this is for holding javascript data
Volker Strobel edited abstract.tex
over 7 years ago
Commit id: 32b810037dcd648eb277e274d8297d02700fb6d1
deletions | additions
diff --git a/abstract.tex b/abstract.tex
index 56d3af9..a902aa5 100644
--- a/abstract.tex
+++ b/abstract.tex
...
issue, this thesis describes an efficient vision-based onboard localization
technique. Using machine learning, a light-weight approach is developed that estimates $x,y$-coordinates within a known, modifiable indoor environment. The computational power of the approach is scalable to different platforms, trading off speed and accuracy.
The proposed system employs
textons as image features. Textons are small Histograms of textons---small characteristic image
patches; their histograms are patches---are used as features
for the in a $k$-Nearest Neighbors ($k$NN) algorithm. The outputs of this regression technique--multiple possible
$x, y$-coordinates are
used in forwarded to a particle filter to neatly aggregate
and smooth the estimates.
%Promising results were obtained for all tasks:
%waypoint navigation, accurate landing, and stable hovering in the
%indoor environment.
To predict the performance of the proposed algorithm in different environments, an evaluation
technique is developed that compares actual
texton histogram similarities to
ideal histogram similarities based on the distance between the underlying
positions. $x,y$-positions. The technique assigns a loss value to a given set of
images, allowing for comparing different environments and positions withing the environment. A software tool creates synthetic images
that could be taken during an actual flight. Using 46 high-resolution images, the synthetic flight images are used to compare their potential as ``map''.
...
%to compare their performance in the real-world. In fact, the results
%could be replicated on these maps.
The
presented approach is based on three pillars: (i) a shift of processing power to an pre-flight phase to pre-compute
computationally complex steps, (ii) lightweight and adaptable algorithms to ensure real-time performance and portability to different platforms,
(iii) modifiable environments that can be tailored to the proposed algorithm.