![](bg9.png)
adaptiveness. The latter allows for the subsequent in-
tegration of additional 3D feature descriptors while
the system is already running in an application sce-
nario. Our approach proved to be able to preserve
classification strategies that have been learned so far
and at the same time to smoothly integrate new de-
scriptors in already learned strategies. The adaptive-
ness of the proposed self-learning approach enhances
the flexibility of a 3D object classification system con-
siderably, as new feature descriptors will be devel-
oped in the future and the learning process for a spe-
cial application scenario does not have to be started
from scratch again.
REFERENCES
Andreopoulos, A. and Tsotsos, J. K. (2013). 50 years of ob-
ject recognition: Directions forward. Computer Vision
and Image Understanding, 117(8):827–891.
Arthur, D. and Vassilvitskii, S. (2007). k-means++: the ad-
vantages of careful seeding. In Proceedings of the
Eighteenth Annual ACM-SIAM Symposium on Dis-
crete Algorithms,, pages 1027–1035.
Ciresan, D. C., Meier, U., and Schmidhuber, J. (2012).
Multi-column deep neural networks for image classi-
fication. In 2012 IEEE Conference on Computer Vi-
sion and Pattern Recognition, Providence, USA, June
16-21, 2012, pages 3642–3649.
Csurka, G., Dance, C., Fan, L., Willamowski, J., and Bray,
C. (2004). Visual categorization with bags of key-
points. In Workshop on statistical learning in com-
puter vision, ECCV, volume 1, pages 1–2. Prague.
Filipe, S. and Alexandre, L. A. (2014). A comparative
evaluation of 3d keypoint detectors in a RGB-D ob-
ject dataset. In VISAPP 2014 - Proceedings of the 9th
International Conference on Computer Vision Theory
and Applications, Volume 1,, pages 476–483.
Garstka, J. (2016). Learning strategies to select point cloud
descriptors for large-scale 3-D object classification.
PhD thesis, FernUniversit
¨
at in Hagen.
Garstka, J. and Peters, G. (2016). Evaluation of local 3-d
point cloud descriptors in terms of suitability for ob-
ject classification. In ICINCO 2016 - 13th Int. Conf.
on Informatics in Control, Automation and Robotics,
Volume 2.
Guo, Y., Bennamoun, M., Sohel, F. A., Lu, M., and Wan, J.
(2014). 3d object recognition in cluttered scenes with
local surface features: A survey. IEEE Trans. Pattern
Anal. Mach. Intell., 36(11):2270–2287.
Joachims, T. (1998). Text categorization with suport vector
machines: Learning with many relevant features. In
Machine Learning: ECML-98, 10th European Con-
ference on Machine Learning,, pages 137–142.
Johnson, A. E. and Hebert, M. (1998). Surface matching
for object recognition in complex three-dimensional
scenes. Image Vision Comput., 16(9-10):635–651.
Lai, K., Bo, L., Ren, X., and Fox, D. (2011). A large-
scale hierarchical multi-view RGB-D object dataset.
In IEEE International Conference on Robotics and
Automation,, pages 1817–1824.
Li, J. and Allinson, N. M. (2008). A comprehensive review
of current local features for computer vision. Neuro-
computing, 71(10-12):1771–1787.
Loncomilla, P., Ruiz-del-Solar, J., and Mart
´
ınez, L. (2016).
Object recognition using local invariant features for
robotic applications. Pattern Recognition, 60:499–
514.
Madry, M., Ek, C. H., Detry, R., Hang, K., and Kragic,
D. (2012). Improving generalization for 3d object
categorization with global structure histograms. In
2012 IEEE/RSJ International Conference on Intelli-
gent Robots and Systems,, pages 1379–1386.
Rusu, R. B., Blodow, N., and Beetz, M. (2009). Fast
point feature histograms for 3d registration. In 2009
IEEE International Conference on Robotics and Au-
tomation, ICRA 2009, Kobe, Japan, May 12-17, 2009,
pages 3212–3217.
Rusu, R. B., Blodow, N., Marton, Z. C., and Beetz, M.
(2008). Aligning point cloud views using persis-
tent feature histograms. In 2008 IEEE/RSJ Interna-
tional Conference on Intelligent Robots and Systems,
September 22-26, 2008, Acropolis Convention Center,
Nice, France, pages 3384–3391.
Salti, S., Tombari, F., and Stefano, L. D. (2011). A per-
formance evaluation of 3d keypoint detectors. In
3D Imaging, Modeling, Processing, Visualization
and Transmission, 2011 International Conference on,
pages 236–243. IEEE.
Sun, Z., Bebis, G., and Miller, R. (2006). On-road vehicle
detection: A review. IEEE Trans. Pattern Anal. Mach.
Intell., 28(5):694–711.
Sutton, R. S. and Barto, A. G. (1998). Reinforcement learn-
ing: An introduction. IEEE Trans. Neural Networks,
9(5):1054–1054.
Tombari, F., Salti, S., and Di Stefano, L. (2010a). Unique
shape context for 3d data description. In Proceedings
of the ACM workshop on 3D object retrieval, pages
57–62. ACM.
Tombari, F., Salti, S., and di Stefano, L. (2010b). Unique
signatures of histograms for local surface description.
In 11th European Conference on Computer Vision
(ECCV), 2010, Proceedings, Part III, pages 356–369.
Watkins, C. J. C. H. and Dayan, P. (1992). Technical note
q-learning. Machine Learning, 8:279–292.
Yang, Y., Yan, G., Zhu, H., Fu, M., and Wang, M. (2014).
Object segmentation and recognition in 3d point cloud
with language model. In Int. Conf. Multisensor Fu-
sion & Information Integration for Intelligent Sys-
tems,, pages 1–6.
Zhong, Y. (2009). Intrinsic shape signatures: A shape de-
scriptor for 3d object recognition. In 12th Interna-
tional Conference on Computer Vision (ICCV Work-
shops), pages 689–696. IEEE.
Self-Learning 3D Object Classification
519