Semantic segmentation for visual indoor localization

Kaminskyi, Yurii

Домівка
→
Students Research & Project Works | Роботи студентів
→
Факультет прикладних наук
→
Освітня програма наук про дані
→
2019
→
Перегляд матеріалів

dc.contributor.author	Kaminskyi, Yurii
dc.date.accessioned	2019-02-19T10:19:06Z
dc.date.available	2019-02-19T10:19:06Z
dc.date.issued	2019
dc.identifier.citation	Kaminskyi, Yurii. Semantic segmentation for visual indoor localization : Master Thesis : manuscript / Yurii Kaminskyi ; Supervisor Jiri Sedlar, Ph. D. ; Ukrainian Catholic University, Department of Computer Sciences. – Lviv : [s.n.], 2019. – 30 p. : ill.	uk
dc.identifier.uri	http://er.ucu.edu.ua/handle/1/1329
dc.language.iso	en	uk
dc.subject	semantic segmentation	uk
dc.subject	indoor localization	uk
dc.subject	Mask R-CNN	uk
dc.title	Semantic segmentation for visual indoor localization	uk
dc.type	Preprint	uk
dc.status	Публікується вперше	uk
dc.description.abstracten	The problem of visual localization and navigation in the 3D environment is a key to solving a vast variety of practical tasks. For example in robotics, where the machine is required to locate itself on the 3D map and steer to a specific location. Another example is a personal assistant in the form of a mobile phone or smart glasses that uses augmented reality techniques to navigate the user seamlessly in large indoor spaces such as airports, hospitals, shopping malls or office buildings. The purpose of this work was to improve the performance of the InLoc localization pipeline that gives state-of-the-art results for indoor visual localization problem. That was done by developing relevant semantic features. Namely, we introduce a variety of features as a result of two different segmentation models: Mask R-CNN and CSAIL. We evaluate the quality of generated features and add the features of the better performing model into the InLoc localization pipeline. With the introduced features we improved the performance of the InLoc localization pipeline and introduced approaches for further research.	uk