access icon free Energy minimisation-based multi-class multi-instance geometric primitives extraction from 3D point clouds

© The Institution of Engineering and Technology
Received 01/12/2019, Accepted 29/05/2020, Revised 03/05/2020, Published 03/06/2020

Geometric primitives contained in three-dimensional (3D) point clouds can provide the meaningful and concise abstraction of 3D data, which plays a vital role in improving 3D vision-based intelligent applications. However, how to efficiently and robustly extract multiple geometric primitives from point clouds is still a challenge, especially when multiple instances of multiple classes of geometric primitives are present. In this study, a novel energy minimisation-based algorithm for multi-class multi-instance geometric primitives extraction from the 3D point cloud is proposed. First, an improved sampling strategy is proposed to generate model hypotheses. Then, an improved strategy to establish the neighbourhood is proposed to help construct and optimise an energy function for points labelling. After that, hypotheses and parameters of models are refined. Iterate this process until the energy does not decrease. Finally, models of multi-class multi-instance geometric primitives are simultaneously and robustly extracted from the 3D point cloud. In comparison with the state-of-the-art methods, it can automatically determine the classes and numbers of geometric primitives in the 3D point cloud. Experimental results with synthetic and real data validate the proposed algorithm.

Inspec keywords: iterative methods; computer vision; feature extraction; minimisation; power aware computing; computational geometry

Other keywords: three-dimensional point clouds; 3D vision-based intelligent applications; energy minimisation; 3D point cloud; multiclass multiinstance geometric primitives extraction

Subjects: Numerical approximation and analysis; Computer vision and image processing techniques; Interpolation and function approximation (numerical analysis); Optimisation techniques; Electrical/electronic equipment (energy utilisation); Interpolation and function approximation (numerical analysis); Image recognition; Performance evaluation and testing; Optimisation techniques; Graphics techniques

References

    1. 1)
      • 14. Li, B., Liu, Q., Shi, X., et al: ‘Graph-based saliency fusion with superpixel-level belief propagation for 3D fixation prediction’. Proc. Int. Conf. on Image Processing, Athens, Greece, October 2018, pp. 2321–2325.
    2. 2)
      • 13. Zuliani, M., Kenney, C., Manjunath, B.: ‘The multiransac algorithm and its application to detect planar homographies’. Proc. Int. Conf. on Image Processing, Genoa, Italy, September 2005, pp. 2969–2972.
    3. 3)
      • 20. Wang, L., Yan, B., Duan, F., et al: ‘Extraction of multi-class multi-instance geometric primitives from point cloud using energy minimization’. Proc. Int. Conf. on Multimedia Modeling, Daejeon, South Korea, January 2020, pp. 279–290.
    4. 4)
      • 9. Toldo, R., Fusiello, A.: ‘Robust multiple structures estimation with J-linkage’. Proc. European Conf. on Computer Vision, Marseille, France, October 2008, pp. 537–547.
    5. 5)
      • 11. Vincent, E., Laganire, R.: ‘Detecting planar homographies in an image pair’. Proc. Int. Symp. on Image and Signal Processing and Analysis, Pula, Croatia, January 2001, pp. 182–187.
    6. 6)
      • 3. Borrmann, D., Elseberg, J., Lingemann, K., et al: ‘The 3D hough transform for plane detection in point clouds: a review and a new accumulator design’, 3D Res., 2011, 2, 3, pp. 1–13.
    7. 7)
      • 1. Rao, Y., Fan, B., Wang, Q., et al: ‘Extreme feature regions detection and accurate quality assessment for point-cloud 3D reconstruction’, IEEE Access, 2019, 7, pp. 37757–37769.
    8. 8)
      • 5. Wang, L., Shen, C., Duan, F., et al: ‘Energy-based multi-plane detection from 3D point clouds’. Proc. Neural Information Processing, Kyoto, Japan, October 2016, pp. 715–722.
    9. 9)
      • 12. Kanazawa, Y., Kawakami, H.: ‘Detection of planar regions with uncalibrated stereo using distributions of feature points’. Proc. British Machine Vision Conf., Kingston, UK, September 2004, pp. 247–256.
    10. 10)
      • 16. Boykov, Y., Jolly, M.: ‘Interactive graph cuts for optimal boundary and region segmentation of objects in ND images’. Proc. Int. Conf. on Computer Vision, Vancouver, Canada, July 2001, pp. 105–112.
    11. 11)
      • 17. Isack, H., Boykov, Y.: ‘Energy-based geometric multi-model fitting’, Int. J. Comput. Vis., 2012, 97, (2), pp. 123–147.
    12. 12)
      • 19. Farenzena, M.A., Fusiello, A., Gherardi, R.: ‘Structure-and-motion pipeline on a hierarchical cluster tree’. Proc. Int. Conf. on 3D Digital Imaging and Modeling, Kyoto, Japan, September 2009, pp. 1489–1496.
    13. 13)
      • 18. Barath, D., Matas, J.: ‘Multi-class model fitting by energy minimization and mode-seeking’. Proc. European Conf. on Computer Vision, Munich, Germany, September 2018, pp. 229–245.
    14. 14)
      • 2. Hough, V.C.P.: ‘Method and means for recognizing complex patterns’, US Pat. 3069654, 1962.
    15. 15)
      • 7. Myatt, D., Torr, P., Nasuto, S., et al: ‘NAPSAC: high noise, high dimensional robust estimation’. Proc. British Machine Vision Conf., Cardiff, UK, September 2002, pp. 458–467.
    16. 16)
      • 6. Wang, L., Shen, C., Duan, F., et al: ‘Energy-based automatic recognition of multiple spheres in three-dimensional point cloud’, Pattern Recognit. Lett., 2016, 83, (3), pp. 287–293.
    17. 17)
      • 15. Boykov, Y., Veksler, O., Zabih, R.: ‘Fast approximate energy minimization via graph cuts’, IEEE Trans. Pattern Anal. Mach. Intell., 2001, 23, (11), pp. 1222–1239.
    18. 18)
      • 8. Yang, Y., Li, B., Li, P., et al: ‘A two-stage clustering based 3d visual saliency model for dynamic scenarios’, IEEE Trans. Multimedia, 2019, 21, (4), pp. 809–820.
    19. 19)
      • 4. Fischler, M., Bolles, R.: ‘Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography’, Commun. ACM, 1981, 24, (6), pp. 381–395.
    20. 20)
      • 10. Toldo, R., Fusiello, A.: ‘Real-time incremental J-linkage for robust multiple structures estimation’. Proc. Int. Symp. on 3D Data Processing Visualization and Transmission, Paris, France, May 2010, pp. 1–6.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2019.1625
Loading

Related content

content/journals/10.1049/iet-ipr.2019.1625
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading