A Survey and Technology Trends of 3D Features for Object Recognition

被引:4
作者
Hashimoto, Manabu [1 ]
Akizuki, Shuichi [1 ]
Takei, Shoichi [1 ]
机构
[1] Chukyo Univ, Grad Sch Comp & Cognit Sci, Nagoya, Aichi, Japan
关键词
object recognition; 3D features; local reference frame; robot vision; POSE ESTIMATION; RANGE IMAGES; SURFACE-FEATURE; REGISTRATION; RETRIEVAL; CLUTTER;
D O I
10.1002/ecj.11992
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Recently, various kinks of three-dimensional (3D) imaging devices such as laser range finder or time-of-flight sensor become popular, so a lot of practical algorithms for recognizing 3D objects using point cloud data have been proposed. In this paper, we will introduce typical object recognition approaches and survey various kinds of 3D features proposed by many researchers. As for some important techniques, their principle and characteristics are explained in detail. Also we will mention about the local reference frame that is very important factor to realize stable feature description and accurate pose estimation in practical use.
引用
收藏
页码:31 / 42
页数:12
相关论文
共 66 条
[1]   3D scene retrieval and recognition with Depth Gradient Images [J].
Adan, Antonio ;
Merchan, Pilar ;
Salamanca, Santiago .
PATTERN RECOGNITION LETTERS, 2011, 32 (09) :1337-1353
[2]  
Akizuki S, 2015, INT S VIS COMP
[3]  
Akizuki S, 2013, IEEJ T ELECT INFORM, V133, P1853
[4]  
Akizuki S., 2014, J JSPE, P1176
[5]   Stable Position and Pose Estimation of Industrial Parts Using Evaluation of Observability of 3D Vector Pairs [J].
Akizuki, Shuichi ;
Hashimoto, Manabu .
JOURNAL OF ROBOTICS AND MECHATRONICS, 2015, 27 (02) :174-181
[6]  
Aldoma Aitor, 2012, Pattern Recognition. Proceedings Joint 34th DAGM and 36th OAGM Symposium, P113, DOI 10.1007/978-3-642-32717-9_12
[7]  
Ando S, 2006, IEICE T INF SYST, p[J89, 1840]
[8]  
[Anonymous], 2007, Transactions of the Institute of Electrical Engineers of Japan, Part C, V127, P615, DOI 10.1541/ieejeiss.127.615
[9]  
[Anonymous], 2009, IEEE INT C ROB AUT
[10]  
[Anonymous], P 21 IEEE RSJ INT C