Point Clouds Registration with Probabilistic Data Association

Agamennoni, Gabriel; Fontana, Simone; Siegwart, Roland; Sorrenti, Domenico G.

doi:10.1109/iros.2016.7759602

Cited by 64 publications

(59 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditional point cloud registration methods: ICP [4] is the best-known algorithm for solving rigid registration problems; it alternates between finding point cloud correspondences and solving a least-squares problem to update the alignment. ICP variants [34,37,5] consider issues with 1 https://github.com/WangYueFt/dcp the basic method, like noise, partiality, and sparsity; probabilistic models [12,13,17] also can improve resilience to uncertain data. ICP can be viewed as an optimization algorithm searching jointly for a matching and a rigid alignment; hence, [11] propose using the Levenberg-Marquardt algorithm to optimize the objective directly, which can yield a better solution.…”

Section: Related Workmentioning

confidence: 99%

Deep Closest Point: Learning Representations for Point Cloud Registration

Wang

Solomon

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

833

656

View full text Add to dashboard Cite

Point cloud registration is a key problem for computer vision applied to robotics, medical imaging, and other applications. This problem involves finding a rigid transformation from one point cloud into another so that they align. Iterative Closest Point (ICP) and its variants provide simple and easily-implemented iterative methods for this task, but these algorithms can converge to spurious local optima. To address local optima and other difficulties in the ICP pipeline, we propose a learning-based method, titled Deep Closest Point (DCP), inspired by recent techniques in computer vision and natural language processing. Our model consists of three parts: a point cloud embedding network, an attention-based module combined with a pointer generation layer, to approximate combinatorial matching, and a differentiable singular value decomposition (SVD) layer to extract the final rigid transformation. We train our model end-to-end on the ModelNet40 dataset and show in several settings that it performs better than ICP, its variants (e.g., Go-ICP, FGR), and the recently-proposed learning-based method PointNetLK. Beyond providing a state-of-the-art registration technique, we evaluate the suitability of our learned features transferred to unseen objects. We also provide preliminary analysis of our learned model to help understand whether domain-specific and/or global features facilitate rigid registration.

show abstract

Section: Related Workmentioning

confidence: 99%

Deep Closest Point: Learning Representations for Point Cloud Registration

Wang

Solomon

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

833

656

View full text Add to dashboard Cite

show abstract

“…As for soft rejections, Bergström et al [17] compared the effect of three M-estimators on ICP and proposed an algorithm to auto-tune them, but they only provided results based on simulated data of simple geometric shapes. Agamennoni et al [18] proposed a soft rejection function based of Student's T-distribution for registration between a sparse and a dense point clouds. But, they compare their algorithm to another complete ICP solution, where multiple stages changed.…”

Section: Related Workmentioning

confidence: 99%

Analysis of Robust Functions for Registration Algorithms

Babin

Giguère

Pomerleau

2019

2019 International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

Registration accuracy is influenced by the presence of outliers and numerous robust solutions have been developed over the years to mitigate their effect. However, without a large scale comparison of solutions to filter outliers, it is becoming tedious to select an appropriate algorithm for a given application. This paper presents a comprehensive analyses of the effects of outlier filters on the Iterative Closest Point (ICP) algorithm aimed at mobile robotic application. Fourteen of the most common outlier filters (such as M-estimators) have been tested in different types of environments, for a total of more than two million registrations. Furthermore, the influence of tuning parameters have been thoroughly explored. The experimental results show that most outlier filters have similar performance if they are correctly tuned. Nonetheless, filters such as Var. Trim., Cauchy, and Cauchy MAD are more stable against different environment types. Interestingly, the simple norm L1 produces comparable accuracy, while been parameterless.

show abstract

“…The method was proposed in [9], and several extensions and generations have been presented. In [10] the authors introduce probabilistic association in ICP, where instead of matching point-to-point, they use a t-distribution to model the distances to a set of target points and assign a weight to each association. ICP iteratively finds point correspondences between point clouds and minimizes a distance cost function.…”

Section: Related Workmentioning

confidence: 99%

Integrating Deep Semantic Segmentation Into 3-D Point Cloud Registration

Zaganidis

Sun

Duckett

et al. 2018

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Abstract-Point cloud registration is the task of aligning 3D scans of the same environment captured from different poses. When semantic information is available for the points, it can be used as a prior in the search for correspondences to improve registration. Semantic-assisted Normal Distributions Transform (SE-NDT) is a new registration algorithm that reduces the complexity of the problem by using the semantic information to partition the point cloud into a set of normal distributions, which are then registered separately. In this paper we extend the NDT registration pipeline by using PointNet, a deep neural network for segmentation and classification of point clouds, to learn and predict per-point semantic labels. We also present the Iterative Closest Point (ICP) equivalent of the algorithm, a special case of Multichannel Generalized ICP. We evaluate the performance of SE-NDT against the state of the art in point cloud registration on the publicly available classification data set Semantic3d.net. We also test the trained classifier and algorithms on dynamic scenes, using a sequence from the public dataset KITTI. The experiments demonstrate the improvement of the registration in terms of robustness, precision and speed, across a range of initial registration errors, thanks to the inclusion of semantic information.

show abstract

Point Clouds Registration with Probabilistic Data Association

Cited by 64 publications

References 13 publications

Deep Closest Point: Learning Representations for Point Cloud Registration

Deep Closest Point: Learning Representations for Point Cloud Registration

Analysis of Robust Functions for Registration Algorithms

Integrating Deep Semantic Segmentation Into 3-D Point Cloud Registration

Contact Info

Product

Resources

About