Advertisement

A Method for the 3D Reconstruction Based on Edge Detection and Feature Extraction

  • Liangcheng SuEmail author
  • Fei Jia
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8971)

Abstract

This paper presents a method for three-dimensional reconstruction from images that can be used to identify obstacles based on a single omnidirectional image obtained by an omnidirectional stereo vision optical device (OSVOD). The OSVOD is a novel catadioptric system based on a common perspective camera coupled with two hyperbolic mirrors. The images captured by OSVOD are unwrapped into cylinder panoramic images, which are then examined for stereo matching along vertical epiploar lines. Given two images of a space point obtained by this vision system, the 3D coordinates of the point can be calculated by using triangulation. An algorithm of the quick stereo matching method based on Canny edge and SIFT feature points is proposed and the result of 3D reconstruction and depth map are obtained. From the results, we can find that the 3D reconstruction accuracy can be accepted for mobile robots’ obstacle detection and navigation tasks.

Keywords

3D reconstruction Canny SIFT Stereo matching Catadioptric system 

Notes

Acknowledgment

This work was supported by the National Natural Science Foundation of China (No. 60905046).

References

  1. 1.
    Yang, L., Noguchi, N.: Human detection for a robot tractor using omni-directional stereo vision. Comput. Electron. Agric. 89(11), 116–125 (2012)CrossRefGoogle Scholar
  2. 2.
    Taheri, M., Dehkordi, M.N., Sharafi, M.: Control and analysis of an omnidirectional autonomous robot based on software approach and multimedia database. Control Eng. Appl. Inform. 14(2), 65–72 (2012)Google Scholar
  3. 3.
    Jia, T., Shi, Y., Zhou, Z.X., Chen, D.Y.: 3D depth information extraction with omni-directional camera. Inf. Process. Lett. 115(2), 285–291 (2015)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Su, L., Luo, C., Zhu, F.: Obtaining obstacle information by an omnidirectional stereo vision system. Int. J. Robot. Autom. 24(3), 222–227 (2009)Google Scholar
  5. 5.
    Sundareswara, R., Schrater, P.R.: Bayesian discounting of camera parameter uncertainty for optimal 3D reconstruction from images. Comput. Vis. Image Underst. 115, 117–126 (2011)CrossRefGoogle Scholar
  6. 6.
    Xiong, Z.-H., Cheng, I., Chen, W., Basu, A., Zhang, M.-J.: Depth space partitioning for omni-stereo object tracking. IET Comput. Vis. 6(2), 153–163 (2012)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Koyasu, H., Miura, J., Shirai, Y.: Mobile robot navigation in dynamic environments using omnidirectional stereo. In: Proceedings of 2003 IEEE International Conference on Robotics and Automation, pp. 893–898 (2003)Google Scholar
  8. 8.
    Banks, J., Corke, P.: Quantitative evaluation of matching methods and validity measures for stereo vision. Int. J. Robot. Res. 18, 512–532 (2001)CrossRefGoogle Scholar
  9. 9.
    Canny, J.: A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. 8(6), 679–698 (1986)CrossRefGoogle Scholar
  10. 10.
    Tian, C., Masry, M., Lipson, H.: Physical sketching: reconstruction and analysis of 3D objects from freehand sketches. Comput. Aided Des. 41, 147–158 (2009)CrossRefGoogle Scholar
  11. 11.
    Han, B., Paulson, C., Wu, D.: 3D dense reconstruction from 2D video sequence via 3D geometric segmentation. J. Vis. Commun. Image 22, 421–431 (2011)CrossRefGoogle Scholar
  12. 12.
    Hor, M.-K., Tang, C.-Y., Wu, Y.-L., Chan, K.-H., Tsai, J.-J.: Robust refinement methods for camera calibration and 3D reconstruction from multiple images. Pattern Recogn. Lett. 32, 1210–1221 (2011)CrossRefGoogle Scholar
  13. 13.
    Yuan, S., Tsui, L.Y., Jie, S.: Regularity selection for effective 3D object reconstruction from a single line drawing. Pattern Recogn. Lett. 29, 1486–1495 (2008)CrossRefGoogle Scholar
  14. 14.
    Kels, S., Dyn, N.: Reconstruction of 3D objects from 2D cross-sections with the 4-point subdivision scheme adapted to sets. Comput. Graph. 35, 741–746 (2011)CrossRefGoogle Scholar
  15. 15.
    Ducke, B., Score, D., Reeves, J.: Multiview 3D reconstruction of the archaeological site at Weymouth from image series. Comput. Graph. 35, 375–382 (2008)CrossRefGoogle Scholar
  16. 16.
    Liang, C., Wong, K.-Y.K.: 3D reconstruction using silhouettes from unordered viewpoints. Image Vis. Comput. 28, 579–589 (2010)CrossRefGoogle Scholar
  17. 17.
    Moura, D.C., Boisvert, J., Barbosa, J.G., Labelle, H., Tavares, J.M.: Fast 3D reconstruction of the spine from biplanar radiographs using a deformable articulated model. Med. Eng. Phys. 33, 924–933 (2011)CrossRefGoogle Scholar
  18. 18.
    Brilakis, I., Fathi, H., Rashidi, A.: Progressive 3D reconstruction of infrastructure with videogrammetry. Autom. Constr. 20, 884–895 (2011)CrossRefGoogle Scholar
  19. 19.
    Guemundsson, S.Á., Pardàs, M., Casas, J.R., Sveinsson, J.R., Aanæs, H., Larsen, R.: Improved 3D reconstruction in smart-room environments using ToF imaging. Comput. Vis. Image Underst. 114, 1376–1384 (2010)CrossRefGoogle Scholar
  20. 20.
    Wei, S.-K.: Stereo matching of catadiotpric panoramic images. Center for matching perception. Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University, CTU- CMP (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2015

Authors and Affiliations

  1. 1.Institute of Electrical EngineeringYanshan UniversityQinhuangdaoPeople’s Republic of China

Personalised recommendations