Plane Fitting in 3D Reconstruction to Preserve Smooth Homogeneous Surfaces

Photogrammetric techniques for weakly-textured surfaces without sufficient information about the R (red), G (green) and B (blue) primary colors of light are challenging. Considering that most urban or indoor object surfaces follow simple geometric shapes, a novel method for reconstructing smooth hom...

Full description

Bibliographic Details
Main Authors: Yanan Xu, Yohwan So, Sanghyuk Woo
Format: Article
Language:English
Published: MDPI AG 2022-12-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/22/23/9391
_version_ 1797462092450627584
author Yanan Xu
Yohwan So
Sanghyuk Woo
author_facet Yanan Xu
Yohwan So
Sanghyuk Woo
author_sort Yanan Xu
collection DOAJ
description Photogrammetric techniques for weakly-textured surfaces without sufficient information about the R (red), G (green) and B (blue) primary colors of light are challenging. Considering that most urban or indoor object surfaces follow simple geometric shapes, a novel method for reconstructing smooth homogeneous planar surfaces based on MVS (Multi-View Stereo) is proposed. The idea behind it is to extract enough features for the image description, and to refine the dense points generated by the depth values of pixels with plane fitting, to favor the alignment of the surface to the detected planes. The SIFT (Scale Invariant Feature Transform) and AKAZE (Accelerated-KAZE) feature extraction algorithms are combined to ensure robustness and help retrieve connections in small samples. The smoothness of the enclosed watertight Poisson surface can be enhanced by enforcing the 3D points to be projected onto the absolute planes detected by a RANSAC (Random Sample Consensus)-based approach. Experimental evaluations of both cloud-to-mesh comparisons in the per-vertex distances with the ground truth models and visual comparisons with a popular mesh filtering based post-processing method indicate that the proposed method can considerably retain the integrity and smoothness of the reconstruction results. Combined with other primitive fittings, the reconstruction extent of homogeneous surfaces can be further extended, serving as primitive models for 3D building reconstruction, and providing guidance for future works in photogrammetry and 3D surface reconstruction.
first_indexed 2024-03-09T17:31:34Z
format Article
id doaj.art-0df2e8f1740d4b7581fa7741e96b654b
institution Directory Open Access Journal
issn 1424-8220
language English
last_indexed 2024-03-09T17:31:34Z
publishDate 2022-12-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj.art-0df2e8f1740d4b7581fa7741e96b654b2023-11-24T12:13:28ZengMDPI AGSensors1424-82202022-12-012223939110.3390/s22239391Plane Fitting in 3D Reconstruction to Preserve Smooth Homogeneous SurfacesYanan Xu0Yohwan So1Sanghyuk Woo2Affiliated Research Institute, Metabank Inc., Daejeon 34430, Republic of KoreaDepartment of Media and Visual Communications, Hannam University, Daejeon 34430, Republic of KoreaDepartment of Media and Visual Communications, Hannam University, Daejeon 34430, Republic of KoreaPhotogrammetric techniques for weakly-textured surfaces without sufficient information about the R (red), G (green) and B (blue) primary colors of light are challenging. Considering that most urban or indoor object surfaces follow simple geometric shapes, a novel method for reconstructing smooth homogeneous planar surfaces based on MVS (Multi-View Stereo) is proposed. The idea behind it is to extract enough features for the image description, and to refine the dense points generated by the depth values of pixels with plane fitting, to favor the alignment of the surface to the detected planes. The SIFT (Scale Invariant Feature Transform) and AKAZE (Accelerated-KAZE) feature extraction algorithms are combined to ensure robustness and help retrieve connections in small samples. The smoothness of the enclosed watertight Poisson surface can be enhanced by enforcing the 3D points to be projected onto the absolute planes detected by a RANSAC (Random Sample Consensus)-based approach. Experimental evaluations of both cloud-to-mesh comparisons in the per-vertex distances with the ground truth models and visual comparisons with a popular mesh filtering based post-processing method indicate that the proposed method can considerably retain the integrity and smoothness of the reconstruction results. Combined with other primitive fittings, the reconstruction extent of homogeneous surfaces can be further extended, serving as primitive models for 3D building reconstruction, and providing guidance for future works in photogrammetry and 3D surface reconstruction.https://www.mdpi.com/1424-8220/22/23/9391weakly-texturedhomogeneous surfaceplane fitting3D reconstruction
spellingShingle Yanan Xu
Yohwan So
Sanghyuk Woo
Plane Fitting in 3D Reconstruction to Preserve Smooth Homogeneous Surfaces
Sensors
weakly-textured
homogeneous surface
plane fitting
3D reconstruction
title Plane Fitting in 3D Reconstruction to Preserve Smooth Homogeneous Surfaces
title_full Plane Fitting in 3D Reconstruction to Preserve Smooth Homogeneous Surfaces
title_fullStr Plane Fitting in 3D Reconstruction to Preserve Smooth Homogeneous Surfaces
title_full_unstemmed Plane Fitting in 3D Reconstruction to Preserve Smooth Homogeneous Surfaces
title_short Plane Fitting in 3D Reconstruction to Preserve Smooth Homogeneous Surfaces
title_sort plane fitting in 3d reconstruction to preserve smooth homogeneous surfaces
topic weakly-textured
homogeneous surface
plane fitting
3D reconstruction
url https://www.mdpi.com/1424-8220/22/23/9391
work_keys_str_mv AT yananxu planefittingin3dreconstructiontopreservesmoothhomogeneoussurfaces
AT yohwanso planefittingin3dreconstructiontopreservesmoothhomogeneoussurfaces
AT sanghyukwoo planefittingin3dreconstructiontopreservesmoothhomogeneoussurfaces