A Review of Fine Registration for 3D Point Clouds

Xian, Yaru; Xiao, Jun; Wang, Ying; Shan, Mengyi; Zhou, Chong

doi:10.2991/icamcs-16.2016.21

Cited by 3 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The NDT algorithm is another popular rigid registration method in computer vision, 3D modeling, and robotic science. 15 , 27 , 28 Because NDT uses a set of distributions transformed from a set of points without searching for the nearest neighbor, there are reports in computer vision and robotics that it has faster computation times and higher accuracy than the ICP method. 20 , 29 , 30 , 31 However, few studies have used the NDT registration algorithm in the OSI system.…”

Section: Discussionmentioning

confidence: 99%

“…Although the ICP method is easily implemented, this technique is computationally expensive or has low accuracy owing to the nearest point calculation. The NDT algorithm is another popular rigid registration method in computer vision, 3D modeling, and robotic science 15,27,28 . Because NDT uses a set of distributions transformed from a set of points without searching for the nearest neighbor, there are reports in computer vision and robotics that it has faster computation times and higher accuracy than the ICP method 20,29–31 .…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Accuracy evaluation of surface registration algorithm using normal distribution transform in stereotactic body radiotherapy/radiosurgery: A phantom study

Lee

Park

Kim

et al. 2022

J Applied Clin Med Phys

View full text Add to dashboard Cite

Purpose To evaluate a feasibility of normal distribution transform (NDT) algorithm compared with the iterative closest point (ICP) method as a useful surface registration in stereotactic body radiotherapy (SBRT)/stereotactic radiosurgery (SRS). Methods Point cloud images using the 3D triangulation technology were obtained from a depth camera‐based optical imaging (OSI) system equipped in a radiosurgery room. Two surface registration algorithms, NDT and ICP, were used to measure and compare the discrepancy values between the reference and the current surfaces during the positioning of the patient. The performance evaluation was investigated by calculating the registration error and root‐mean‐square (RMS) values for the surface model, reposition, and target accuracy, which were analyzed statistically using a paired t‐test. Results For surface model accuracy, the average of the registration error and RMS values were measured as 3.56 ± 2.20 mm and 6.98 ± 1.89 mm for ICP method, and 1.76 ± 1.32 mm and 3.58 ± 1.30 mm for NDT method (p < 0.05). For reposition accuracy, the average registration error and RMS values were calculated as 1.41 ± 0.98 mm and 2.53 ± 1.64 mm using ICP method, and 0.92 ± 0.61 mm and 1.75 ± 0.80 mm using NDT method (p = 0.005). The overall target accuracy using the NDT method reduced the average of the reposition error and overall RMS value by 0.71 and 1.32 mm, respectively, compared to the ICP method (p = 0.03). Conclusions We found that the surface registration algorithm based on NDT method provides more reliable accuracy in the values of surface model, reposition, and target accuracies than the classic ICP method. The NDT method in OSI systems offers reasonable accuracy in SBRT/SRS.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Accuracy evaluation of surface registration algorithm using normal distribution transform in stereotactic body radiotherapy/radiosurgery: A phantom study

Lee

Park

Kim

et al. 2022

J Applied Clin Med Phys

View full text Add to dashboard Cite

show abstract

“…Better results can be obtained afterwards. The basic principle of ICP is: first obtain the feature points of two point sets, perform data matching according to the feature points, and set these matching points as imaginary corresponding points, then solve the motion parameters according to this correspondence relationship, and finally use these parameters for data Conversion [9][10] . In simple terms, the ICP algorithm is to minimize the objective function S2 through the corresponding points.…”

Section: Multi-source Data Fusion Technologymentioning

confidence: 99%

Building 3D Realistic Modeling Based on Air-ground Multi-source Data Fusion

Wang¹,

Zhang²,

Wang³

2020

E3S Web Conf.

View full text Add to dashboard Cite

Three-dimensional point cloud data is a new form of three-dimensional collection, which not only contains the geometric topology information of the object, but also has high simplicity and flexibility. In this paper, the air-ground multi-source data fusion technology is used to study the fine reconstruction of the 3D scene: based on the 3D laser scanning laser point cloud, the 3D spatial information of the ground visible objects is obtained, and the orthophoto obtained by the drone aerial photography is assisted, Obtain the three-dimensional space information of the top of the ground feature, and the ground three-dimensional laser scanner can quickly obtain the three-dimensional surface information of the building facade, ground, and trees. Due to the complex structure of the building and the occlusion of spatial objects, sub-station scanning is required when acquiring point cloud data. This article uses the Sino-German Energy Conservation Center Building of Shenyang Jianzhu University as the research area, using drone tilt photography technology and ground lidar technology to integrate. During the experiment, the field industry adopted the UAV image acquisition strategy of “automatic shooting of regular routes, supplemented by manual shooting of areas of interest”; in the field industry, the method of “manual coarse registration and ICP algorithm fine registration” The example results show that the ground 3D laser point cloud air-ground image fusion 3D modeling effect proposed in this paper is better and the quality is greatly improved, which makes up for the ground 3D laser scanning. In point cloud modeling, a large number of holes are insufficient due to occlusion and missing top information.

show abstract