Stein ICP for Uncertainty Estimation in Point Cloud Matching

Maken, Fahira Afzal; Ramos, Fábio; Ott, Lionel

doi:10.1109/lra.2021.3137503

Cited by 19 publications

(12 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it encounters challenges when dealing with complex geometries featuring low overlap or significant displacements, primarily due to the difficulty in finding reasonable correspondences via closest point search. Consequently, numerous ICP variants have been proposed to address these issues, including various designs concerning correspondence matching [17,18], objective functions [11,19], and robust kernels [20]. In the context of our system's rigid registration thread, we leverage geometric features such as normals and curvatures to enhance correspondence matching, as demonstrated in prior work [11].…”

Section: Rigid Registrationmentioning

confidence: 99%

PatchFusion: Patch-based Nonrigid Tracking and Reconstruction of Deformable Objects using a Single RGB-D Sensor

Zhao,

Yu,

2024

Preprint

View full text Add to dashboard Cite

This paper introduces PatchFusion, an innovative approach for nonrigid tracking and reconstruction of deformable objects using a single RGB-D sensor. Existing methods face challenges in accurately capturing the rapid deformations of soft and flexible objects, thereby limiting their utility in diverse scenarios. Our approach overcomes this challenge by employing a dynamic patch-based framework that adapts to rapid inter-frame motions. Firstly, patch-wise rigid transformation fields for non-overlapping patches are solved via Iterative Closest Point (ICP) by incorporating geometric features as additional similarity constraints, thereby enhancing robustness and accuracy. Secondly, deformation optimization based on a nonrigid solver is applied to refine the coarse transformation fields. In order to enable simultaneous tracking and reconstruction of deformable objects, the patch-based rigid solver is designed to run in parallel with the nonrigid solver, serving as a plug-and-play module requiring minimal modifications for integration while enabling real-time performance. Following a comprehensive evaluation, PatchFusion showcases superior performance in effectively dealing with rapid inter-frame deformations when compared to existing techniques, rendering it a promising solution with broad applicability across domains such as robotics, computer vision, and human-computer interaction.

show abstract

Section: Rigid Registrationmentioning

confidence: 99%

PatchFusion: Patch-based Nonrigid Tracking and Reconstruction of Deformable Objects using a Single RGB-D Sensor

Zhao,

Yu,

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Therefore, it is necessary to photograph the point cloud at the missing corner and extract local features for matching calculation. Figure 4(d-f) show the iterative closest point (ICP) [9] matching effect of the corresponding local feature point cloud, both of which have better matching effect. Figure 4(g-i) show the point cloud matching effect obtained by point pair feature (PPF) [10][11] method.…”

Section: Point Cloud Matching Experimentsmentioning

confidence: 99%

Robot grasping detection technology based on 3D structured light

Zhang

Chen

et al. 2023

International Conference on Optical and Photonic Engineering (icOPEN 2022)

View full text Add to dashboard Cite

With the development of robot technology, automatic assembly technology based on industrial robots has been greatly applied. Considering the high-precision automatic grasping of heterogeneous products, robot grasping detection technology is put forward. Although the current method of using camera is relatively mature, it is greatly affected by the ambient light and the surface material of the object, resulting in the limited versatility. Since the 3D structured light method based on the laser scanning galvanometer has the characteristics of high speed and high accuracy, strong environmental adaptability and weak influence by the surface material of the object, the structured light equipment using laser scanning galvanometer was installed at the end of the robot to realize the grasping detection of the products. Through hand eye calibration, point cloud acquisition, point cloud processing, point cloud matching and other links, the point cloud collection and accurate matching of local features are realized. The experiment shows that the grasping detection accuracy is less than 0.32mm. It can not only achieve accurate grasping of different products, but also has the characteristics of strong adaptability to surface materials, environmental lighting, and high accuracy.

show abstract

“…However, the algorithm has a low accuracy of the pose estimation when the uncertainty of the prior estimation of the system is high, and the numerical stability is not high. The pose calibration method can also utilize the point cloud registration algorithm of LiDAR, and the commonly used algorithm is the iterative closest point (ICP) algorithm [8], which can accurately find the conversion relationship between two radar scans. However, when the sample size of the point set is too large, the ICP algorithm will waste computational resources.…”

Section: Introductionmentioning

confidence: 99%

L-PCM: Localization and Point Cloud Registration-Based Method for Pose Calibration of Mobile Robots

Ning,

Huang

2024

Information

View full text Add to dashboard Cite

The autonomous navigation of mobile robots contains three parts: map building, global localization, and path planning. Precise pose data directly affect the accuracy of global localization. However, the cumulative error problems of sensors and various estimation strategies cause the pose to have a large gap in data accuracy. To address these problems, this paper proposes a pose calibration method based on localization and point cloud registration, which is called L-PCM. Firstly, the method obtains the odometer and IMU (inertial measurement unit) data through the sensors mounted on the mobile robot and uses the UKF (unscented Kalman filter) algorithm to filter and fuse the odometer data and IMU data to obtain the estimated pose of the mobile robot. Secondly, the AMCL (adaptive Monte Carlo localization) is improved by combining the UKF fusion model of the IMU and odometer to obtain the modified global initial pose of the mobile robot. Finally, PL-ICP (point to line-iterative closest point) point cloud registration is used to calibrate the modified global initial pose to obtain the global pose of the mobile robot. Through simulation experiments, it is verified that the UKF fusion algorithm can reduce the influence of cumulative errors and the improved AMCL algorithm can optimize the pose trajectory. The average value of the position error is about 0.0447 m, and the average value of the angle error is stabilized at about 0.0049 degrees. Meanwhile, it has been verified that the L-PCM is significantly better than the existing AMCL algorithm, with a position error of about 0.01726 m and an average angle error of about 0.00302 degrees, effectively improving the accuracy of the pose.

show abstract

Stein ICP for Uncertainty Estimation in Point Cloud Matching

Cited by 19 publications

References 47 publications

PatchFusion: Patch-based Nonrigid Tracking and Reconstruction of Deformable Objects using a Single RGB-D Sensor

PatchFusion: Patch-based Nonrigid Tracking and Reconstruction of Deformable Objects using a Single RGB-D Sensor

Robot grasping detection technology based on 3D structured light

L-PCM: Localization and Point Cloud Registration-Based Method for Pose Calibration of Mobile Robots

Contact Info

Product

Resources

About