Object Detection in Point Clouds Using Conformal Geometric Algebra

Sveier, Aksel; Kleppe, Adam Leon; Tingelstad, Lars; Egeland, Olav

doi:10.1007/s00006-017-0759-1

Cited by 16 publications

(7 citation statements)

References 11 publications

(9 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…4c, where several items were placed on a table. The objects were extracted using [26], which generated a set of point The RMS shows the overall distance error between the two compared point clouds. The comment describes some of the remarks that was done with the visual inspection of the results clouds.…”

Section: Methodsmentioning

confidence: 99%

A Curvature-Based Descriptor for Point Cloud Alignment Using Conformal Geometric Algebra

Kleppe

Egeland

2018

Adv. Appl. Clifford Algebras

Self Cite

View full text Add to dashboard Cite

This paper presents a descriptor for course alignment of point clouds using conformal geometric algebra. The method is based on selecting keypoints depending on shape factors to identify distinct features of the object represented by the point cloud, and a descriptor is then calculated for each keypoint by fitting two spheres that describe the local curvature. The method for estimating the point correspondences is to a larger extent based on geometric arguments than the method of Kleppe et al. (IEEE Trans Autom Sci Eng, 2017), which results in improved performance. The accuracy of the curvature-based descriptor is validated in experiments, and is shown to compare favorably to stateof-the-art methods in an experiment on course alignment of industrial parts to be assembled with robots.

show abstract

Section: Methodsmentioning

confidence: 99%

A Curvature-Based Descriptor for Point Cloud Alignment Using Conformal Geometric Algebra

Kleppe

Egeland

2018

Adv. Appl. Clifford Algebras

Self Cite

View full text Add to dashboard Cite

show abstract

“…Classical Inlier/Outlier Estimation Approaches Given a pair of point clouds, inlier estimation determines which points in one point cloud are most similar to the points in another. Estimating inlier point-pairs is a well documented problem that finds application in registration [11], object detection [37], and flow estimation [23]. Locally optimal methods achieve this by finding all point-pairs between point clouds, and retaining only the inliers by using algorithms such as RANSAC [35,26].…”

Section: Related Workmentioning

confidence: 99%

MaskNet: A Fully-Convolutional Network to Estimate Inlier Points

Sarode¹,

Dhagat²,

Srivatsan³

et al. 2020

Preprint

View full text Add to dashboard Cite

Point clouds have grown in importance in the way computers perceive the world. From LIDAR sensors in autonomous cars and drones to the time of flight and stereo vision systems in our phones, point clouds are everywhere. Despite their ubiquity, point clouds in the real world are often missing points because of sensor limitations or occlusions, or contain extraneous points from sensor noise or artifacts. These problems challenge algorithms that require computing correspondences between a pair of point clouds. Therefore, this paper presents a fully-convolutional neural network that identifies which points in one point cloud are most similar (inliers) to the points in another. We show improvements in learning-based and classical point cloud registration approaches when retrofitted with our network. We demonstrate these improvements on synthetic and realworld datasets. Finally, our network produces impressive results on test datasets that were unseen during training, thus exhibiting generalizability. Code and videos are available at https://github.com/vinits5/masknet

show abstract

“…Gallo et al [18] address the problem of RANSAC often connecting nearby patches that are actually unconnected, for example at steps and curbs. By combining RANSAC with conformal geometric algebra, Sveier et al [19] perform the least squares fitting necessary to assess the fitness of a plane hypothesis analytically instead of numerically. Alehdaghi et al [20] present a highly parallelized GPU implementation of RANSAC for plane extraction.…”

Section: Related Workmentioning

confidence: 99%

A Maximum Likelihood Approach to Extract Finite Planes from 3-D Laser Scans

Schaefer

Vertens

Büscher

et al. 2019

2019 International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

Whether it is object detection, model reconstruction, laser odometry, or point cloud registration: Plane extraction is a vital component of many robotic systems. In this paper, we propose a strictly probabilistic method to detect finite planes in organized 3-D laser range scans. An agglomerative hierarchical clustering technique, our algorithm builds planes from bottom up, always extending a plane by the point that decreases the measurement likelihood of the scan the least. In contrast to most related methods, which rely on heuristics like orthogonal point-to-plane distance, we leverage the ray path information to compute the measurement likelihood. We evaluate our approach not only on the popular SegComp benchmark, but also provide a challenging synthetic dataset that overcomes SegComp's deficiencies. Both our implementation and the suggested dataset are available at [1].

show abstract

Object Detection in Point Clouds Using Conformal Geometric Algebra

Cited by 16 publications

References 11 publications

A Curvature-Based Descriptor for Point Cloud Alignment Using Conformal Geometric Algebra

A Curvature-Based Descriptor for Point Cloud Alignment Using Conformal Geometric Algebra

MaskNet: A Fully-Convolutional Network to Estimate Inlier Points

A Maximum Likelihood Approach to Extract Finite Planes from 3-D Laser Scans

Contact Info

Product

Resources

About