6D Pose Estimation from Point Cloud Using an Improved Point Pair Features Method

被引：8

作者：

Wang, Haoyu ^{[1
]}

Wang, Hesheng ^{[1
]}

Zhuang, Chungang ^{[1
]}

机构：

[1] Shanghai Jiao Tong Univ, Sch Mech Engn, Shanghai, Peoples R China

来源：

2021 7TH INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION AND ROBOTICS (ICCAR) | 2021年

基金：

中国国家自然科学基金;

关键词：

pose estimation; point pair features; point cloud; normal estimation; 3D computer vision; RECOGNITION;

D O I：

10.1109/ICCAR52225.2021.9463502

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The Point Pair Features (PPF) method has been shown to be effective for pose estimation under clutter and occlusion. Our improved method mainly includes: (1) an approach for solving normal orientations of closed geometries based on Odd-even Rule; (2) an efficient downsampling approach by dividing a voxel grid into equivalent angle cells; (3) a verification step based on fitting points. The method is evaluated on real datasets of clutter and shows better performance as well as efficiency for 6D pose estimation compared to original PPF method.

引用

页码：280 / 284

页数：5

共 16 条

[1]

Aldoma A., 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops), P585, DOI 10.1109/ICCVW.2011.6130296

[2] Point Pair Features Based Object Detection and Pose Estimation Revisited [J].

Birdal, Tolga ;

Ilic, Slobodan .

2015 INTERNATIONAL CONFERENCE ON 3D VISION, 2015, :527-535

[3] 3D Object Detection and Localization using Multimodal Point Pair Features [J].

Drost, Bertram ;

Ilic, Slobodan .

SECOND JOINT 3DIM/3DPVT CONFERENCE: 3D IMAGING, MODELING, PROCESSING, VISUALIZATION & TRANSMISSION (3DIMPVT 2012), 2012, :9-16

[4] Model Globally, Match Locally: Efficient and Robust 3D Object Recognition [J].

Drost, Bertram ;

Ulrich, Markus ;

Navab, Nassir ;

Ilic, Slobodan .

2010 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2010, :998-1005

[5] 3D Object Recognition in Cluttered Scenes with Local Surface Features: A Survey [J].

Guo, Yulan ;

Bennamoun, Mohammed ;

Sohel, Ferdous ;

Lu, Min ;

Wan, Jianwei .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2014, 36 (11) :2270-2287

[6] Going Further with Point Pair Features [J].

Hinterstoisser, Stefan ;

Lepetit, Vincent ;

Rajkumar, Naresh ;

Konolige, Kurt .

COMPUTER VISION - ECCV 2016, PT III, 2016, 9907 :834-848

[7] BOP: Benchmark for 6D Object Pose Estimation [J].

Hodan, Tomas ;

Michel, Frank ;

Brachmann, Eric ;

Kehl, Wadim ;

Buch, Anders Glent ;

Kraft, Dirk ;

Drost, Bertram ;

Vidal, Joel ;

Ihrke, Stephan ;

Zabulis, Xenophon ;

Sahin, Caner ;

Manhardt, Fabian ;

Tombari, Federico ;

Kim, Tae-Kyun ;

Matas, Jiri ;

Rother, Carsten .

COMPUTER VISION - ECCV 2018, PT X, 2018, 11214 :19-35

[8] A performance evaluation of point pair features [J].

Kiforenko, Lilita ;

Drost, Bertram ;

Tombari, Federico ;

Kruger, Norbert ;

Buch, Anders Glent .

COMPUTER VISION AND IMAGE UNDERSTANDING, 2018, 166 :66-80

[9] 3D Object Recognition and Pose Estimation From Point Cloud Using Stably Observed Point Pair Feature [J].

Li, Deping ;

Wang, Hanyun ;

Liu, Ning ;

Wang, Xiaoming ;

Xu, Jin .

IEEE ACCESS, 2020, 8 :44335-44345

[10]

Rusinkiewicz S, 2001, THIRD INTERNATIONAL CONFERENCE ON 3-D DIGITAL IMAGING AND MODELING, PROCEEDINGS, P145, DOI 10.1109/IM.2001.924423

← 1 2 →