2023

Jump to: 2022, 2021

12 pages, 443 KiB

Open AccessArticle

Three-Dimensional Point Cloud Segmentation Algorithm Based on Depth Camera for Large Size Model Point Cloud Unsupervised Class Segmentation

by Kun Fang, Kaiming Xu, Zhigang Wu, Tengchao Huang and Yubang Yang

Sensors 2024, 24(1), 112; https://doi.org/10.3390/s24010112 - 25 Dec 2023

Viewed by 864

Abstract

This paper proposes a 3D point cloud segmentation algorithm based on a depth camera for large-scale model point cloud unsupervised class segmentation. The algorithm utilizes depth information obtained from a depth camera and a voxelization technique to reduce the size of the point [...] Read more.

This paper proposes a 3D point cloud segmentation algorithm based on a depth camera for large-scale model point cloud unsupervised class segmentation. The algorithm utilizes depth information obtained from a depth camera and a voxelization technique to reduce the size of the point cloud, and then uses clustering methods to segment the voxels based on their density and distance to the camera. Experimental results show that the proposed algorithm achieves high segmentation accuracy and fast segmentation speed on various large-scale model point clouds. Compared with recent similar works, the algorithm demonstrates superior performance in terms of accuracy metrics, with an average Intersection over Union (IoU) of 90.2% on our own benchmark dataset. Full article

► Show Figures

Figure 1

25 pages, 31779 KiB

Open AccessArticle

MoReLab: A Software for User-Assisted 3D Reconstruction

by Arslan Siddique, Francesco Banterle, Massimiliano Corsini, Paolo Cignoni, Daniel Sommerville and Chris Joffe

Sensors 2023, 23(14), 6456; https://doi.org/10.3390/s23146456 - 17 Jul 2023

Viewed by 1562

Abstract

We present MoReLab, a tool for user-assisted 3D reconstruction. This reconstruction requires an understanding of the shapes of the desired objects. Our experiments demonstrate that existing Structure from Motion (SfM) software packages fail to estimate accurate 3D models in low-quality videos due to [...] Read more.

We present MoReLab, a tool for user-assisted 3D reconstruction. This reconstruction requires an understanding of the shapes of the desired objects. Our experiments demonstrate that existing Structure from Motion (SfM) software packages fail to estimate accurate 3D models in low-quality videos due to several issues such as low resolution, featureless surfaces, low lighting, etc. In such scenarios, which are common for industrial utility companies, user assistance becomes necessary to create reliable 3D models. In our system, the user first needs to add features and correspondences manually on multiple video frames. Then, classic camera calibration and bundle adjustment are applied. At this point, MoReLab provides several primitive shape tools such as rectangles, cylinders, curved cylinders, etc., to model different parts of the scene and export 3D meshes. These shapes are essential for modeling industrial equipment whose videos are typically captured by utility companies with old video cameras (low resolution, compression artifacts, etc.) and in disadvantageous lighting conditions (low lighting, torchlight attached to the video camera, etc.). We evaluate our tool on real industrial case scenarios and compare it against existing approaches. Visual comparisons and quantitative results show that MoReLab achieves superior results with regard to other user-interactive 3D modeling tools. Full article

► Show Figures

Figure 1

13 pages, 2688 KiB

Open AccessArticle

Phase Unwrapping Error Correction Based on Multiple Linear Regression Analysis

by Zhuang Lv, Kaifeng Zhu, Xin He, Lei Zhang, Jiawei He, Zhiya Mu, Jun Wang, Xin Zhang and Ruidong Hao

Sensors 2023, 23(5), 2743; https://doi.org/10.3390/s23052743 - 02 Mar 2023

Cited by 3 | Viewed by 1677

Abstract

Fringe projection profilometry (FPP) is prone to phase unwrapping error (PUE) due to phase noise and measurement conditions. Most of the existing PUE-correction methods detect and correct PUE on a pixel-by-pixel or partitioned block basis and do not make full use of the [...] Read more.

