Advertisement

A Research for Reconstructing 3D Object by Using an RGB-D Camera

  • Van Sinh NguyenEmail author
  • Manh Ha Tran
  • Quang Minh Anh Le
Conference paper
  • 186 Downloads
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1014)

Abstract

Reconstruction of 3D objects and their application in practice is more and more studying. The input data are acquired from different devices and techniques. They are processed based on geometric modeling, image processing techniques, and computer graphics. The output data are 3D models that represent their initial shapes of the real-world objects. This paper presents research for reconstructing the 3D objects by using an RGB-D camera. The main contribution of the paper includes studying and analyzing several methods to reconstruct a 3D object from a set of 3D point clouds acquired from different devices. Our proposed method is then performed based on a combination of geometric modeling and images processing to build a 3D model of an object from a set of noisy 3D point clouds. We have also implemented and compared obtained results between the methods to determine the most suitable in term of precision and robustness on noisy real data captured by the Microsoft Kinect.

Keywords

Geometric modeling RGB-D camera 3D point clouds Voxel grid filter Cluster removal Plane segmentation Registration process 

References

  1. 1.
    Dzenan, L., Jasmin, V., Haris, B.: Framework for automated reconstruction of 3D model from multiple 2D aerial images. In: International Symposium ELMAR, pp. 173–176 (2017)Google Scholar
  2. 2.
    Sinh, N.V., Ha, M.T., Quang, V.H.M.: A research on 3D model construction from 2D Dicom. In: Proceedings of International Conference on Advanced Computing and Applications (ACOMP) 2016, pp. 158–163. IEEE ISBN: 978-1-5090-6143-3 (2016)Google Scholar
  3. 3.
    Sinh, N.V., Ha, M.T., Minh, T.K.: Filling holes on the surface of 3D point clouds based on reverse computation of Bezier curves. In: Information Systems Design and Intelligent Applications, Advances in Intelligent Systems and Computing, pp. 334–345. ISSN: 2194-5357 (2018)Google Scholar
  4. 4.
    Izadi, S., Kim, D., Hilliges, O., Molyneaux, D., Newcombe, R., Kohli, P., Shotton, J., Hodges, S., Freeman, D., Davison, A., Fitzgibbon, A.: Kinectfusion: Real-time 3D reconstruction and interaction using a moving depth camera. In: Proceedings of the 24th annual ACM symposium on User interface software and technology, pp. 559–568. ACM, New York (October 2011)Google Scholar
  5. 5.
    Zollhofer, M., Siegl, C., Ri_elmacher, B., Vetter, M., Dreyer, B., Stamminger, M., Bauer, F.: Low-cost real-time 3D reconstruction of large-scale excavation sites using an RGB-D camera. In: Workshops on Graphics and Cultural Heritage, pp. 01–10. EUROGRAPHICS (2014)Google Scholar
  6. 6.
    Kajal, S.: Kinect sensor based object feature estimation in depth images. Int. J. Sign. Process. Image Process. Patt. Recogn. 8(12), 237–246 (2015)Google Scholar
  7. 7.
    Shih-Wen, H., Yi-Cheng, T.: Applying multiple kinect on the development of a rapid 3D mannequin scan platform. Int. J. Mech. Mecha. Eng. 10(7), 1199–1023 (2016)Google Scholar
  8. 8.
    Meyer, G.P., Minh, N.D.: Real-time 3D face modeling with a commodity depth camera. In: IEEE International Conference on Multimedia and Expo Workshops, pp. 1–4 (2013)Google Scholar
  9. 9.
    Chen, X., Wu, Q., Wang, S.: Research on 3D reconstruction based on multiple views. In: The 13th International Conference on Computer Science & Education (ICCSE 2018), pp. 269–273, ISSN: 2473-9464 (2018)Google Scholar
  10. 10.
    Nizami, I.F., et al.: Impact of feature selection algorithms on blind image quality assessment. Arab. J. Sci. Eng. 43(8), 4057–4070 (2018)Google Scholar
  11. 11.
    Bhateja, V., et al.: A reduced reference distortion measure for performance improvement of smart cameras. IEEE Sens. J. 15(5), 2531–2540 (2015)Google Scholar
  12. 12.
    Xie, J., Hsu, Y.F., Feris, R.S., Sun, M.T.: Fine registration of 3D point clouds fusing structural and photometric information using an RGB-D camera. 32, 194–204 (2015)Google Scholar
  13. 13.
    Ying, H., Bin, L., Jun, Y., Shunzhi, L., Jin, H.: An iterative closest points algorithm for registration of 3D laser scanner point clouds with geometric features. J. Sens. - MDPI 17(8) (2017)Google Scholar
  14. 14.
    Michael, K., Matthew, B., Hugues, H.: Poisson surface reconstruction. In: Proceedings of the fourth Eurographics Symposium on Geometry processing, pp. 61–70 (2006)Google Scholar
  15. 15.
    ISTI. The Italian National Research Council. http://www.meshlab.net/ (2018)
  16. 16.
    Moreno, C., Li, M.: A comparative study of filtering methods for point clouds in real-time video streaming. In: Proceedings of the World Congress on Engineering and Computer Science Vol I WCECS 2016, pp. 388–393. ISBN: 978-988-14047-1-8 (2016)Google Scholar
  17. 17.
    Point clouds. Point cloud library (PCL). http://pointclouds.org. (2018)
  18. 18.
    Michael, Y.Y., Wolfgang, F.: Plane detection in point cloud data. In: Technical Report Nr. 1 (2010)Google Scholar
  19. 19.
    Pujol-Miro, A., Ruiz-Hidalgo, J., Casas, J.R.: Registration of images to unorganized 3D point clouds using contour cues. In: 25th European Signal Processing Conference (EUSIPCO), pp. 91–95. ISBN: 978-0-9928626-7-1 (2017)Google Scholar
  20. 20.
    Jacek, N., Marek, K., Michat, D.: 3D face data acquisition and modelling based on an RGBD camera matrix. In: The 8th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications, pp. 157–160 (2015)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Van Sinh Nguyen
    • 1
    Email author
  • Manh Ha Tran
    • 1
  • Quang Minh Anh Le
    • 1
  1. 1.School of Computer Science and EngineeringInternational University of HCMCHo Chi Minh CityVietnam

Personalised recommendations