Describing 3D Geometric Primitives Using the Gaussian Sphere and the Gaussian Accumulator

Toony, Zahra; Laurendeau, Denis; Gagné, Christian

doi:10.1007/s13319-015-0074-3

Cited by 6 publications

(7 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The primitives that are considered in this paper are planes, spheres, cylinders, cones, and tori as well as partial models of the latter four types of primitives. Based on the method presented in [Toony et al, 2014], the type of primitive is found. The parameters are extracted for each primitive type are listed in figure 1.…”

Section: Proposed Methods (Pgp2x)mentioning

confidence: 99%

“…Our approach deals with original models without any preprocessing but the assumption is made that the model contains only one primitive which can be in the first category but without a prior segmentation process. Since several methods have been proposed to determine the type of primitives, [Toony et al, 2014,Osada et al, 2002, Kazhdan et al, 2003, Zhu et al, 2012, in this paper, we assume that the type of each primitive is known and focus on an accurate estimation of primitive parameters.…”

Section: Related Workmentioning

confidence: 99%

“…Estimating the parameters of 3D models can be helpful in different applications such as reverse engineering, 3D model retrieval, and classification of 3D models. Some methods have been proposed to recognize different types of primitives [Toony et al, 2014, Osada et al, 2002, Kazhdan et al, 2003, Zhu et al, 2012. Once a primitive has been recognized, we need an approach to extract the parameters of each primitive.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

PGP2X: Principal Geometric Primitives Parameters Extraction

Toony

Laurendeau

Gagné

2015

Proceedings of the 10th International Conference on Computer Graphics Theory and Applications

View full text Add to dashboard Cite

In reverse engineering, it is important to extract the 3D geometric primitives that compose an object. It is also important to find the values of the parameters describing each primitive. This paper presents an approach for the estimation of the parameters of geometric primitives once their type is known using 3D information. The primitives of interest are planes, spheres, cylinders, cones, tori and partial instances of the latter four types. The proposed approach extends methods found in the literature for planes, spheres, cylinders and cones and proposes a new method for dealing with tori. The results of the proposed method are compared to approaches found in the literature as well as with ground truth values. The proposed method can be applied to the estimation of parameters of geometric primitives of synthetic CAD models as well as for models of real objects acquired with 3D scanners.

show abstract

Section: Proposed Methods (Pgp2x)mentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

PGP2X: Principal Geometric Primitives Parameters Extraction

Toony

Laurendeau

Gagné

2015

Proceedings of the 10th International Conference on Computer Graphics Theory and Applications

View full text Add to dashboard Cite

show abstract

“…Toony et al [34] proposes unit sphere tessellation into 1996 equilateral triangle cells. This approach gives near uniform cells in area and shape, resolving previous issues with unequal weighting, pole singularities, and non-equivariant kernels.…”

Section: Dominant Plane Normal Estimationmentioning

confidence: 99%

Polylidar3D-Fast Polygon Extraction from 3D Data

Castagno

Atkins

2020

Sensors

View full text Add to dashboard Cite

Flat surfaces captured by 3D point clouds are often used for localization, mapping, and modeling. Dense point cloud processing has high computation and memory costs making low-dimensional representations of flat surfaces such as polygons desirable. We present Polylidar3D, a non-convex polygon extraction algorithm which takes as input unorganized 3D point clouds (e.g., LiDAR data), organized point clouds (e.g., range images), or user-provided meshes. Non-convex polygons represent flat surfaces in an environment with interior cutouts representing obstacles or holes. The Polylidar3D front-end transforms input data into a half-edge triangular mesh. This representation provides a common level of abstraction for subsequent back-end processing. The Polylidar3D back-end is composed of four core algorithms: mesh smoothing, dominant plane normal estimation, planar segment extraction, and finally polygon extraction. Polylidar3D is shown to be quite fast, making use of CPU multi-threading and GPU acceleration when available. We demonstrate Polylidar3D’s versatility and speed with real-world datasets including aerial LiDAR point clouds for rooftop mapping, autonomous driving LiDAR point clouds for road surface detection, and RGBD cameras for indoor floor/wall detection. We also evaluate Polylidar3D on a challenging planar segmentation benchmark dataset. Results consistently show excellent speed and accuracy.

show abstract

“…For example, an early method simultaneous grows multiple seed regions with dynamic primitive model selection by iterative regression [17], but was not shown to necessarily work for noisy cluttered scenes. A more recent work in reverse engineering [18] assumes the input 3D mesh has been previously segmented into parts, and then classifies each part based on the Gaussian sphere, i.e. the normal space.…”

Section: B Related Workmentioning

confidence: 99%

Primitive Fitting Using Deep Geometric Segmentation

Feng²

2019

Proceedings of the International Symposium on Automation and Robotics in Construction (IAARC)

View full text Add to dashboard Cite

To identify and fit geometric primitives (e.g., planes, spheres, cylinders, cones) in a noisy point cloud is a challenging yet beneficial task for fields such as robotics and reverse engineering. As a multi-model multi-instance fitting problem, it has been tackled with different approaches including RANSAC, which however often fit inferior models in practice with noisy inputs of cluttered scenes. Inspired by the corresponding human recognition process, and benefiting from the recent advancements in image semantic segmentation using deep neural networks, we propose BAGSFit as a new framework addressing this problem. Firstly, through a fully convolutional neural network, the input point cloud is point-wisely segmented into multiple classes divided by jointly detected instance boundaries without any geometric fitting. Thus, segments can serve as primitive hypotheses with a probability estimation of associating primitive classes. Finally, all hypotheses are sent through a geometric verification to correct any misclassification by fitting primitives respectively. We performed training using simulated range images and tested it with both simulated and real-world point clouds. Quantitative and qualitative experiments demonstrated the superiority of BAGSFit.

show abstract

Describing 3D Geometric Primitives Using the Gaussian Sphere and the Gaussian Accumulator

Cited by 6 publications

References 38 publications

PGP2X: Principal Geometric Primitives Parameters Extraction

PGP2X: Principal Geometric Primitives Parameters Extraction

Polylidar3D-Fast Polygon Extraction from 3D Data

Primitive Fitting Using Deep Geometric Segmentation

Contact Info

Product

Resources

About