Fringe projection profilometry (FPP) is prone to phase unwrapping error (PUE) due to phase noise and measurement conditions. Most of the existing PUE-correction methods detect and correct PUE on a pixel-by-pixel or partitioned block basis and do not make full use of the correlation of all information in the unwrapped phase map. In this study, a new method for detecting and correcting PUE is proposed. First, according to the low rank of the unwrapped phase map, multiple linear regression analysis is used to obtain the regression plane of the unwrapped phase, and thick PUE positions are marked on the basis of the tolerance set according to the regression plane. Then, an improved median filter is used to mark random PUE positions and finally correct marked PUE. Experimental results show that the proposed method is effective and robust. In addition, this method is progressive in the treatment of highly abrupt or discontinuous regions. Full article

► Show Figures

Figure 1

2022

Jump to: 2023, 2021

17 pages, 9563 KiB

Open AccessArticle

An Improved Shape from Focus Method for Measurement of Three-Dimensional Features of Fuel Nozzles

by Liang Hou, Jiahao Zou, Wei Zhang, Yun Chen, Wen Shao, Yuan Li and Shuyuan Chen

Sensors 2023, 23(1), 265; https://doi.org/10.3390/s23010265 - 27 Dec 2022

Cited by 3 | Viewed by 1552

Abstract

The precise three-dimensional measurement of fuel nozzles is of great significance to assess the manufacturing accuracy and improve the spray and atomization performance. This paper proposes an improved fast shape from focus (SFF) method for three-dimensional measurement of key features of fuel nozzles. [...] Read more.

The precise three-dimensional measurement of fuel nozzles is of great significance to assess the manufacturing accuracy and improve the spray and atomization performance. This paper proposes an improved fast shape from focus (SFF) method for three-dimensional measurement of key features of fuel nozzles. In order to ensure the measurement accuracy and efficiency of the SFF, the dispersion of the measured points from a standard flat plane was used to select the optimal combination of the focus measure operator, window size and sampling step size. In addition, an approximate method for the focus measure interval is proposed to improve the measurement efficiency, which uses the peak region of the central pixel to replace the peak region of other pixels. The results show that the proposed method decreased the average computation time of the focus measure by 79.19% for the cone section and by 38.30% for the swirl slot. Compared with a reference laser scanning microscope, the measurement error in length is within 10 μm and the error in angle is within a maximum 0.15°. Full article

► Show Figures

Figure 1

17 pages, 6562 KiB

Open AccessArticle

Study of Texture Indicators Applied to Pavement Wear Analysis Based on 3D Image Technology

by Yutao Li, Yuanhan Qin, Hui Wang, Shaodong Xu and Shenglin Li

Sensors 2022, 22(13), 4955; https://doi.org/10.3390/s22134955 - 30 Jun 2022

Cited by 5 | Viewed by 1435

Abstract

Pavement texture characteristics can reflect early performance decay, skid resistance, and other information. However, most statistical texture indicators cannot express this difference. This study adopts 3D image camera equipment to collect texture data from laboratory asphalt mixture specimens and actual pavement. A pre-processing [...] Read more.

Pavement texture characteristics can reflect early performance decay, skid resistance, and other information. However, most statistical texture indicators cannot express this difference. This study adopts 3D image camera equipment to collect texture data from laboratory asphalt mixture specimens and actual pavement. A pre-processing method was carried out, including data standardisation, slope correction, missing value and outlier processing, and envelope processing. Then the texture data were calculated based on texture separation, texture power spectrum, grey level co-occurrence matrix, and fractal theory to acquire six leading texture indicators and eight extended indicators. The Pearson correlation coefficient was used to analyse the correlation of different texture indicators. The distinction vector based on the information entropy is calculated to analyse the distinction of the indicators. High correlations between ENE (energy) and ENT (entropy), ENT and D (Minkowski dimension) were found. The CON (contrast) has low correlations with HT (macro-texture power spectrum area), ENT and D. However, the differentiation of ENE and HT is more prominent, and the differentiation of the CON is smaller. ENE, ENT, CON and D indicators based on macro-texture and the corresponding original texture have strong linear correlations. However, the microtexture indicators are not linearly correlated with the corresponding original texture indicators. D, WT (micro-texture power spectrum area) and ENT exhibit high degrees of numerical concentration for the same road sections and may be more statistically helpful in distinguishing the characteristics of the pavement performance decay of the road sections. Full article

► Show Figures

Figure 1

11 pages, 4067 KiB

Open AccessArticle

Point-Wise Phase Estimation Method in Fringe Projection Profilometry under Non-Sinusoidal Distortion

by Zhuoyi Yin, Cong Liu, Chuang Zhang, Xiaoyuan He and Fujun Yang

Sensors 2022, 22(12), 4478; https://doi.org/10.3390/s22124478 - 13 Jun 2022

Cited by 1 | Viewed by 1614

Abstract

In fringe projection profilometry, high-order harmonics information of distorted fringe will lead to errors in the phase estimation. In order to solve this problem, a point-wise phase estimation method based on a neural network (PWPE-NN) is proposed in this paper. The complex nonlinear [...] Read more.

