Shape from stereo and shading by gradient constrained interpolation

Abstract

Textureless regions, though error prone in stereo, may contain shading information that may be exploited. Shape from shading (SFS) results relate to world coordinates by arbitrary scaling factors which are difficult to estimate. We propose a method for estimating dense disparities from sparse correspondences using SFS cues. We show that SFS can impose constraints on the gradient of disparity in textureless regions with constant albedo. Gradient Constrained Interpolation (GCI), which solves the estimation problem in one dimension, is presented. We efficiently generate paths between correspondences that cover the image and then use GCI to fill the pixels in between. Results are presented on real and synthetic images, and provide quantitative evaluations to show that the method outperforms baseline methods.

A novel algorithm and hardware architecture for fast video-based shape reconstruction of space debris

“…The FPGA and the processor subsystems share an external memory, used to store results and temporary data, and they communicate between each other in order to avoid any collision during memory reads or writes. As aforementioned, the results obtained by the stereo-vision algorithm can be merged to the ones in output from the Fast-SfS algorithm to correct them and to enhance their accuracy [15,16]. The following subsections detail the functions and the internal architecture of the two subsystems.…”

“…While the idea of merging sparse depth data, obtained by the stereo-vision, with SfS output data is not new [15,16], this paper proposes, for the first time, a comprehensive system hardware architecture implementing the two orthogonal approaches.…”

“…Since several types of space debris fall into this category, shape-from-shading algorithms that work by exploiting pixel intensities in a single image [13], combined to stereo-vision, could represent an efficient solution [14][15][16]. Moreover, in this type of missions, high performances are required to maximize the throughput of processed frames that enables an increase of the extracted information and, consequently, the accuracy of the reconstructed shape models.…”