3D Feature Detector-Descriptor Pair Evaluation on Point Clouds

Stancelova, Paula; Šikudová, Elena; Cernekova, Zuzana

doi:10.23919/eusipco47968.2020.9287339

Cited by 5 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SIFT3D [ 16 ] is an extension of the original 2D SIFT detector in which the difference between Gaussian pyramids is used to find the key points. Steder et al [ 17 ] exploit the NARF detector to select points at which the surface is stable and that features a sufficient amount of change in the local neighborhood.…”

Section: Related Workmentioning

confidence: 99%

A Structure-Based Iterative Closest Point Using Anderson Acceleration for Point Clouds with Low Overlap

Zeng

Chen

Zhang

et al. 2023

Sensors

View full text Add to dashboard Cite

The traditional point-cloud registration algorithms require large overlap between scans, which imposes strict constrains on data acquisition. To facilitate registration, the user has to strategically position or move the scanner to ensure proper overlap. In this work, we design a method of feature extraction based on high-level information to establish structure correspondences and an optimization problem. And we rewrite it as a fixed-point problem and apply the Lie algebra to parameterize the transform matrix. To speed up convergence, we introduce Anderson acceleration, an approach enhanced by heuristics. Our model attends to the structural features of the region of overlap instead of the correspondence between points. The experimental results show the proposed ICP method is robust, has a high accuracy of registration on point clouds with low overlap on a laser datasets, and achieves a computational time that is competitive with that of prevalent methods.

show abstract

Section: Related Workmentioning

confidence: 99%

A Structure-Based Iterative Closest Point Using Anderson Acceleration for Point Clouds with Low Overlap

Zeng

Chen

Zhang

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Where in G is the Gaussian function and P(x,y,z) is 3D coordinates of a point cloud. The convolution is performed by voxel grid filters [54].…”

Section:  mentioning

confidence: 99%

“…This transformation function models geometric differences such as translations and rotations well. The M-estimator sample consensus (MSAC) [54], an extension of RANSAC, is used to estimate the parameters of the 3D affine model. The points in the source data are then transferred to the target data space using the parameters of this transformation function, and their distance from the correspondence point in the target data is considered as the error of each corresponding pair.…”

Section: Matching and Eliminating Wrong Correspondencesmentioning

confidence: 99%

A Novel 3-D Local DAISY-Style Descriptor to Reduce the Effect of Point Displacement Error in Point Cloud Registration

Ghorbani

Ebadi

Sedaghat

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

3D point clouds are widely considered for applications in different fields. Various methods have been proposed to generate point cloud data: LIDAR and image matching from static and mobile platforms, including, e.g., Terrestrial Laser S canning (TLS ). With multiple point clouds from stationary platforms, point cloud registration is a crucial and fundamental issue. A standard approach is a point-based registration, which relies on pairs of corresponding points in twopoint clouds. Therefore, a necessary step in point-based registration is the construction of 3D local descriptors. One of the (many) challenges that will specifically affect the performance of local descriptors with local spatial information is the point displacement error. This error is caused by the difference in the distributions of points surrounding a (potentially) corresponding center point in the two-point clouds. It can occur for various reasons such as i) distortions caused by the sensors recording the data, ii) moving objects, iii) varying density of point cloud, iv) change of viewing angle, and v) different of the sensors. The purpose of this article is to develop a new 3D local descriptor reducing the effect of this type of error in point cloud coarse registration. The approach includes an improved Local Reference Frame (LRF) and a new geometric arrangement in point cloud space for the 3D local descriptor. Inspired by the 2D DAIS Y descriptor, a geometric arrangement is created to reduce the effect of the point displacement error. in addi tion, directional histograms are considered as features. Investigations are performed for point clouds from challenging environments, which are publicly available. The results of this study show the high performance of the proposed approach for point cloud registration, especially in more challenging and noisy environments.

show abstract

Augmented reality-based guidance in product assembly and maintenance/repair perspective: A state of the art review on challenges and opportunities

Eswaran¹,

Gulivindala²,

Inkulu³

et al. 2023

Expert Systems with Applications

View full text Add to dashboard Cite

3D Feature Detector-Descriptor Pair Evaluation on Point Clouds

Cited by 5 publications

References 20 publications

A Structure-Based Iterative Closest Point Using Anderson Acceleration for Point Clouds with Low Overlap

A Structure-Based Iterative Closest Point Using Anderson Acceleration for Point Clouds with Low Overlap

A Novel 3-D Local DAISY-Style Descriptor to Reduce the Effect of Point Displacement Error in Point Cloud Registration

Augmented reality-based guidance in product assembly and maintenance/repair perspective: A state of the art review on challenges and opportunities

Contact Info

Product

Resources

About