2024-03-19T11:59:27Zhttps://www.tdx.cat/oai/requestoai:www.tdx.cat:10803/3995872017-09-14T14:28:52Zcom_10803_381col_10803_387
nam a 5i 4500
Place Recognition, Loop Closure, Mapping, Localization, Mosaicing, Bag-of-Words
Appearance-based Loop Closure Detection and its Application to Topological Mapping and Image Mosaicing
:
Universitat de les Illes Balears,
2017
Accés lliure
http://hdl.handle.net/10803/399587
cr |||||||||||
AAMMDDs2017 sp ||||fsm||||0|| 0 eng|c
García Fidalgo, Emilio,
autor
1 recurs en línia (170 pàgines)
Tesi
Doctorat
Universitat de les Illes Balears. Departament de Ciències Matemàtiques i Informàtica
2016
Universitat de les Illes Balears. Departament de Ciències Matemàtiques i Informàtica
Tesis i dissertacions electròniques
Ortiz Rodríguez, Alberto,
supervisor acadèmic
TDX
Mapping and localization are two essential processes in autonomous mobile robotics since
they are the basis of other higher level and more complex tasks, such as obstacle avoidance or
path planning. Mapping is the process through which a robot builds its own representation of
the environment when a map of the environment is not available. There exist mainly two types
of maps: metric and topological. While metric maps represent the world as accurate as
possible with regard to a global coordinate system, topological maps represent the
environament in an abstract manner by means of a graph, which implies several benefits in
front of the classic metric approaches. Due to the unavoidable noise that sensors present,
mapping algorithms usually rely on loop closure detection techniques, which entails the correct
identification of previously seen places to reduce the uncertainty of the resulting maps. This
dissertation deals with the problem of generating topological maps of the environment using
efficient appearance-based loop closure detection techniques. Since the quality of a visual loop
closure detection algorithm is related to the image description method and its ability to index
previously seen images, several methods for loop closure detection adopting diferent
approaches are developed and assessed. Then, these methods are used as basic components
in three novel topological mapping algorithms. The results obtained indicate that the solutions
proposed attain a better performance than several state-of-the-art approaches. To conclude,
given that place recognition is also a key component in other research areas, a multi-threaded
image mosaicing algorithm is proposed. This approach makes use of one of the loop closure
detection techniques previously introduced in order to find overlapping pairs between images
and finally obtain seamless mosaics of different environments in a reasonable amount of time.
ES-BaCBU
cat
rda
ES-BaCBU
text
txt
rdacontent
informàtic
c
rdamedia
recurs en línia
cr
rdacarrier