3D plane detection for robot perception applying particle swarm optimization

Masuta, Hiroyuki; Makino, Shinichiro; Lim, Hun-ok

doi:10.1109/wac.2014.6936041

Cited by 11 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the selection of growth units, the point‐based method often selects seed points randomly; the method based on rectangular areas selects planar clusters either randomly or with the smallest mean squared error; in the method used by Masuta et al. (), the growth unit is selected by particle swarm optimisation.…”

Section: Related Workmentioning

confidence: 99%

A multi‐scale plane‐detection method based on the Hough transform and region growing

Leng

Xiao

Wang

2016

The Photogrammetric Record

View full text Add to dashboard Cite

The detection of planes from 3D point clouds plays an important role in fields such as 3D modelling, rock mechanics, registration and robotics. A multi-scale plane-detection method is proposed, based on extracting growth units using the Hough transform and subsequent region growing into actual plane boundaries. Because the approximate geometric features of the original plane area can be obtained from the growth units, discriminant conditions for adaptive plane growing could be provided for the growing stage. In order to detect physical planes at different scales, a strategy of multi-scale normal estimation is introduced. Simulated icosahedron point clouds, together with actual engineering point clouds, were used to test the performance of the proposed method. Experimental results show that planar point clouds could be detected effectively, especially with rock-mass engineering applications.

show abstract

Section: Related Workmentioning

confidence: 99%

A multi‐scale plane‐detection method based on the Hough transform and region growing

Leng

Xiao

Wang

2016

The Photogrammetric Record

View full text Add to dashboard Cite

show abstract

“…Fig.3 (a), (b) and (c) shows a snapshot of SR-3000 image, distribution of particles and a result of simplified plane detection, respectively. The particles of PSO are updated to gather around detected small planes [24]. However, it is difficult to detect a steady plane because of sensing noise.…”

Section: A Point Cloud Group Of An Unknown Objectmentioning

confidence: 99%

“…But, there are many planes on the object position in the case of a round object and multi-object situation. Therefore, the planes are integrated to one plane set as an object based [24]. The largest detected plane as a table plane is eliminated from the detected plane.…”

Section: A Point Cloud Group Of An Unknown Objectmentioning

confidence: 99%

See 1 more Smart Citation

Direct perception and action system for unknown object grasping

Masuta

Lim

Motoyoshi

et al. 2015

2015 24th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN)

Self Cite

View full text Add to dashboard Cite

This paper discusses the direct perception for grasping and the action for perception using depth sensor. The previous method should recognize the accurate physical parameters to grasp an unknown object. Hence, we propose a sensation based perception which perceives exclusively the relevant information to the behavior of the robot. To perceive an unknown object, we have proposed the plane detection based approach of the SPD-SE. The SPD-SE may have applicability to robot perception at real time, and has advantages that the point group and properties of an unknown object can be extracted at the same time. The sensation of grasping is explained by inertia tensor and fuzzy inference. The sensation of grasping affords the possibility of action to a robot directly without inference from physical information such as size, posture and shape. As experimental results, we show that the robot can detect a relevant information of a grasping behavior directly. And, the sensation of grasping presents own state and environmental state together by one parameter.

show abstract

“…RANSAC may detect spurious feature surfaces or discontinuous surfaces. Region Growing performs a local search to identify and expand the regions with same characteristics [14]. Region Growing may lead to holes and over-segmentation issues.…”

Section: Introductionmentioning

confidence: 99%

Major Orientation Estimation-Based Rock Surface Extraction for 3D Rock-Mass Point Clouds

2019

View full text Add to dashboard Cite

In the fields of 3D modeling, analysis of discontinuities and engineering calculation, surface extraction is of great importance. The rapid development of photogrammetry and Light Detection and Ranging (LiDAR) technology facilitates the study of surface extraction. Automatic extraction of rock surfaces from 3D rock-mass point clouds also becomes the basis of 3D modeling and engineering calculation of rock mass. This paper presents an automated and effective method for extracting rock surfaces from unorganized rock-mass point clouds. This method consists of three stages: (i) clustering based on voxels; (ii) estimating major orientations based on Gaussian Kernel and (iii) rock surface extraction. Firstly, the two-level spatial grid is used for fast voxelization and segmenting the point cloud into three types of voxels, including coplanar, non-coplanar and sparse voxels. Secondly, the coplanar voxels, rather than the scattered points, are employed to estimate major orientations by using a bivariate Gaussian Kernel. Finally, the seed voxels are selected on the basis of major orientations and the region growing method based on voxels is applied to extract rock surfaces, resulting in sets of surface clusters. The sub-surfaces of each cluster are coplanar or parallel. In this paper, artificial icosahedron point cloud and natural rock-mass point clouds are used for testing the proposed method, respectively. The experimental results show that, the proposed method can effectively and accurately extract rock surfaces in unorganized rock-mass point clouds.

show abstract

3D plane detection for robot perception applying particle swarm optimization

Cited by 11 publications

References 13 publications

A multi‐scale plane‐detection method based on the Hough transform and region growing

A multi‐scale plane‐detection method based on the Hough transform and region growing

Direct perception and action system for unknown object grasping

Major Orientation Estimation-Based Rock Surface Extraction for 3D Rock-Mass Point Clouds

Contact Info

Product

Resources

About