In fringe projection profilometry, high-order harmonics information of distorted fringe will lead to errors in the phase estimation. In order to solve this problem, a point-wise phase estimation method based on a neural network (PWPE-NN) is proposed in this paper. The complex nonlinear mapping relationship between the gray values and the phase under non-sinusoidal distortion is constructed by using the simple neural network model. It establishes a novel implicit expression for phase solution without complicated measurement operations. Compared with the previous method of combining local image information, it can accurately calculate each phase value by point. The comparison results show that the traditional method is with periodic phase errors, while the proposed method can effectively eliminate phase errors caused by non-sinusoidal phase shifting. Full article

► Show Figures

Figure 1

15 pages, 13618 KiB

Open AccessArticle

Dental Implant Navigation System Based on Trinocular Stereo Vision

by Songlin Bi, Menghao Wang, Jiaqi Zou, Yonggang Gu, Chao Zhai and Ming Gong

Sensors 2022, 22(7), 2571; https://doi.org/10.3390/s22072571 - 27 Mar 2022

Cited by 5 | Viewed by 3464

Abstract

Traditional dental implant navigation systems (DINS) based on binocular stereo vision (BSV) have limitations, for example, weak anti-occlusion abilities, as well as problems with feature point mismatching. These shortcomings limit the operators’ operation scope, and the instruments may even cause damage to the [...] Read more.

Traditional dental implant navigation systems (DINS) based on binocular stereo vision (BSV) have limitations, for example, weak anti-occlusion abilities, as well as problems with feature point mismatching. These shortcomings limit the operators’ operation scope, and the instruments may even cause damage to the adjacent important blood vessels, nerves, and other anatomical structures. Trinocular stereo vision (TSV) is introduced to DINS to improve the accuracy and safety of dental implants in this study. High positioning accuracy is provided by adding cameras. When one of the cameras is blocked, spatial positioning can still be achieved, and doctors can adjust to system tips; thus, the continuity and safety of the surgery is significantly improved. Some key technologies of DINS have also been updated. A bipolar line constraint algorithm based on TSV is proposed to eliminate the feature point mismatching problem. A reference template with active optical markers attached to the jaw measures head movement. A T-type template with active optical markers is used to obtain the position and direction of surgery instruments. The calibration algorithms of endpoint, axis, and drill are proposed for 3D display of the surgical instrument in real time. With the preoperative path planning of implant navigation software, implant surgery can be carried out. Phantom experiments are carried out based on the system to assess the feasibility and accuracy. The results show that the mean entry deviation, exit deviation, and angle deviation are 0.55 mm, 0.88 mm, and 2.23 degrees, respectively. Full article

► Show Figures

Figure 1

23 pages, 7742 KiB

Open AccessArticle

Accurate Real-Time Localization Estimation in Underground Mine Environments Based on a Distance-Weight Map (DWM)

by Zhuli Ren and Liguan Wang

Sensors 2022, 22(4), 1463; https://doi.org/10.3390/s22041463 - 14 Feb 2022

Cited by 12 | Viewed by 2596

Abstract

The precise localization of an underground mine environment is key to achieving unmanned and intelligent underground mining. However, in an underground environment, GPS is unavailable, there are variable and often poor lighting conditions, there is visual aliasing in long tunnels, and the occurrence [...] Read more.

The precise localization of an underground mine environment is key to achieving unmanned and intelligent underground mining. However, in an underground environment, GPS is unavailable, there are variable and often poor lighting conditions, there is visual aliasing in long tunnels, and the occurrence of airborne dust and water, presenting great difficulty for localization. We demonstrate a high-precision, real-time, without-infrastructure underground localization method based on 3D LIDAR. The underground mine environment map was constructed based on GICP-SLAM, and inverse distance weighting (IDW) was first proposed to implement error correction based on point cloud mapping called a distance-weight map (DWM). The map was used for the localization of the underground mine environment for the first time. The approach combines point cloud frames matching and DWM matching in an unscented Kalman filter fusion process. Finally, the localization method was tested in four underground scenes, where a spatial localization error of 4 cm and 60 ms processing time per frame were obtained. We also analyze the impact of the initial pose and point cloud segmentation with respect to localization accuracy. The results showed that this new algorithm can realize low-drift, real-time localization in an underground mine environment. Full article

► Show Figures

Figure 1

25 pages, 37544 KiB

Open AccessArticle

sSfS: Segmented Shape from Silhouette Reconstruction of the Human Body

by Wiktor Krajnik, Łukasz Markiewicz and Robert Sitnik

Sensors 2022, 22(3), 925; https://doi.org/10.3390/s22030925 - 25 Jan 2022

Cited by 2 | Viewed by 3385

Abstract

Three-dimensional (3D) shape estimation of the human body has a growing number of applications in medicine, anthropometry, special effects, and many other fields. Therefore, the demand for the high-quality acquisition of a complete and accurate body model is increasing. In this paper, a [...] Read more.

