A method of 3D object recognition and localization in a cloud of points

被引：0
作者：
Jerzy Bielicki
Robert Sitnik
机构：
[1] Warsaw University of Technology,Institute of Micromechanics and Photonics
来源：
EURASIP Journal on Advances in Signal Processing | / 2013卷
关键词：
3D object recognition; Point cloud;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
The proposed method given in this article is prepared for analysis of data in the form of cloud of points directly from 3D measurements. It is designed for use in the end-user applications that can directly be integrated with 3D scanning software. The method utilizes locally calculated feature vectors (FVs) in point cloud data. Recognition is based on comparison of the analyzed scene with reference object library. A global descriptor in the form of a set of spatially distributed FVs is created for each reference model. During the detection process, correlation of subsets of reference FVs with FVs calculated in the scene is computed. Features utilized in the algorithm are based on parameters, which qualitatively estimate mean and Gaussian curvatures. Replacement of differentiation with averaging in the curvatures estimation makes the algorithm more resistant to discontinuities and poor quality of the input data. Utilization of the FV subsets allows to detect partially occluded and cluttered objects in the scene, while additional spatial information maintains false positive rate at a reasonably low level.
引用
收藏
相关论文
共 45 条
  • [1] Fridtjof GM(1992)Stein, Structural indexing: efficient 3-D object recognition IEEE Trans. Pattern Anal. Mach. Intell 14 125-145
  • [2] Chin RJ(1997)Seng Chua, Point signatures a new representation for 3D object recognition Int. J. Comput. Vis 25 63-85
  • [3] Yiyong Sun JP(2003)The point fingerpint. A new 3-D object representation scheme IEEE Trans. Syst. Man Cybern 33 712-717
  • [4] Andreas K(2009)On the repeatability and quality of keypoints for local feature-based 3D object retrieval from cluttered scenes Int. J. Comput. Vis 89 348-361
  • [5] Page DL(2001)Hough transform-based 3D mesh retrieval Proc. SPIE 4476 175-185
  • [6] Abidi MA(2006)Segmentation of point clouds using smoothness constraint ISPRS XXXVI 248-253
  • [7] Mian A(1992)Surface shape and curvature scales Image Vis. Comput 10 557-564
  • [8] Bennamoun M(2007)Chen, 3D free-form object recognition in range images using local surface patches Pattern Recognit. Lett 28 1252-1262
  • [9] Owens R(1998)Surface matching for object recognition in complex 3-D scenes Image Vis. Comput 16 635-651
  • [10] Zaharia T(1999)Using spin images for efficient object recognition in cluttered 3D scenes IEEE Trans. Pattern Anal. Mach. Intell 21 433-449
12345