Efficiently registering scan point clouds of 3D printed parts for shape accuracy assessment and modeling

Decker, Nathan; Wang, Yuanxiang; Huang, Qiang

doi:10.1016/j.jmsy.2020.04.001

Cited by 30 publications

(6 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 3D reconstruction and face modeling, binocular stereo vision has been used more often, which can quickly acquire 3D coordinates and does not require human intervention, so it has better results in 3D face recognition and reconstruction. However, in the face modeling process, some face regions do not have obvious features and are difficult to recognize, so it is not only difficult to match effectively by directly applying the grayscale similarity principle [25] but also difficult to create models, so this paper uses two different methods, specifically: the extraction of the main feature points of the left and right faces is completed by the ASM algorithm, the initial parallax map is clarified, and then, the adaptive parallax map is improved and adjusted by using the filtering algorithm. The feature points obtained by the extraction algorithm may have offset coordinates and inaccurate feature point positions, and face alignment can be used as a method to optimize the facial feature extraction results.…”

Section: Binocular Stereo Visionmentioning

confidence: 99%

A 3D Face Modeling and Recognition Method Based on Binocular Stereo Vision and Depth-Sensing Detection

et al. 2022

View full text Add to dashboard Cite

The human face is an important channel for human interaction and is the most expressive part of the human body with personalized and diverse characteristics. To improve the modeling speed as well as recognition speed and accuracy of 3D faces, this paper proposes a laser scanning binocular stereo vision imaging method based on binocular stereo vision and depth-sensing detection method. Existing matching methods have a weak anti-interference capability, cannot identify the spacing of objects quickly and efficiently, and have too large errors. Using the technique mentioned in this paper can remedy these shortcomings by mainly using the laser lines scanned onto the object as strong feature cues for left and right views for binocular vision matching and thus for depth measurement perception of the object. The experiments in this paper first explore the effect of parameter variation of the laser scanning binocular vision imaging system on the accuracy of object measurement depth values in an indoor environment; the experimental data are selected from 68 face feature points for modeling, cameras that photograph faces, stereo calibration of the cameras using calibration methods to obtain the parameters of the binocular vision imaging system, and after stereo correction of the left and right camera images, the laser line scan light is used as a pixel matching strong features for binocular camera matching, which can achieve fast recognition and high accuracy and then select the system parameters with the highest accuracy to perform 3D reconstruction experiments on actual target objects in the indoor environment to achieve faster recognition.

show abstract

Section: Binocular Stereo Visionmentioning

confidence: 99%

A 3D Face Modeling and Recognition Method Based on Binocular Stereo Vision and Depth-Sensing Detection

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Aligning the captured point clouds with their CAD models is often done using the standard ICP method in the literature. [4,[24][25][26]. However, this typically involves using a (fully) scanned template model [24,26,27], instead of sampling from a CAD model.…”

Section: Introductionmentioning

confidence: 99%

Comparison of Point Cloud Registration Techniques on Scanned Physical Objects

Denayer,

De Winter,

Bernardes

et al. 2024

Sensors

View full text Add to dashboard Cite

This paper presents a comparative analysis of six prominent registration techniques for solving CAD model alignment problems. Unlike the typical approach of assessing registration algorithms with synthetic datasets, our study utilizes point clouds generated from the Cranfield benchmark. Point clouds are sampled from existing CAD models and 3D scans of physical objects, introducing real-world complexities such as noise and outliers. The acquired point cloud scans, including ground-truth transformations, are made publicly available. This dataset includes several cleaned-up scans of nine 3D-printed objects. Our main contribution lies in assessing the performance of three classical (GO-ICP, RANSAC, FGR) and three learning-based (PointNetLK, RPMNet, ROPNet) methods on real-world scans, using a wide range of metrics. These include recall, accuracy and computation time. Our comparison shows a high accuracy for GO-ICP, as well as PointNetLK, RANSAC and RPMNet combined with ICP refinement. However, apart from GO-ICP, all methods show a significant number of failure cases when applied to scans containing more noise or requiring larger transformations. FGR and RANSAC are among the quickest methods, while GO-ICP takes several seconds to solve. Finally, while learning-based methods demonstrate good performance and low computation times, they have difficulties in training and generalizing. Our results can aid novice researchers in the field in selecting a suitable registration method for their application, based on quantitative metrics. Furthermore, our code can be used by others to evaluate novel methods.

show abstract

“…With the number of 3D printers rapidly increasing [1,2], it has created an increases demand for developing tools and methods to evaluate their capabilities and limitations [3]. For evaluating a 3D printer, printing accuracy is one of the most critical performance metrics [4,5].…”

Section: Introductionmentioning

confidence: 99%

An error identification and compensation method for Cartesian 3D printer based on specially designed test artifact

Li²,

Ding³

et al. 2023

Int J Adv Manuf Technol

View full text Add to dashboard Cite

The printing accuracy is one of the most important metrics to evaluate the additive manufacturing (AM) machine. In this paper, an error identification and compensation method for Cartesian 3D printer is presented based on a specially-designed test artifact to improve printing accuracy. The relationship between the geometric errors of the printed object and the kinematic errors of the printer axes is established based on the theory of the multi-body system. A series of formulas are derived to separate the kinematic errors of each axis from the geometric errors. To extract the geometric errors required for the mathematical calculations, an artifact with the special features is proposed and printed. The geometric errors of the characteristic points on the artifact is measured by a coordinate measuring machine (CMM). From the measured geometric errors, kinematic errors of the printer can be identified, and can be further compensated by adjusting the CAD model of the object. Two compensated algorithms are established; one uses the fitted curves of the kinematic errors, and the other uses the average kinematic error values. Printing tests and case studies are performed to verify the effectiveness of the proposed method. The results show that the proposed method can improve printing accuracy of the Cartesian 3D printer.

show abstract

Efficiently registering scan point clouds of 3D printed parts for shape accuracy assessment and modeling

Cited by 30 publications

References 35 publications

A 3D Face Modeling and Recognition Method Based on Binocular Stereo Vision and Depth-Sensing Detection

A 3D Face Modeling and Recognition Method Based on Binocular Stereo Vision and Depth-Sensing Detection

Comparison of Point Cloud Registration Techniques on Scanned Physical Objects

An error identification and compensation method for Cartesian 3D printer based on specially designed test artifact

Contact Info

Product

Resources

About