A New Approach for 3D Edge Extraction by Fusing Point Clouds and Digital Images

Abstract:

Edges are crucial features for object segmentation and classification in both image and point cloud processing. Though many research efforts have been made in edge extraction and enhancement in both areas, their applications are limited respectively owing to their own technical properties. This paper presents a new approach to integrating the edge pixels in the 2D image into boundary data in the 3D point cloud by establishing the mapping relationship between these two types of data to represent the 3D edge features of the object. The 3D edge extraction based on the adoption of Microsoft Kinect as a 3D sensor - involves the following three steps: first, the generation of a range image from the point cloud of the object, second the edge extraction in the range image and edge extraction in the digital image, and finally edge data integration by referring to the correspondence map between point cloud data and image pixels.

• Periodical: Applied Mechanics and Materials (Volumes 457-458)
• Pages: 1012-1016
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.457-458.1012
• Online since: October 2013
• Authors: Ying Wang*, Daniel Ewert, Daniel Schilberg, Sabina Jeschke
• Keywords:

  Found Keywords

  Digital Image

  , Data Fusion, Edge Extraction, Point Cloud

References

[1] A. Mohammad, A. Alamouri, S. Jeschke, A MDV-Based approach for appearance enhancement of historical images,  Automation, Communication and Cybernetics in Science and Engineering, (2013) 545-557.

DOI: 10.1007/978-3-642-33389-7_43

[2] I. Abdou, W. Pratt, Quantitative methods of edge detection, Proceedings of the IEEE, 67(1979) 753-763.

[3] S. Gumhold, X. Wang, R. MacLeod, Feature extraction from point clouds, Proceedings of 10th international meshing roundtable, 2001(2001).

[4] J. Ryde, J.A. Delmerico, Extracting edge voxels from 3D volumetric maps to reduce map size and accelerate mapping alignment, Computer and Robot Vision (CRV), 2012 Ninth Conference on. IEEE, (2012) 330-337.

DOI: 10.1109/crv.2012.50

[5] J. Cao, et al., Sharp feature extraction in point clouds, IET Image Processing, 7 (2012) 863-869.

[6] M. Sonka, V. Hlavac, R. Boyle, Image Processing, Analysis, and Machine Vision, Thomson-Engineering, pp.124-129, (2007).

[7] OpenCV. org, http: /docs. opencv. org/doc/tutorials/imgproc/imgtrans/canny_detector/canny_detector. html < last visited: 2013/08/01: 11: 10 >.

[8] G. Bradski, A. Kaehler, Learning OpenCV: Computer Vision with the OpenCV Library, O'Reilly, pp.151-153, (2008).

[9] B. Steder, R. B. Rusu, K. Konolige, W. Burgard, Point feature extraction on 3D range scans taking into account object boundaries, The IEEE International Conference on Robotics and Automation (ICRA), (2011).

DOI: 10.1109/icra.2011.5980187

[10] PCL, http: /www. pointclouds. org/documentation/tutorials/, < last visited: 2013/08/01: 14: 18 >.