PrimiTect: Fast Continuous Hough Voting for Primitive Detection
- URL: http://arxiv.org/abs/2005.07457v1
- Date: Fri, 15 May 2020 10:16:07 GMT
- Title: PrimiTect: Fast Continuous Hough Voting for Primitive Detection
- Authors: Christiane Sommer and Yumin Sun and Erik Bylow and Daniel Cremers
- Abstract summary: Our method classifies points into different geometric primitives, such as planes and cones, leading to a compact representation of the data.
We use a local, low-dimensional parameterization of primitives to determine type, shape and pose of the object that a point belongs to.
This makes our algorithm suitable to run on devices with low computational power, as often required in robotics applications.
- Score: 49.72425950418304
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This paper tackles the problem of data abstraction in the context of 3D point
sets. Our method classifies points into different geometric primitives, such as
planes and cones, leading to a compact representation of the data. Being based
on a semi-global Hough voting scheme, the method does not need initialization
and is robust, accurate, and efficient. We use a local, low-dimensional
parameterization of primitives to determine type, shape and pose of the object
that a point belongs to. This makes our algorithm suitable to run on devices
with low computational power, as often required in robotics applications. The
evaluation shows that our method outperforms state-of-the-art methods both in
terms of accuracy and robustness.
Related papers
- A Weighted K-Center Algorithm for Data Subset Selection [70.49696246526199]
Subset selection is a fundamental problem that can play a key role in identifying smaller portions of the training data.
We develop a novel factor 3-approximation algorithm to compute subsets based on the weighted sum of both k-center and uncertainty sampling objective functions.
arXiv Detail & Related papers (2023-12-17T04:41:07Z) - Improving Online Lane Graph Extraction by Object-Lane Clustering [106.71926896061686]
We propose an architecture and loss formulation to improve the accuracy of local lane graph estimates.
The proposed method learns to assign the objects to centerlines by considering the centerlines as cluster centers.
We show that our method can achieve significant performance improvements by using the outputs of existing 3D object detection methods.
arXiv Detail & Related papers (2023-07-20T15:21:28Z) - Marching-Primitives: Shape Abstraction from Signed Distance Function [29.7543198254021]
We present a novel method, named Marching-Primitives, to obtain a primitive-based abstraction directly from an SDF.
Our method grows geometric primitives iteratively by analyzing the connectivity of voxels.
We evaluate the performance of our method on both synthetic and real-world datasets.
arXiv Detail & Related papers (2023-03-23T11:42:35Z) - Fitting and recognition of geometric primitives in segmented 3D point
clouds using a localized voting procedure [1.8352113484137629]
We introduce a novel technique for processing point clouds that, through a voting procedure, is able to provide an initial estimate of the primitive parameters each type.
By using these estimates we localize the search of the optimal solution in a dimensionally-reduced space, making it efficient to extend the HT to more primitive than those that generally found in the literature.
arXiv Detail & Related papers (2022-05-30T20:47:43Z) - PointInst3D: Segmenting 3D Instances by Points [136.7261709896713]
We propose a fully-convolutional 3D point cloud instance segmentation method that works in a per-point prediction fashion.
We find the key to its success is assigning a suitable target to each sampled point.
Our approach achieves promising results on both ScanNet and S3DIS benchmarks.
arXiv Detail & Related papers (2022-04-25T02:41:46Z) - Sim2Real 3D Object Classification using Spherical Kernel Point
Convolution and a Deep Center Voting Scheme [28.072144989298298]
Learning from artificial 3D models alleviates the cost of annotation necessary to approach this problem.
We conjecture that the cause of those issue is the fact that many methods learn directly from point coordinates, instead of the shape.
We introduce spherical kernel point convolutions that directly exploit the object surface, represented as a graph, and a voting scheme to limit the impact of poor segmentation.
arXiv Detail & Related papers (2021-03-10T15:32:04Z) - 1-Point RANSAC-Based Method for Ground Object Pose Estimation [5.954779483701331]
Given outlier-contaminated data, a pose of an object is calculated with algorithms discovering n = 3, 4 in the RANSAC-based scheme.
However, the computational complexity increases along with n and the high complexity imposes a severe strain on devices which should estimate multiple object poses in real time.
In this paper, we propose an efficient method based on 1-point RANSAC for estimating a pose an object on the ground.
arXiv Detail & Related papers (2020-08-09T12:58:58Z) - A Self-Training Approach for Point-Supervised Object Detection and
Counting in Crowds [54.73161039445703]
We propose a novel self-training approach that enables a typical object detector trained only with point-level annotations.
During training, we utilize the available point annotations to supervise the estimation of the center points of objects.
Experimental results show that our approach significantly outperforms state-of-the-art point-supervised methods under both detection and counting tasks.
arXiv Detail & Related papers (2020-07-25T02:14:42Z) - Aligning Partially Overlapping Point Sets: an Inner Approximation
Algorithm [80.15123031136564]
We propose a robust method to align point sets where there is no prior information about the value of the transformation.
Our algorithm does not need regularization on transformation, and thus can handle the situation where there is no prior information about the values of the transformations.
Experimental results demonstrate the better robustness of the proposed method over state-of-the-art algorithms.
arXiv Detail & Related papers (2020-07-05T15:23:33Z) - Learning to Detect Entanglement [1.4763055441508717]
Classifying states as entangled or separable is a fundamental, but expensive task.
This paper presents a method, the forest algorithm, to improve the amount of resources needed to detect entanglement.
arXiv Detail & Related papers (2017-09-11T22:47:24Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.