Underwater multi-spectral photometric stereo reconstruction from a single RGBD image

One of the main problems faced by the photometric stereo method is that several measurements are required, as this method needs illumination from light sources from different directions. A solution to this problem is the color photometric stereo method, which conducts one-shot measurements by simultaneously illuminating lights of different wavelengths. However, the classic color photometric stereo method only allows measurements of white objects, while a surface-normal estimation of a multicolored object using this method is theoretically impossible. Therefore, it is necessary to add some constraints to estimate the surface normal of a multicolored object using the framework of the color photometric stereo method. In this study, a median filter is employed as the constraint condition of albedo, and the surface normal of the occluding boundary is employed as the constraint condition of the surface normal. By employing a median filter as the constraint condition, the smooth distribution of the albedo and normal is calculated while the sharp features at the boundary of different albedos and normals are preserved. The surface normal at the occluding boundary is propagated into the inner part of the object region, and forms the abstract shape of the object. Such a surface normal gives a great clue to be used as an initial guess to the surface normal. To demonstrate the effectiveness of this study, a measurement device that can realize the multispectral photometric stereo method with seven colors is employed instead of the classic color photometric stereo method with three colors.

show abstract

“…are known, the surface normal n can be obtained by calculating the pseudo-inverse matrix L + of matrix L, as shown in Equation (15).…”

Section: Determining Surface Normal and Albedomentioning

confidence: 99%

Color Photometric Stereo Using Multi-Band Camera Constrained by Median Filter and Occluding Boundary

2019

View full text Add to dashboard Cite

show abstract

“…Be inspired that SLAM algorithms estimates depth maps when it performs localization and mapping, we can import depth map from SLAM into multi-spectral photometric algorithm for 3D shape recovery. Considering that the experimental setup of [9] exactly meets our experimental requirements, that is, they need to reconstruct the objects' three-dimensional structure filmed by a dynamic camera, we can take advantage of the mothods they use. In contrast, we use depth map from LSD-SLAM as priors in multispectral photometric stereo algorithm for dense 3D reconstruction.…”

Section: Multispectral Photometric Stereomentioning

confidence: 99%

“…The camera motion metrix is used to convert point cloud view. Also, we can derive depth maps of each keyframe from semi-dense SLAM which will be used as priori information for optimization-based multi-spectral photometric stereo algorithm [9] to recover a dense surface normal. Then, the dense surface normal from multispectral photometric stereo is added into the semi-dense point cloud from SLAM for further fusion.…”

Section: Introductionmentioning

confidence: 99%

Combining depth-estimation-based multi-spectral photometric stereo and SLAM for real-time dense 3D reconstruction

Dong

et al. 2018

Proceedings of the 4th International Conference on Communication and Information Processing

Self Cite

View full text Add to dashboard Cite

Obtaining dense 3D reconstrution with low computational cost is one of the important goals in the field of SLAM. In this paper we propose a dense 3D reconstruction framework from monocular multispectral video sequences using jointly semi-dense SLAM and Multispectral Photometric Stereo approaches. Starting from multispectral video, SALM (a) reconstructs a semi-dense 3D shape that will be densified;(b) recovers relative sparse depth map that is then fed as prioris into optimization-based multispectral photometric stereo for a more accurate dense surface normal recovery;(c)obtains camera pose that is subsequently used for conversion of view in the process of fusion where we combine the relative sparse point cloud with the dense surface normal using the automated cross-scale fusion method proposed in this paper to get a dense point cloud with subtle texture information. Experiments show that our method can effectively obtain denser 3D reconstructions.

show abstract

“…The distance between the superpixel center, C m , and each pixel, i, is calculated in region 2g × 2g around the C m [42]. Then, all the pixels can be assigned to the nearest cluster center, and the superpixels with the approximate size of g × g are finally obtained [35].…”

Section: Initial Samples Generation For Statistical Modelmentioning

confidence: 99%

“…Then the centers are adjusted to seed locations where the lowest gradient meets in a 3 × 3 neighborhood [42]. This procedure is important as it avoids centering a superpixel on an edge, and reduces the probability of seeding a superpixel with a noisy pixel.…”

Section: Initial Samples Generation For Statistical Modelmentioning

confidence: 99%

Multi-Feature Segmentation for High-Resolution Polarimetric SAR Data Based on Fractal Net Evolution Approach

Chen

et al. 2017

Remote Sensing

View full text Add to dashboard Cite

Segmentation techniques play an important role in understanding high-resolution polarimetric synthetic aperture radar (PolSAR) images. PolSAR image segmentation is widely used as a preprocessing step for subsequent classification, scene interpretation and extraction of surface parameters. However, speckle noise and rich spatial features of heterogeneous regions lead to blurred boundaries of high-resolution PolSAR image segmentation. A novel segmentation algorithm is proposed in this study in order to address the problem and to obtain accurate and precise segmentation results. This method integrates statistical features into a fractal net evolution algorithm (FNEA) framework, and incorporates polarimetric features into a simple linear iterative clustering (SLIC) superpixel generation algorithm. First, spectral heterogeneity in the traditional FNEA is substituted by the G 0 distribution statistical heterogeneity in order to combine the shape and statistical features of PolSAR data. The statistical heterogeneity between two adjacent image objects is measured using a log likelihood function. Second, a modified SLIC algorithm is utilized to generate compact superpixels as the initial samples for the G 0 statistical model, which substitutes the polarimetric distance of the Pauli RGB composition for the CIELAB color distance. The segmentation results were obtained by weighting the G 0 statistical feature and the shape features, based on the FNEA framework. The validity and applicability of the proposed method was verified with extensive experiments on simulated data and three real-world high-resolution PolSAR images from airborne multi-look ESAR, spaceborne single-look RADARSAT-2, and multi-look TerraSAR-X data sets. The experimental results indicate that the proposed method obtains more accurate and precise segmentation results than the other methods for high-resolution PolSAR images.

show abstract

Underwater multi-spectral photometric stereo reconstruction from a single RGBD image

Cited by 11 publications

References 9 publications

Color Photometric Stereo Using Multi-Band Camera Constrained by Median Filter and Occluding Boundary

Color Photometric Stereo Using Multi-Band Camera Constrained by Median Filter and Occluding Boundary

Combining depth-estimation-based multi-spectral photometric stereo and SLAM for real-time dense 3D reconstruction

Multi-Feature Segmentation for High-Resolution Polarimetric SAR Data Based on Fractal Net Evolution Approach

Contact Info

Product

Resources

About