Robust 3D point cloud registration based on bidirectional Maximum Correntropy Criterion

Robust affine registration method using line/surface normals and correntropy criterion

The problem of matching point clouds is an efficient way of registration, which is significant for many research fields including computer vision, machine learning, and robotics. There may be linear or non-linear transformation between point clouds, but determining the affine relation is more challenging among linear cases. Various methods have been presented to overcome this problem in the literature and one of them is the affine variant of the iterative closest point (ICP) algorithm. However, traditional affine ICP variants are highly sensitive to effects such as noises, deformations, and outliers; the least-square metric is substituted with the correntropy criterion to increase the robustness of ICPs to such effects. Correntropy-based robust affine ICPs available in the literature use point-to-point metric to estimate transformation between point clouds. Conversely, in this study, a line/surface normal that examines point-to-curve or point-to-plane distances is employed together with the correntropy criterion for affine point cloud registration problems. First, the maximum correntropy criterion measure is built for line/surface normal conditions. Then, the closed-form solution that maximizes the similarity between point sets is achieved for 2D registration and extended for 3D registration. Finally, the application procedure of the developed robust affine ICP method is given and its registration performance is examined through extensive experiments on 2D and 3D point sets. The results achieved highlight that our method can align point clouds more robustly and precisely than the state-of-the-art methods in the literature, while the registration time of the process remains at reasonable levels.

A novel visualization system of using augmented reality in knee replacement surgery: Enhanced bidirectional maximum correntropy algorithm

BACKGROUND AND AIM

Image registration and alignment are the main limitations of augmented reality (AR)-based knee replacement surgery. This research aims to decrease the registration error, eliminate outcomes that are trapped in local minima to improve the alignment problems, handle the occlusion and maximize the overlapping parts.

METHODOLOGY

Markerless image registration method was used for AR-based knee replacement surgery to guide and visualize the surgical operation. While weight least square algorithm was used to enhance stereo camera-based tracking by filling border occlusion in right-to-left direction and non-border occlusion from left-to-right direction.

RESULTS

This study has improved video precision to 0.57-0.61 mm alignment error. Furthermore, with the use of bidirectional points, that is, forward and backward directional cloud point, the iteration on image registration was decreased. This has led to improve the processing time as well. The processing time of video frames was improved to 7.4-11.74 frames per second.

CONCLUSIONS

It seems clear that this proposed system has focused on overcoming the misalignment difficulty caused by the movement of patient and enhancing the AR visualization during knee replacement surgery. The proposed system was reliable and favourable which helps in eliminating alignment error by ascertaining the optimal rigid transformation between two cloud points and removing the outliers and non-Gaussian noise. The proposed AR system helps in accurate visualization and navigation of anatomy of knee such as femur, tibia, cartilage, blood vessels and so forth.

Measurement accuracy of 3-Dimensional mapping technologies versus standard goniometry for angle assessment

BACKGROUND

A specific aspect of the hypospadias phenotype that may contribute to long-term outcomes is the presence of ventral penile curvature and the adequacy of its surgical correction. The current gold standard to assess this angle is intraoperative goniometry of an erect penis. 3-dimensional (3D) mapping technologies may overcome the limitations of these traditional methods through their combination of digital image and geometric replication to produce consistent 3D digital forms of a physical structure. The aim of this study is to evaluate the measurement accuracy and reliability of handheld 3D mapping technologies versus standard goniometry for angle assessment in a laboratory setting.

METHODS

Blocks with specified angles (10-45°) were printed using a Zortrax M200 3D printer (±0.2% accuracy). Following the completion of standardized training, blinded participants measured each block angle using a baseline digit goniometer. Additionally, complete digital models of the blocks were created using 3D mapping technologies. Structured light scanning was completed using an Artec Space Spider and Artec Studio 13. Traditional photogrammetry was completed using a Canon Eos Rebel T5i DSLR camera and Agisoft Metashape Pro. Photogrammetry with a 3D camera was completed using the VECTRA H1 and VECTRA Analysis Module. All 3D models were imported into the software Autodesk Inventor in which automated angle measurements through the central plane were obtained. Statistical analysis was performed to determine the accuracy, precision and reliability of each modality using SAS 9.4 software. The reliability of goniometry and each mapping technology was evaluated using two-way random effect models with absolute agreement.

RESULTS

Six 3D printed blocks were evaluated. 5 digital models per block were created using each of the 3 mapping technologies. Inter-rater reliability of goniometry was moderate (ICC 0.76, 95% CI 0.46, 0.92), whereas all mapping technologies demonstrated excellent test-retest reliability: structured light scanning (ICC 0.99; 95% CI 0.999, 0.999); traditional photogrammetry (0.99; 0.99, 0.99); 3D camera (0.99; 0.99, 0.99). Mean angle measurements and standard error for each angle and modality are provided in the table.

CONCLUSIONS

This study demonstrated excellent accuracy, precision and reliability of off-the-shelf, handheld 3D mapping technologies and moderate reliability for goniometry when applied to measurements of angulation in a laboratory setting. The described methods developed in the laboratory for optimization of angle analysis from 3D models are an important step toward reliable, reproducible phenotypic analysis of congenital genitourinary conditions in future intraoperative and database development applications.

Multi-view registration of unordered range scans by fast correspondence propagation of multi-scale descriptors

This paper proposes a global approach for the multi-view registration of unordered range scans. Our method starts with the pair-wise registration, where multi-scale descriptor is selected for feature point and the propagation of feature correspondence is accordingly accelerated. Subsequently, we design an effective rule to judge the reliability of these pair-wise registration results. According to the judgment of reliability, we propose a model fusion method, which can utilize reliable results of pair-wise registration to augment the model shape. Finally, multi-view registration can be achieved by operating the pair-wise registration, reliability judgment, and model fusion alternately. The proposed approach can be applied to scene reconstruction and robot mapping. Experimental results conducted on public datasets show that the proposed approach can automatically achieve multi-view registration of unordered range scans. Compared with other related approaches, the proposed approach has superior performances in accuracy and effectiveness.