuring the relative blurriness between a reference image and the remaining ones. The blurring process needs to be explicitly modeled, a very few images are usually required and the approach can be applied to dynamic scenes. Similarly, 30 [8,9] have chosen to solve the inverse problem by precisely modeling the defocusing process with the help of an all-...
Bayesian and probabilistic models are widely used in image processing to handle noise due to various alteration phenomena. To benefit from the spatial information in a tractable way, Markov Random Fields (MRF) are often assumed with isotropic neighborhoods, that is however at the detriment of the preservation of thin structures. In this study, we aim at relaxing this assumption on stationarity and isotropy of the neighborhood shape in order to get a prior probability term that is relevant not only within the homogeneous areas but also close to object borders and within thin structures. To tackle the issue of neighborhood shape estimation, we propose to use tensor voting, that allows for the estimation of structure direction and saliency at various scales. We propose three main ways to derive anisotropic neighborhoods, namely shape-based, target-based and cardinal-based neighborhood. Then, having defined the neighborhood field, we introduce an energy that will be minimized using graph cuts, and illustrate the benefits of our approach against the use of isotropic neighborhoods in the applicative context of crack detection. First results on such a challenging problem are very encouraging.
Shape-From-Focus (SFF) refers to the challenging inverse problem of recovering the scene depth from a given set of focused images using a static camera. Standard approaches model the interactions between neighboring pixels to get a regularized solution. Nevertheless, isotropic regularization is known to introduce undesired artifacts and to remove early thin structures. These structures have a small size in at least one dimension and are more numerous when considering superpixel preprocessing. This paper addresses the improvement of SFF regularization through the estimation of the presence of such structures and the construction of anisotropic neighborhoods sticking along image edges and proposes a flexible formulation over pixels or superpixels. A thoroughly study comparing different strategies for constructing these neighborhoods in terms of accuracy and running time for the targeted application is provided. Notably, experiments performed on a reference dataset show the overall superiority of the approach, e.g. a decrease of the RMSE value by about 20%, and its robustness against generated superpixels.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.