Skip to main content
Log in

Performance Evaluation of 3D Keypoint Detectors

  • Published:
International Journal of Computer Vision Aims and scope Submit manuscript

Abstract

In the past few years detection of repeatable and distinctive keypoints on 3D surfaces has been the focus of intense research activity, due on the one hand to the increasing diffusion of low-cost 3D sensors, on the other to the growing importance of applications such as 3D shape retrieval and 3D object recognition. This work aims at contributing to the maturity of this field by a thorough evaluation of several recent 3D keypoint detectors. A categorization of existing methods in two classes, that allows for highlighting their common traits, is proposed, so as to abstract all algorithms to two general structures. Moreover, a comprehensive experimental evaluation is carried out in terms of repeatability, distinctiveness and computational efficiency, based on a vast data corpus characterized by nuisances such as noise, clutter, occlusions and viewpoint changes.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18

Similar content being viewed by others

Notes

  1. www.graphics.stanford.edu/data/3Dscanrep.

  2. www.csse.uwa.edu.au/~ajmal.

  3. vision.deis.unibo.it/SHOT.

  4. svn://scm.gforge.inria.fr/svn/mvviewer.

  5. http://geomtop.org/software/hks.html.

  6. http://www.caam.rice.edu/software/ARPACK/.

  7. http://www.cise.ufl.edu/research/sparse/umfpack/.

  8. The requirement of 16 GB of RAM for 100 K vertices was confirmed by personal communication with the authors.

  9. Recently, the detector proposed in Novatnack and Nishino (2008) has been used (Bariya and Nishino 2010) for object recognition on the Laser Scanner dataset by synthesizing range images from a number of uniformly distributed overlapping views of the 3D model of the object. This technique is not suitable for our experimental comparison because the performance of detectors working on range images will be influenced by external factors such as synthetic views position and distribution.

  10. As MeshDoG implements a non-linear scale increment within its scale-space, we tuned its scale-space parameters so as to best approximate the same scale set used by the other methods.

References

  • Akagunduz, E., & Ulusoy, I. (2007). 3D object representation using transform and scale invariant 3D features. In Proc. int. conf. on computer vision (ICCV) (pp. 1–8).

    Google Scholar 

  • Akgül, C., Sankur, B., Yemez, Y., & Schmitt, F. (1992). 3D model retrieval using probability density-based shape descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(6), 1117–1133.

    Article  Google Scholar 

  • Bariya, P., & Nishino, K. (2010). Scale-hierarchical 3D object recognition in cluttered scenes. In Proc. int. conf. on computer vision and pattern recognition (CVPR) (pp. 1657–1664).

    Google Scholar 

  • Beis, J., & Lowe, D. (1997). Shape indexing using approximate nearest-neighbour search in high dimensional spaces. In Proc. int. conf. on computer vision and pattern recognition (CVPR) (pp. 1000–1006).

    Chapter  Google Scholar 

  • Boyer, E., Bronstein, A. M., Bronstein, M. M., Bustos, B., Darom, T., Horaud, R., Hotz, I., Keller, Y., Keustermans, J., Kovnatsky, A., et al. (2011). SHREC 2011: robust feature detection and description benchmark. In Eurographics workshop on shape retrieval (vol. 2, pp. 79–86).

    Google Scholar 

  • Bronstein, M., & Kokkinos, I. (2010). Scale-invariant heat kernel signatures for non-rigid shape recognition. In Proc. int. conf. on computer vision and pattern recognition (pp. 1704–1711).

    Google Scholar 

  • Bronstein, A. M., Bronstein, M. M., Bustos, B., Castellani, U., Crisani, M., Falcidieno, B., Guibas, L. J., Kokkinos, I., Murino, V., Ovsjanikov, M., Patané, G., Sipiran, I., Spagnuolo, M., & Sun, J. (2010). SHREC 2010: robust feature detection and description benchmark. In EUROGRAPHICS workshop on 3D object retrieval (3DOR).

    Google Scholar 

  • Castellani, U., Cristani, M., & Fantoni, S. (2008). Sparse points matching by combining 3D mesh saliency with statistical descriptors. In Proc computer graphics forum (pp. 643–652).

    Google Scholar 

  • Chen, H., & Bhanu, B. (2007). 3D free-form object recognition in range images using local surface patches. Pattern Recognition Letters, 28(10), 1252–1262.

    Article  Google Scholar 

  • Chua, C. S., & Jarvis, R. (1997). Point signatures: a new representation for 3D object recognition. International Journal of Computer Vision, 25(1), 63–85.

    Article  Google Scholar 

  • D’Errico, J. (2010). Surface fitting using gridfit. MATLAB Central File Exchange.

  • Dorai, C., & Jain, A. (1997). Cosmos-a representation scheme for 3D free-form objects. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(10), 1115–1130.

    Article  Google Scholar 

  • Fadaifard, H., & Wolberg, G. (2011). Multiscale 3D feature extraction and matching. In Proc. int. conf. on 3D imaging, modeling, processing, visualization and transmission (3DIMPVT) (pp. 228–235).

    Chapter  Google Scholar 

  • Frome, A., Huber, D., Kolluri, R., Bülow, T., & Malik, J. (2004). Recognizing objects in range data using regional point descriptors. In Proc. Europ. conf. on computer vision (ECCV) (vol. 3, pp. 224–237).

