Correspondence matching in unorganized 3D point clouds using Convolutional Neural Networks

Pujol-Miro, Alba; Casas, Josep R.; Ruiz-Hidalgo, Javier

doi:10.1016/j.imavis.2019.02.013

Cited by 15 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e new method of combining two data spaces proposed by Saval-CalvoM is very novel, which is of great help to image recognition, but the application of visual sensors is not adequate. Pujol-MiroA proposed a new method based on a convolutional neural network (CNN), which can obtain the corresponding matching between the key point sets captured by multiple unorganized 3D point clouds independent of the sensors used [3]. e CNN method He proposed is very good at capturing 3D features, but the acceptance of it is a bit lagging behind.…”

Section: Introductionmentioning

confidence: 99%

3D Image Based on Visual Sensor in Public Space Landscape Model

Liu¹

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

With the rapid development of the times, the computing of the internet of things and the industry go hand in hand, the application of visual sensors is becoming more and more extensive, and the image fusion technology and target recognition technology have been further improved. It can be said that it is a hot topic at home and abroad high-end technology. With the continuous improvement of people’s living standards, the specific requirements for the quality of life are gradually increasing. The landscape construction of public space has become a topic of discussion. People are becoming more and more stringent about the landscape environment around them. Landscape designers also feel distressed by this and pursue this higher level, which can not only improve the living environment, but also make people being able to live and work in peace, and contentment is an honor for the landscape architect. Therefore, this study builds an excellent public space landscape model based on the 3D image processing of the visual sensor, establishes the coverage relationship table through the genetic algorithm and the greedy algorithm, and then uses the infrared image segmentation method of the local entropy combined with the region growth method to segment the 3D image of the vision sensor. Then, we use the multi-image fusion method based on the dimensional closeness to merge and finally analyze the public space landscape model with extremely high integrity. Moreover, this study also discusses the analysis results of temperature and time on the integrity of the landscape model. Between 35.5°C and 36.7°C, from 12 o’clock to 14 o’clock, the integrity of the public space landscape model is as high as 97.2%.

show abstract

Section: Introductionmentioning

confidence: 99%

3D Image Based on Visual Sensor in Public Space Landscape Model

Liu¹

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…The CPD-based methods cannot deal well with large volume points and they are easy to be affected by the outliers. Compared with traditional methods, deep learning-based methods [38][39][40] can directly learn highlevel feature representations from a large volume of data to achieve good performance on pairwise point clouds with large overlap and small-scale, but there are many difficulties for this kind of methods to register a pair of TLS point clouds with small overlap and large-scale.…”

Section: Introductionmentioning

confidence: 99%

Automatic Pairwise Coarse Registration of Terrestrial Point Clouds Using 3D Line Features

Xiong

et al. 2022

IEEE Access

View full text Add to dashboard Cite

The fully automatic registration of 3D terrestrial laser scanning (TLS) point clouds, which is the first step in the usage of point clouds, is a highly challenging task in Light Detection and Ranging (LiDAR) remote sensing applications. Here, an automatic algorithm for pairwise coarse registration of TLS point clouds using 3D line features is proposed. First, the 3D line sets were extracted from the original pair of point clouds respectively, and two arbitrary lines from a point cloud were used to construct a 2-line base; Then, a pair of conjugate 2-line bases were identified from the source and target 3D line sets at a time, based on which a 3D rotation matrix together with its corresponding overlap between the pairwise 3D line sets was calculated; Third, a series of 3D rotation matrixes together with their overlaps were obtained using the traversing strategy to identify conjugate 2-line base pairs, and the 3D rotation matrix with the highest overlap was outputted as the final 3D rotation matrix, which was further used to compute the corresponding lines set from the pairwise 3D line sets; Next, based on the set of common perpendicular midpoints between the line correspondences, the 3D translation vector was computed; Finally, the 3D transformation matrix between pairwise point clouds was obtained by combining the 3D rotation matrix and the 3D translation vector. The proposed method was tested on three different TLS datasets, with experimental results demonstrating that the proposed algorithm could perform well on registering pairwise TLS point clouds. The rotation and translation errors of aligning the nine experimental pairwise point clouds were all less than 0.50° and 0.55m, respectively. This registration framework was also shown to be superior to state-of-the-art methods in terms of registration accuracy.

show abstract

“…For example, Zhang et al [62] divided the point clouds into regular grids and used a 3D convolution network to extract features for matching. Pujol-Miró et al [63] proposed a multiview-based method, which generates multiple views from different angles using a single point cloud. Image convolutional neural networks have been used to determine the correspondences between views.…”

Section: Introductionmentioning

confidence: 99%

An Efficient Probabilistic Registration Based on Shape Descriptor for Heritage Field Inspection

Zang

Xiao

et al. 2020

IJGI

View full text Add to dashboard Cite

Heritage documentation is implemented by digitally recording historical artifacts for the conservation and protection of these cultural heritage objects. As efficient spatial data acquisition tools, laser scanners have been widely used to collect highly accurate three-dimensional (3D) point clouds without damaging the original structure and the environment. To ensure the integrity and quality of the collected data, field inspection (i.e., on-spot checking the data quality) should be carried out to determine the need for additional measurements (i.e., extra laser scanning for areas with quality issues such as data missing and quality degradation). To facilitate inspection of all collected point clouds, especially checking the quality issues in overlaps between adjacent scans, all scans should be registered together. Thus, a point cloud registration method that is able to register scans fast and robustly is required. To fulfill the aim, this study proposes an efficient probabilistic registration for free-form cultural heritage objects by integrating the proposed principal direction descriptor and curve constraints. We developed a novel shape descriptor based on a local frame of principal directions. Within the frame, its density and distance feature images were generated to describe the shape of the local surface. We then embedded the descriptor into a probabilistic framework to reject ambiguous matches. Spatial curves were integrated as constraints to delimit the solution space. Finally, a multi-view registration was used to refine the position and orientation of each scan for the field inspection. Comprehensive experiments show that the proposed method was able to perform well in terms of rotation error, translation error, robustness, and runtime and outperformed some commonly used approaches.

show abstract

Correspondence matching in unorganized 3D point clouds using Convolutional Neural Networks

Cited by 15 publications

References 16 publications

3D Image Based on Visual Sensor in Public Space Landscape Model

3D Image Based on Visual Sensor in Public Space Landscape Model

Automatic Pairwise Coarse Registration of Terrestrial Point Clouds Using 3D Line Features

An Efficient Probabilistic Registration Based on Shape Descriptor for Heritage Field Inspection

Contact Info

Product

Resources

About