Three-dimensional (3D) shape estimation of the human body has a growing number of applications in medicine, anthropometry, special effects, and many other fields. Therefore, the demand for the high-quality acquisition of a complete and accurate body model is increasing. In this paper, a short survey of current state-of-the-art solutions is provided. One of the most commonly used approaches is the Shape-from-Silhouette (SfS) method. It is capable of the reconstruction of dynamic and challenging-to-capture objects. This paper proposes a novel approach that extends the conventional voxel-based SfS method with silhouette segmentation—segmented Shape from Silhouette (sSfS). It allows the 3D reconstruction of body segments separately, which provides significantly better human body shape estimation results, especially in concave areas. For validation, a dataset representing the human body in 20 complex poses was created and assessed based on the quality metrics in reference to the ground-truth photogrammetric reconstruction. It appeared that the number of invalid reconstruction voxels for the sSfS method was 1.7 times lower than for the state-of-the-art SfS approach. The root-mean-square (RMS) error of the distance to the reference surface was also 1.22 times lower. Full article

► Show Figures

Figure 1

23 pages, 14407 KiB

Open AccessArticle

Selection of Methods of Surface Texture Characterisation for Reduction of the Frequency-Based Errors in the Measurement and Data Analysis Processes

by Przemysław Podulka

Sensors 2022, 22(3), 791; https://doi.org/10.3390/s22030791 - 20 Jan 2022

Cited by 20 | Viewed by 2618

Abstract

Processes of surface texture characterisation can be roughly divided into measurement issues and analysis of the results obtained. Both actions can be fraught with various errors, some of which can be analysed with frequency performance. In this paper, various types of surface topographies [...] Read more.

Processes of surface texture characterisation can be roughly divided into measurement issues and analysis of the results obtained. Both actions can be fraught with various errors, some of which can be analysed with frequency performance. In this paper, various types of surface topographies were studied, e.g., cylinder liners after the plateau-honing process, plateau-honed liners with additionally burnished dimples of various sizes (width and depth), turned, milled, ground, laser-textured, ceramic, composite and some general isotropic topographies, respectively. They were measured with a stylus or via optical (white light interferometry) methods. They were analysed with frequency-based methods, proposed in often applied measuring equipment, e.g., power spectral density, autocorrelation function and spectral analysis. All of the methods were supported by regular (commonly used) algorithms, or filters with (robust) Gaussian, median, spline or Fast Fourier Transform performance, respectively. The main purpose of the paper was to use regular techniques for the improvement of detection and reduction processes regarding the influence of high-frequency noise on the results of surface texture measurements. It was found that for selected types of surface textures, profile (2D) analysis gave more confidential results than areal (3D) characterisation. It was therefore suggested to detect and remove frequency-defined errors with a multi-threaded performance application. In the end, some guidance on how to use regular methods in the analysis of selected types of surface topographies following the reduction of both measurement (high-frequency noise) and data analysis errors was required. Full article

► Show Figures

Figure 1

2021

Jump to: 2023, 2022

14 pages, 7567 KiB

Open AccessArticle

Multi-Incidence Holographic Profilometry for Large Gradient Surfaces with Sub-Micron Focusing Accuracy

by Moncy Sajeev Idicula, Tomasz Kozacki, Michal Józwik, Patryk Mitura, Juan Martinez-Carranza and Hyon-Gon Choo

Sensors 2022, 22(1), 214; https://doi.org/10.3390/s22010214 - 29 Dec 2021

Cited by 5 | Viewed by 1582

Abstract

Surface reconstruction for micro-samples with large discontinuities using digital holography is a challenge. To overcome this problem, multi-incidence digital holographic profilometry (MIDHP) has been proposed. MIDHP relies on the numerical generation of the longitudinal scanning function (LSF) for reconstructing the topography of the [...] Read more.