    Google Scholar 

  • Johnson, A., & Hebert, M. (1999). Using spin images for efficient object recognition in cluttered 3D scenes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 21(5), 433–449.

    Article  Google Scholar 

  • Katz, S., Tal, A., & Basri, R. (2007). Direct visibility of point sets. ACM Trans on Graphics, 26(3) 24.

    Google Scholar 

  • Knopp, J., Prasad, M., Willems, G., Timofte, R., & Van Gool, L. (2010). Hough transform and 3D SURF for robust three dimensional classification. In Proc. Europ. conf. on computer vision (ECCV).

    Google Scholar 

  • Lindeberg, T. (1998). Feature detection with automatic scale selection. International Journal of Computer Vision, 30(2), 79–116.

    Article  Google Scholar 

  • Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2), 91–110.

    Article  Google Scholar 

  • Mian, A. S., Bennamoun, M., & Owens, R. A. (2010). On the repeatability and quality of keypoints for local feature-based 3D object retrieval from cluttered scenes. International Journal of Computer Vision, 89(2–3), 348–361.

    Article  Google Scholar 

  • Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., & Van Gool, L. (2005). A comparison of affine region detectors. International Journal of Computer Vision, 65(1–2), 43–72.

    Article  Google Scholar 

  • Moreels, P., & Perona, P. (2007). Evaluation of features detectors and descriptors based on 3D objects. International Journal of Computer Vision, 73(3), 263–284.

    Article  Google Scholar 

  • Novatnack, J., & Nishino, K. (2007). Scale-dependent 3D geometric features. In Proc. int. conf. on computer vision (ICCV) (pp. 1–8).

    Google Scholar 

  • Novatnack, J., & Nishino, K. (2008). Scale-dependent/invariant local 3D shape descriptors for fully automatic registration of multiple sets of range images. In Proc. Europ. conf. on computer vision (ECCV) (pp. 440–453).

    Google Scholar 

  • Salti, S., Tombari, F., & Di Stefano, L. (2010). On the use of implicit shape models for recognition of object categories in 3D data. In Proc. Asian conf. on computer vision (ACCV) (pp. 653–666).

    Google Scholar 

  • Salti, S., Tombari, F., & Di Stefano, L. (2011). A performance evaluation of 3D keypoint detectors. In Proc. int. conf. on 3D imaging, modeling, processing, visualization and transmission (3DIMPVT) (pp. 236–243).

    Chapter  Google Scholar 

  • Schmid, C., Mohr, R., & Bauckhage, C. (2000). Evaluation of interest point detectors. International Journal of Computer Vision, 37(2), 151–172.

    Article  MATH  Google Scholar 

  • Shang, L., & Greenspan, M. (2010). Real-time object recognition in sparse range images using error surface embedding. International Journal of Computer Vision, 89(2–3), 211–228.

    Article  Google Scholar 

  • Shilane, P., Min, P., Kazhdan, M., & Funkhouser, T. (2004). The Princeton shape benchmark. In Proc. shape modeling international (pp. 167–178).

    Google Scholar 

  • Sun, J., Ovsjanikov, M., & Guibas, L. (2009). A concise and provably informative multi-scale signature based on heat diffusion. In Proc. Eurographics symposium on geometry processing (SGP) (pp. 1383–1392).

    Google Scholar 

  • Tombari, F., Salti, S., & Di Stefano, L. (2010). Unique signatures of histograms for local surface description. In Proc. Europ. conf. on computer vision (ECCV) (pp. 356–369). Berlin: Springer.

    Google Scholar 

  • Unnikrishnan, R., & Hebert, M. (2008). Multi-scale interest regions from unorganized point clouds. In Proc. workshop on search in 3D (S3D) (pp. 1–8).

    Google Scholar 

  • Yoshizawa, S., Belyaev, A., & Seidel, H. P. (2004). A fast and simple stretch-minimizing mesh parameterization. In Proc. shape modeling and applications (pp. 200–208).

    Chapter  Google Scholar 

  • Zaharescu, A., Boyer, E., Varanasi, K., & Horaud, R. (2009). Surface feature detection and description with applications to mesh matching. In Proc int conf on computer vision and pattern recognition (CVPR) (pp. 373–380).

    Google Scholar 

  • Zhong, Y. (2009). Intrinsic shape signatures: a shape descriptor for 3D object recognition. In Proc. int. conf. on computer vision workshops (pp. 1–8).

    Google Scholar 

Download references

Acknowledgements

The authors would like to thank Dr. Andrei Zaharescu, Dr. Jian Sun and Dr. Umberto Castellani for sharing the code of their proposals and being always kindly ready to answer our doubts and recall some details that were essential for carrying out this evaluation. The authors would also like to thank Maurizio Galassi, who assisted them in adapting the SP detector to their evaluation framework, Filippo Pulga, who helped providing the C++ implementation of several detectors, and Thomas Ricci, who worked hard to port to C++ the gridfit script.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Federico Tombari.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Tombari, F., Salti, S. & Di Stefano, L. Performance Evaluation of 3D Keypoint Detectors. Int J Comput Vis 102, 198–220 (2013). https://doi.org/10.1007/s11263-012-0545-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11263-012-0545-4

Keywords

Navigation