Boosting Shape Registration Algorithms via Reproducing Kernel Hilbert Space Regularizers

Parkison, Steven A.; Ghaffari, Maani; Zhang, Ray; Ushani, Arash K.; Eustice, Ryan M.

doi:10.1109/lra.2019.2932865

Cited by 9 publications

(10 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This algorithm regularizes the generalized iterative closest point (ICP) registration algorithm under the assumption that the intensity of the point cloud is locally consistent. Learning the point cloud intensity function from the noise intensity measurement instead of directly using the intensity difference solves possible mismatch problems in the data association process [61].…”

Section: Registration Methods Based On Mathematical Solutionsmentioning

confidence: 99%

High-Precision 3D Reconstruction for Small-to-Medium-Sized Objects Utilizing Line-Structured Light Scanning: A Review

2021

View full text Add to dashboard Cite

Three-dimensional reconstruction technology has demonstrated broad application potential in the industrial, construction, medical, forestry, agricultural, and pastural sectors in the last few years. High-quality digital point cloud information exists to help researchers to understand objects and environments. However, current research mainly focuses on making adaptive adjustments to various scenarios and related issues in the application of this technology rather than looking for further improvements and enhancements based on technical principles. Meanwhile, a review of approaches, algorithms, and techniques for high-precision 3D reconstruction utilizing line-structured light scanning, which is analyzed from a deeper perspective of elementary details, is lacking. This paper takes the technological path as the logical sequence to provide a detailed summary of the latest development status of each key technology, which will serve potential users and new researchers in this field. The focus is placed on exploring studies reconstructing small-to-medium-sized objects, as opposed to performing large-scale reconstructions in the field.

show abstract

Section: Registration Methods Based On Mathematical Solutionsmentioning

confidence: 99%

High-Precision 3D Reconstruction for Small-to-Medium-Sized Objects Utilizing Line-Structured Light Scanning: A Review

2021

View full text Add to dashboard Cite

show abstract

“…While the majority relies on geometric information, there has been some work which includes additional information such as color or intensity to e.g. reject outliers [10] or partition distributions [11]. Compared to all previously mentioned methods, ours does not minimize a metrical error in vector space but rather measures the similarity between clouds and therefore, operates globally.…”

Section: A Local Pointcloud Registrationmentioning

confidence: 99%

PHASER: A Robust and Correspondence-Free Global Pointcloud Registration

Bernreiter

Ott

Nieto

et al. 2021

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

We propose PHASER, a correspondence-free global registration of sensor-centric pointclouds that is robust to noise, sparsity, and partial overlaps. Our method can seamlessly handle multimodal information, and does not rely on keypoint nor descriptor preprocessing modules. By exploiting properties of Fourier analysis, PHASER operates directly on the sensor's signal, fusing the spectra of multiple channels and computing the 6-DoF transformation based on correlation. Our registration pipeline starts by finding the most likely rotation r ∈ SO(3) followed by computing the most likely translation t ∈ R 3. Both estimates, r, and t are distributed according to a probability distribution that takes the underlying manifold into account, i.e., a Bingham and a Gaussian distribution, respectively. This further allows our approach to consider the periodic-nature of r and naturally represents its uncertainty. We extensively compare PHASER against several well-known registration algorithms on both simulated datasets, and real-world data acquired using different sensor configurations. Our results show that PHASER can globally align pointclouds in less than 100 ms with an average accuracy of 2 cm and 0.5 • , is resilient against noise, and can handle partial overlap.

show abstract

“…Color ICP [14] defines a sum of reprojected photometric and depth loss on dense RGB-D point clouds. GICP-RKHS [29] also appends an additional regularizer to the GICP's loss for point intensity via the Relevance Vector Machine [37]. Semantic-ICP [7] treats points' semantic labels and associations as additional hidden variables as a part of the EM-ICP framework.…”

Section: Related Workmentioning

confidence: 99%

“…Point clouds obtained by RGB-D cameras, stereo cameras, and LIDARs contain rich color and intensity measurements besides the geometric information. The extra non-geometric information can improve the registration performance [6]- [8]. Deep learning can provide semantic attributes of the scene as measurements [9]- [11].…”

Section: Introductionmentioning

confidence: 99%

“…This paper presents a nonparametric registration framework that jointly integrates geometric and semantic measurements and does not require explicit data association. Unlike existing methods that rely on geometric residuals with regularizers to include appearance information [14], [29], the proposed framework formulates the problem using a single objective function, and is solved by the gradient ascent on Riemannian manifolds, similar to the work of [30], [31]. In particular, this work has the following contributions.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A New Framework for Registration of Semantic Point Clouds from Stereo and RGB-D Cameras

Zhang¹,

Lin²,

Lin³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

This paper reports on a novel nonparametric rigid point cloud registration framework that jointly integrates geometric and semantic measurements such as color or semantic labels into the alignment process and does not require explicit data association. The point clouds are represented as nonparametric functions in a reproducible kernel Hilbert space. The alignment problem is formulated as maximizing the inner product between two functions, essentially a sum of weighted kernels, each of which exploits the local geometric and semantic features. As a result of the continuous models, analytical gradients can be computed, and a local solution can be obtained by optimization over the rigid body transformation group. Besides, we present a new point cloud alignment metric that is intrinsic to the proposed framework and takes into account geometric and semantic information. The evaluations using publicly available stereo and RGB-D datasets show that the proposed method outperforms state-of-the-art outdoor and indoor frame-to-frame registration methods. An open-source GPU implementation is also provided.

show abstract

Boosting Shape Registration Algorithms via Reproducing Kernel Hilbert Space Regularizers

Cited by 9 publications

References 31 publications

High-Precision 3D Reconstruction for Small-to-Medium-Sized Objects Utilizing Line-Structured Light Scanning: A Review

High-Precision 3D Reconstruction for Small-to-Medium-Sized Objects Utilizing Line-Structured Light Scanning: A Review

PHASER: A Robust and Correspondence-Free Global Pointcloud Registration

A New Framework for Registration of Semantic Point Clouds from Stereo and RGB-D Cameras

Contact Info

Product

Resources

About