![](bg8.png)
environments are rich of planar, rectangular structu-
res. Therefore, we relied on the sensors of Microsofts
HoloLens to detect 3D planes and determined view-
point invariant planes. Finally, we computed SIFT
features and determined correspondences using two
viewpoint invariant planes.
In the future, we plan to overcome issues while
detecting visible planes. As we have shown in our
evaluation, it possible that we discard planes using our
greedy selection approach. Additionally, we plan a
more extensive evaluation of the system.
REFERENCES
Baatz, G., K
¨
oser, K., Chen, D., Grzeszczuk, R., and Polle-
feys, M. (2010). Handling urban location recognition
as a 2D homothetic problem. In Computer Vision –
ECCV 2010, volume 6316, pages 266–279.
Bay, H., Ess, A., Tuytelaars, T., and Van Gool, L. (2008).
Speeded-Up Robust Features (SURF). Comput. Vis.
Image Underst., 110(3):346–359.
Brown, M. and Lowe, D. G. (2007). Automatic panora-
mic image stitching using invariant features. In Int. J.
Comput. Vis., volume 74, pages 59–73. Kluwer Aca-
demic Publishers-Plenum Publishers.
Cai, G. R., Jodoin, P. M., Li, S. Z., Wu, Y. D., Su, S. Z.,
and Huang, Z. K. (2013). Perspective-SIFT: An effi-
cient tool for low-altitude remote sensing image regis-
tration. Signal Processing, 93(11):3088–3110.
Chen, M., Shao, Z., Li, D., and Liu, J. (2013). Invariant
matching method for different viewpoint angle ima-
ges. Appl. Opt., 52(1):96–104.
Donoser, M., Riemenschneider, H., and Bischof, H. (2010).
Shape guided Maximally Stable Extremal Region
(MSER) tracking. In Proc. - Int. Conf. Pattern Re-
cognit., pages 1800–1803.
Filax, M., Gonschorek, T., and Ortmeier, F. (2017). Quad-
SIFT: Unwrapping planar quadrilaterals to enhance
feature matching. In WSCG 2017 - Short Papers Pro-
ceedings, volume 25.
Hartley, R. and Zisserman, A. (2004). Multiple View Ge-
ometry in Computer Vision. Cambridge University
Press.
K
¨
oser, K. and Koch, R. (2007). Perspectively invariant nor-
mal features. Proc. IEEE Int. Conf. Comput. Vis.
Lowe, D. G. (1999). Object recognition from local scale-
invariant features. In Proc. Seventh IEEE Int. Conf.
Comput. Vis., volume 2, pages 1150–1157. Ieee.
Lowe, D. G. (2004). Distinctive image features from scale-
invariant keypoints. International journal of computer
vision, 60(2):91–110.
Matas, J., Chum, O., Urban, M., and Pajdla, T. (2002). Ro-
bust Wide Baseline Stereo from. Br. Mach. Vis. Conf.,
pages 384–393.
Matas, J., Chum, O., Urban, M., and Pajdla, T. (2004).
Robust wide-baseline stereo from maximally sta-
ble extremal regions. Image and vision computing,
22(10):761–767.
McDonald, J. (2009). Viewpoint invariant features from
single images using 3D geometry. 2009 Work. Appl.
Comput. Vis., pages 1–6.
Morel, J.-M. and Yu, G. (2009). ASIFT: A New Framework
for Fully Affine Invariant Image Comparison. SIAM
J. Imaging Sci., 2(2):438–469.
Nister, D., Naroditsky, O., and Bergen, J. (2006). Visual
odometry for ground vehicle applications. J. F. Robot.,
23(1):3–20.
Rublee, E., Rabaud, V., Konolige, K., and Bradski, G.
(2011). ORB: An efficient alternative to SIFT or
SURF. In Proc. IEEE Int. Conf. Comput. Vis., pages
2564–2571. IEEE.
Srajer, F., Schwing, A. G., Pollefeys, M., and Pajdla, T.
(2015). MatchBox: Indoor image matching via box-
like scene estimation. In Proc. - 2014 Int. Conf. 3D
Vision, 3DV 2014, pages 705–712.
Wu, C., Clipp, B., Li, X., Frahm, J. M., and Pollefeys, M.
(2008). 3D model matching with viewpoint-invariant
patches (VIP). 26th IEEE Conf. Comput. Vis. Pattern
Recognition, CVPR, pages 1–8.
Yu, G. and Morel, J. (2009). A fully affine invariant image
comparison method. Int. Conf. Acoust. Speech Signal
Process., 26(1):1597–1600.
Yu, G. and Morel, J.-M. (2011). ASIFT: An Algorithm for
Fully Affine Invariant Comparison. Image Processing
On Line, 1:11–38.
Yu, Y., Member, S. S., Huang, K., Member, S. S., Chen, W.,
Member, S. S., and Tan, T. (2012). A novel algorithm
for view and illumination invariant image matching.
IEEE Trans. Image Process., 21(1):229–40.
Yuille, A. L. and Coughlan, J. M. (2000). The Manhat-
tan World Assumption: Regularities in scene satistic
which enable Bayesian inference. NIPS - Neural Inf.
Process. Syst., pages 2–8.
VISAPP 2018 - International Conference on Computer Vision Theory and Applications
588