Advertisement

Hierarchical Denoising Method of Crop 3D Point Cloud Based on Multi-view Image Reconstruction

  • Lei Chen
  • Yuan YuanEmail author
  • Shide Song
Conference paper
Part of the IFIP Advances in Information and Communication Technology book series (IFIPAICT, volume 545)

Abstract

Since the advantages of low cost and high efficiency, the three dimensional point cloud reconstruction based on multi-view image sequence and stereo matching has been widely used in agriculture. However, the reconstructed three dimensional point cloud often contains a lot of noise data because of the complex morphology of crop. In order to improve the precision of three dimensional point cloud reconstruction, the paper proposed a hierarchical denoising method which first adopts the density clustering to deal with the large scale outliers, combined with crop morphology analysis, and then smooths the small scale noise with fast bilateral filtering. Two crops of rice and cucumber were taken to validate the method in the experiments. The results demonstrated that the proposed method can achieve better denoising results while preserving the integrity of the boundary of crop 3D model.

Keywords

Denoising 3D point cloud Multi-view Image processing Crop 

Notes

Acknowledgments

The work is supported by the National Natural Science Foundation of China under No. 31501223 and No. 31871521.

References

  1. 1.
    Liu, G., Si, Y., Feng, J.: 3D reconstruction of agriculture and forestry crops. Trans. Chin. Soc. Agric. Mach. 45(6), 38–46, 19 (2014). (in Chinese)Google Scholar
  2. 2.
    Yuan, X., Wen, W., Guo, X., Wang, C.: 3-dimentional morphology simulation of tomato canopy-based on measured data. J. Chin. Agric. Mech. Res. 34(2), 172–176 (2012). (in Chinese)CrossRefGoogle Scholar
  3. 3.
    Ma, Y., Guo, Y., Li, B.: Azimuthal distribution of maize plant leaves determined by 3D digitizer. Acta Agron. Sin. 32(6), 791–798 (2006). (in Chinese)Google Scholar
  4. 4.
    Fang, H., Hu, L., He, R., He, Y.: Research on plant 3-D information acquisition method. Trans. Chin. Soc. Agric. Eng. 28(3), 142–147 (2012). (in Chinese)Google Scholar
  5. 5.
    Paulus, S., Schumann, H., Kuhlmann, H., Léon, J.: High-precision laser scanning system for capturing 3D plant architecture and analysing growth ofcereal plants. Biosys. Eng. 121(18), 1–11 (2014)CrossRefGoogle Scholar
  6. 6.
    Alenyà, G., Dellen, B., Foix, S., Torras, C.: Robotized plant probing: leaf segmentation utilizing time-of-fight data. IEEE Robot. Automat. Mag. 20(3), 50–59 (2013)CrossRefGoogle Scholar
  7. 7.
    He, D., Shao, X., Wang, D., Hu, S.: Denoising method of 3-D point cloud data of plants obtained by Kinect. Trans. Chin. Soc. Agric. Mach. 47(1), 331–336 (2016). (in Chinese)Google Scholar
  8. 8.
    Hu, P., Guo, Y., Li, B., Zhu, J., Ma, Y.: Three-dimensional reconstruction of plant architecture based on multiple view stereo method and accuracy evaluation. Trans. Chin. Soc. Agric. Eng. 31(11), 209–214 (2015). (in Chinese)Google Scholar
  9. 9.
    Yang, L., Guo, X., Lu, S., Zhao, C.: 3D morphological reconstruction of cucumber leaf based on multiple images. Trans. Chin. Soc. Agric. Eng. 25(2), 141–144 (2009)Google Scholar
  10. 10.
    Hayashi, S., et al.: Evaluation of a strawberry-harvesting robot in a field test. Biosys. Eng. 105(2), 160–171 (2010)CrossRefGoogle Scholar
  11. 11.
    Fleishman, S., Drori, I., Cohen-Or, D.: Bilateral mesh denoising. ACM Trans. Graph. 22(3), 950–953 (2003)CrossRefGoogle Scholar
  12. 12.
    Zheng, Y., Fu, H., Au, O.K., Tai, C.: Bilateral normal filtering for mesh denoising. IEEE Trans. Vis. Comput. Graph. 17(10), 1521–1530 (2011)CrossRefGoogle Scholar
  13. 13.
    Dutta, S., Banerjee, S., Biswas, P.K., Bhowmick, P.: Mesh denoising by improved 3d geometric bilateral filter. In: Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics, pp. 1–4 (2013)Google Scholar
  14. 14.
    Lange, C., Polthier, K.: Anisotropic smoothing of point sets. Comput. Aided Geom. Des. 22(7), 680–692 (2005)MathSciNetCrossRefGoogle Scholar
  15. 15.
    Jalba, A., Roerdink, J.B.T.M.: Efficient surface reconstruction from noisy data using regularized membrane potentials. IEEE Trans. Image Process. 18(5), 1119–1134 (2009)MathSciNetCrossRefGoogle Scholar
  16. 16.
    Wang, X., Li, Z., Ma, Y., Zhang, X., Wang, Y., Sun, Y.: Robust denoising of unorganized point clouds. In: IEEE Conference Anthology, pp. 1–3 (2013)Google Scholar
  17. 17.
    Yu, J., Wei, M., Qin, J., Wu, J., Heng, P.A.: Feature-preserving mesh denoising via normal guided quadric error metrics. Opt. Lasers Eng. 62(6), 57–68 (2014)CrossRefGoogle Scholar
  18. 18.
    Zaman, F., Wong, Y., Ng, B.: Density-based denoising of point cloud. CoRR abs/1602.05312 (2016)Google Scholar
  19. 19.
    Ester, M., Kriegel, H., Sander, J., Xu, X.: A density-based algorithm for discovering clusters in large spatial databases with noise. In: Proceedings of the Second International Conference on Knowledge Discovery and Data Mining (KDD 1996), Portland, Oregon, USA, pp. 226–231 (1996)Google Scholar
  20. 20.
    Paris, S., Durand, F.: A fast approximation of the bilateral filter using a signal processing approach. Int. J. Comput. Vis. 81(1), 24–52 (2009)CrossRefGoogle Scholar
  21. 21.
    Özyesil, O., Voroninski, V., Basri, R., Singer, A.: A survey on structure from motion. CoRR abs/1701.08493 (2017)Google Scholar
  22. 22.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)MathSciNetCrossRefGoogle Scholar
  23. 23.
    Bradley, D., Boubekeur, T., Heidrich, W.: Accurate multi-view reconstruction using robust binocular stereo and surface meshing. In: 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2008), Anchorage, Alaska, USA, 24–26 June 2008, pp. 1–8 (2008)Google Scholar
  24. 24.
    Yang, Z., Xiao, D.: A systemic point-cloud de-noising and smoothing method for 3D shape reuse. In: 12th International Conference on Control Automation Robotics and Vision, ICARCV 2012, Guangzhou, China, 5–7 December 2012, pp. 1722–1727 (2012)Google Scholar
  25. 25.
    Li, P., Wu, H., Jing, J., Li, R.: Noise classification denoising algorithm for point cloud model. Comput. Eng. Appl. 52(20), 188–192 (2016). (in Chinese)Google Scholar

Copyright information

© IFIP International Federation for Information Processing 2019

Authors and Affiliations

  1. 1.Institute of Intelligent MachinesChinese Academy of SciencesHefeiChina
  2. 2.School of MicroelectronicsUniversity of Chinese Academy of SciencesBeijingChina

Personalised recommendations