Depth estimation improvement in 3D integral imaging using an edge removal approach

Sotoca, José Martínez; Carmona, Pedro; Espinós-Morató, Héctor; Pla, Filiberto; Javidi, Bahram

doi:10.1007/s10044-018-0721-4

Cited by 2 publications

(4 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second one called Elemental Imaging from Edge removal (EIEd-rem) approach [24], removes the edges of objects in the EIs when they are in focus. This is a problem that appears when using the variance where the objects close to cameras, once they are in focus, have a tendency to expand their corresponding edges in the scene for images in focus at higher depths.…”

Section: Resultsmentioning

confidence: 99%

“…In [28] and [37] the use of a photo-consistency measure is proposed by combining a defocus and a correspondence measure in a light-field camera. This measure, made by these two terms, was extended to the case of SAII in [24] and [33]. The defocus measure allows for an optimal contrast to be obtained in a certain patch of the image with the aim to improve stability over occluded regions.…”

Section: B Depth Map and All-in-focus Reconstruction For Median Distmentioning

confidence: 99%

“…Several works [22]- [24] have tried to tackle two of the problems that affect most the quality in a 3D reconstruction scenario (and, in particular, in SAII). The first one is to define a robust photo-consistency measure that detects when the surface of an object is in focus.…”

Section: Introductionmentioning

confidence: 99%

“…This is made by creating a variance map per elemental image and applying a clustering technique to classify pixels into two classes, foreground and background pixels, depending on the variance value each pixel has [29], [30]. In [24] a similar strategy has been used by means of a previous estimation of depths of the edges belonging to the occluding objects, in order to improve the accuracy in the depth map. Others apply methods to fill in the missing information using, for instance, inpainting techniques [31].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Depth and All-in-Focus Image Estimation in Synthetic Aperture Integral Imaging Under Partial Occlusions

et al. 2019

Self Cite

View full text Add to dashboard Cite

A common assumption in the integral imaging reconstruction is that a pixel will be photoconsistent if all viewpoints observed by the different cameras converge at a single point when focusing at the proper depth. However, the presence of occlusions between objects in the scene prevents this from being fulfilled. In this paper, a novel depth and all-in focus image estimation method is presented, based on a photo-consistency measure that uses the median criterion in relation to the elemental images. The interest of this approach is to find a solution to detect which camera correctly sees the partially occluded object at a certain depth and allows for a precise solution to the object depth. In addition, a robust solution is proposed to detect the boundary limits between partially occluded objects, which are subsequently used during the regularization depth estimation process. The experimental results show that the proposed method outperforms other state-of-the-art depth estimation methods in a synthetic aperture integral imaging framework. INDEX TERMS Synthetic aperture integral imaging, depth map estimation, all-in-focus image, partial occlusions, 3D image processing.

show abstract

Section: Resultsmentioning

confidence: 99%