Abstract Estimating depth from a single image is challenging because 2D may correspond to many different 3D scenes with the same depth. While most deep learning based prediction methods extract features using small convolutional kernels receptive fields, which results in deformed edges and inaccurate values of distant objects estimation results. Aiming at this problem, we propose network on Swi...

A depth estimation algorithm from plenoptic images is presented. There are two stages to estimate the depth. First is the initial estimation base on the epipolar plane images (EPIs). Second is the refinement of the estimations. At the initial estimation, adaptive window matching is used to improve the robustness. The size of the matching window is based on the texture description of the sample ...

In this paper, the crack detection and depth ratio estimation method are presented in beamlikestructures using Elman Networks. For this purpose, by using the frequencies of modes asinput, crack depth ratio of each element was detected as output. Performance of the proposedmethod was evaluated by using three numerical scenarios of crack for fixed-simply supportedbeam consisting of a single crack...

We propose a framework for depth estimation from a set of calibrated images, captured with a moving camera with varying parameters. Our framework respects the physical limits of the camera, and considers various effects such as motion parallax, defocus blur, zooming and occlusions which are often unavoidable. In fact, the stereo [1] and the depth from defocus [2] are essentially special cases i...

With the development of computational intelligence algorithms, unsupervised monocular depth and pose estimation framework, which is driven by warped photometric consistency, has shown great performance in day-time scenario. While some challenging environments, like night rainy night, essential consistency hypothesis untenable because complex lighting reflection, so that above framework cannot b...