Performance Evaluation of Learned 3D Features

被引:4
作者
Spezialetti, Riccardo [1 ]
Salti, Samuele [1 ]
Di Stefano, Luigi [1 ]
机构
[1] Viale Risorgimento 2, Bologna, Italy
来源
IMAGE ANALYSIS AND PROCESSING - ICIAP 2019, PT I | 2019年 / 11751卷
关键词
3D Computer Vision; Surface matching; 3D features; RECOGNITION;
D O I
10.1007/978-3-030-30642-7_47
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Matching surfaces is a challenging 3D Computer Vision problem typically addressed by local features. Although a variety of 3D feature detectors and descriptors has been proposed in literature, they have seldom been proposed together and it is yet not clear how to identify the most effective detector-descriptor pair for a specific application. A promising solution is to leverage machine learning to learn the optimal 3D detector for any given 3D descriptor [15]. In this paper, we report a performance evaluation of the detector-descriptor pairs obtained by learning a paired 3D detector for the most popular 3D descriptors. In particular, we address experimental settings dealing with object recognition and surface registration.
引用
收藏
页码:519 / 531
页数:13
相关论文
共 17 条
[1]  
[Anonymous], 2010, WORKSH DEF SOLV REAL
[2]  
Frome A, 2004, LECT NOTES COMPUT SC, V3023, P224
[3]   A Comprehensive Performance Evaluation of 3D Local Feature Descriptors [J].
Guo, Yulan ;
Bennamoun, Mohammed ;
Sohel, Ferdous ;
Lu, Min ;
Wan, Jianwei ;
Kwok, Ngai Ming .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2016, 116 (01) :66-89
[4]   Rotational Projection Statistics for 3D Local Surface Description and Object Recognition [J].
Guo, Yulan ;
Sohel, Ferdous ;
Bennamoun, Mohammed ;
Lu, Min ;
Wan, Jianwei .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2013, 105 (01) :63-86
[5]   Using spin images for efficient object recognition in cluttered 3D scenes [J].
Johnson, AE ;
Hebert, M .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1999, 21 (05) :433-449
[6]   Learning Compact Geometric Features [J].
Khoury, Marc ;
Zhou, Qian-Yi ;
Koltun, Vladlen .
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, :153-161
[7]   On the Repeatability and Quality of Keypoints for Local Feature-based 3D Object Retrieval from Cluttered Scenes [J].
Mian, A. ;
Bennamoun, M. ;
Owens, R. .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2010, 89 (2-3) :348-361
[8]   Aligning Point Cloud Views using Persistent Feature Histograms [J].
Rusu, Radu Bogdan ;
Blodow, Nico ;
Marton, Zoltan Csaba ;
Beetz, Michael .
2008 IEEE/RSJ INTERNATIONAL CONFERENCE ON ROBOTS AND INTELLIGENT SYSTEMS, VOLS 1-3, CONFERENCE PROCEEDINGS, 2008, :3384-3391
[9]  
Rusu RB, 2010, IEEE INT C INT ROBOT, P2155, DOI 10.1109/IROS.2010.5651280
[10]   Learning a Descriptor-specific 3D Keypoint Detector [J].
Salti, Samuele ;
Tombari, Federico ;
Spezialetti, Riccardo ;
Di Stefano, Luigi .
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, :2318-2326