Surface reconstruction for micro-samples with large discontinuities using digital holography is a challenge. To overcome this problem, multi-incidence digital holographic profilometry (MIDHP) has been proposed. MIDHP relies on the numerical generation of the longitudinal scanning function (LSF) for reconstructing the topography of the sample with large depth and high axial resolution. Nevertheless, the method is unable to reconstruct surfaces with large gradients due to the need of: (i) high precision focusing that manual adjustment cannot fulfill and (ii) preserving the functionality of the LSF that requires capturing and processing many digital holograms. In this work, we propose a novel MIDHP method to solve these limitations. First, an autofocusing algorithm based on the comparison of shapes obtained by the LSF and the thin tilted element approximation is proposed. It is proven that this autofocusing algorithm is capable to deliver in-focus plane localization with submicron resolution. Second, we propose that wavefield summation for the generation of the LSF is carried out in Fourier space. It is shown that this scheme enables a significant reduction of arithmetic operations and can minimize the number of Fourier transforms needed. Hence, a fast generation of the LSF is possible without compromising its accuracy. The functionality of MIDHP for measuring surfaces with large gradients is supported by numerical and experimental results. Full article

► Show Figures

Figure 1

18 pages, 29799 KiB

Open AccessArticle

Determining Surface Shape of Translucent Objects with the Combination of Laser-Beam-Based Structured Light and Polarization Technique

by Bingquan Chen, Peng Shi, Yanhua Wang, Yongze Xu, Hongyang Ma, Ruirong Wang, Chunhong Zheng and Pengcheng Chu

Sensors 2021, 21(19), 6587; https://doi.org/10.3390/s21196587 - 01 Oct 2021

Cited by 2 | Viewed by 2096

Abstract

In this study, we focus on the 3D surface measurement and reconstruction of translucent objects. The proposed approach of surface-shape determination of translucent objects is based on the combination of the projected laser-beam-based sinusoidal structured light and the polarization technique. The theoretical analyses [...] Read more.

In this study, we focus on the 3D surface measurement and reconstruction of translucent objects. The proposed approach of surface-shape determination of translucent objects is based on the combination of the projected laser-beam-based sinusoidal structured light and the polarization technique. The theoretical analyses are rigorously completed in this work, including the formation, propagation, and physical features of the generated sinusoidal signal by the designed optical system, the reflection and transmission of the projected monochromatic fringe pattern on the surface of the translucent object, and the formation and the separation of the direct-reflection and the global components of the surface radiance of the observed object. The results of experimental investigation designed in accordance with our theoretical analyses have confirmed that accurate reconstructions can be obtained using the one-shot measurement based on the proposed approach of this study and Fourier transform profilometry, while the monochromaticity and the linearly-polarized characteristic of the projected sinusoidal signal can be utilized by using a polarizer and an optical filter simultaneously for removing the global component, i.e., the noised signal contributed by multiply-scattered photons and the background illuminance in the frame of our approach. Moreover, this study has also revealed that the developed method is capable of getting accurate measurements and reconstructions of translucent objects when the background illumination exists, which has been considered as a challenging issue for 3D surface measurement and reconstruction of translucent objects. Full article

► Show Figures

Figure 1

18 pages, 32774 KiB

Open AccessArticle

Digital Hologram Watermarking Based on Multiple Deep Neural Networks Training Reconstruction and Attack

by Ji-Won Kang, Jae-Eun Lee, Jang-Hwan Choi, Woosuk Kim, Jin-Kyum Kim, Dong-Wook Kim and Young-Ho Seo

Sensors 2021, 21(15), 4977; https://doi.org/10.3390/s21154977 - 22 Jul 2021

Cited by 2 | Viewed by 2788

Abstract

This paper proposes a method to embed and extract a watermark on a digital hologram using a deep neural network. The entire algorithm for watermarking digital holograms consists of three sub-networks. For the robustness of watermarking, an attack simulation is inserted inside the [...] Read more.

This paper proposes a method to embed and extract a watermark on a digital hologram using a deep neural network. The entire algorithm for watermarking digital holograms consists of three sub-networks. For the robustness of watermarking, an attack simulation is inserted inside the deep neural network. By including attack simulation and holographic reconstruction in the network, the deep neural network for watermarking can simultaneously train invisibility and robustness. We propose a network training method using hologram and reconstruction. After training the proposed network, we analyze the robustness of each attack and perform re-training according to this result to propose a method to improve the robustness. We quantitatively evaluate the results of robustness against various attacks and show the reliability of the proposed technique. Full article

► Show Figures

Figure 1

Journal Menu

Journal Browser

3D/4D Optical Imaging Sensors for Surface Measurement, Processing and Applications

Share This Topical Collection

Editor

Topical Collection Information

Keywords

Published Papers (13 papers)

2023

Jump to: 2022, 2021

2022

Jump to: 2023, 2021

2021

Jump to: 2023, 2022

Further Information

Guidelines

MDPI Initiatives

Follow MDPI