Automatic Object Shape Completion from 3D Point Clouds for Object Manipulation

被引:8
作者
Figueiredo, Rui [1 ]
Moreno, Plinio [1 ]
Bernardino, Alexandre [1 ]
机构
[1] Univ Lisbon, Inst Super Tecn, LARSyS, Inst Syst & Robot ISR IST, Lisbon, Portugal
来源
PROCEEDINGS OF THE 12TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS (VISIGRAPP 2017), VOL 4 | 2017年
关键词
Shape Completion; Symmetry; Part-based Object Representation; Semantic Parts; REGISTRATION;
D O I
10.5220/0006170005650570
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
3D object representations should be able to model the shape at different levels, considering both low-level and high-level shape descriptions. In robotics applications, is difficult to compute the shape descriptors in self-occluded point clouds while solving manipulation tasks. In this paper we propose an object completion method that under some assumptions works well for a large set of kitchenware objects, based on Principal Component Analysis (PCA). In addition, object manipulation in robotics must consider not only the shape but the of actions that an agent may perform. Thus, shape-only descriptions are limited because do not consider where the object is located with respect to others and the type of constraints associated to manipulation actions. In this paper, we define a set of semantic parts (i.e. bounding boxes) that consider grasping constraints of kitchenware objects, and how to segment the object into those parts. The semantic parts provide a general representation across object categories, which allows to reduce the grasping hypotheses. Our algorithm is able to find the semantic parts of kitchenware objects in and efficient way.
引用
收藏
页码:565 / 570
页数:6
相关论文
共 17 条
[1]  
Aleotti J, 2012, IEEE INT CONF ROBOT, P4190, DOI 10.1109/ICRA.2012.6224678
[2]  
ASUS, AS XTION PRO
[3]   A METHOD FOR REGISTRATION OF 3-D SHAPES [J].
BESL, PJ ;
MCKAY, ND .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1992, 14 (02) :239-256
[4]   Efficient 3D object detection by fitting superquadrics to range image data for robot's object manipulation [J].
Biegelbauer, Georg ;
Vincze, Markus .
PROCEEDINGS OF THE 2007 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1-10, 2007, :1086-+
[5]  
Bohg J, 2011, IEEE INT CONF ROBOT
[6]   OBJECT MODELING BY REGISTRATION OF MULTIPLE RANGE IMAGES [J].
CHEN, Y ;
MEDIONI, G .
IMAGE AND VISION COMPUTING, 1992, 10 (03) :145-155
[7]   Efficient pose estimation of rotationally symmetric objects [J].
de Figueiredo, Rui Pimentel ;
Moreno, Plinio ;
Bernardino, Alexandre .
NEUROCOMPUTING, 2015, 150 :126-135
[8]  
Faria Diego R., 2012, IFAC Proceedings Volumes, V45, P247, DOI [DOI 10.3182/20120905-3-HR-2030.00090, https://doi.org/10.3182/20120905-3-HR-2030.00090]
[9]  
Hourdakis E, 2014, J SOFTWARE ENG ROBOT, V5, P13
[10]  
Jerez J, NEWTON GAME DYNAMICS