Geoscience Reference
In-Depth Information
quadrilateral), which allows us to hereafter develop a new
filter capable of discard a
larger set of false positives.
The achieved results allow us to conclude that the proposed method is valid for
scenarios similar to those where we conducted our experiences. Other improve-
ments can be performed, which are de
ned in the next section.
8 Future Work
Future work will address issues related to system performance, POI match outcome
and further experiments. Regarding performance, although the SURF algorithm has
presented good results, it would be important to test the ORB detector, which
theoretically can perform more analysis per second with the same success rate.
Regarding POI match outcome, a new
filter should be tested that detects the current
false positive situations by discarding concave quadrilaterals. Finally, further
experiments are recommended with distinct light conditions, for instance, higher
luminosity, and a higher density of POIs to detect, in order to verify the system
accuracy and performance.
References
1. Wing M, Eklund A (2007) Performance comparison of a low-cost mapping grade global
positioning systems (GPS) receiver and consumer grade GPS receiver under dense forest
canopy. J For 105:9
14
2. Monico J (2000) Posicionamento pelo NAVSTAR-GPS. Editora UNESP, S
-
ã
o Paulo
3. Diggelen F (2009) A-GPS
Assisted GPS, GNSS and SBAS. Artech House, Boston
4. Figueiras J, Frattasi S (2010) Mobile positioning and tracking:
—
from conventional
to
cooperative techniques. Wiley, London
5. Bernal J, Vilari
ñ
oF,S
á
nchez J (2010) Feature detectors and feature descriptors: where we are
now. Universitat Autonoma de Barcelona, Barcelona
6. Lowe DG (1999) Object recognition from local scale-invariant features. In: The proceedings
of the seventh IEEE international conference on computer vision, 1999, 20
-
27 Sept 1999,
pp 1150
-
1157
7. Bay H, Tuytelaars T, Van Gool L (2006) SURF: speeded up robust features. In: Computer
vision-ECCV, Springer, Graz, 7
417
8. Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. Computer
vision and pattern recognition (CVPR 2005), San Diego, 25 June 2005, pp 886
13 May 2006, pp 404
-
-
893
9. Juan L, Gwun O (2009) A comparison of SIFT, PCA-SIFT and SURF. Int J Image Process
3:143
-
152
10. Rublee E, Rabaud V, Konolige K, Bradski G (2011) ORB: an efficient alternative to SIFT or
SURF. International conference on computer vision, Barcelona
-
Search WWH ::
Custom Search