Models and Methods for Inertial and Visual Odometry

dc.contributorAalto Universityen
dc.contributor.authorCortes Reina, Santiago
dc.contributor.departmentTietotekniikan laitosfi
dc.contributor.departmentDepartment of Computer Scienceen
dc.contributor.schoolPerustieteiden korkeakoulufi
dc.contributor.schoolSchool of Scienceen
dc.contributor.supervisorKannala, Juho, Prof, Aalto University, Department of Computer Science, Finland; Solin, Arno, Prof., Aalto University, Department of Computer Science, Finland
dc.description.abstractSmartphones have become a part of everyday modern life. Their presence and capabilities have changed the way a lot of tasks are performed. Among them is navigation, how to find a way from one point to another. Satellite-based navigation allows for easy localization and path planning when traveling outdoors in the open. Another recent capability is augmented reality and local mapping. However, medium-scale indoor navigation and mapping have not been reliably solved. Challenges in these environments are characterized by an unreliable satellite signal and visual features which are not easily recognizable or not revisited. This thesis is focused on inertial and visual-inertial navigation for pedestrian dead reckoning. The systems, algorithms, datasets, and benchmarks proposed in this thesis are all designed with smartphones and pedestrians in mind. The central statement of the thesis is that careful consideration of uncertainty sources, the characteristics of pedestrian motion, and the quality of the available signals allows for a system that produces reliable odometry over medium-length sequences of pedestrian motion. Two sensor modalities are explored in this thesis, inertial and visual-inertial odometry. Pure inertial odometry relies on complementary signals to keep a reliable estimate of the pose. Multiple approaches to utilize these complementary signals are explored in this thesis. Visual-inertial odometry is approached with computational efficiency in mind. The measurements from the camera and the inertial sensors are integrated using a state space model driven by inertial odometry. This is to allow for efficient use of camera information and complementary online processing. This thesis also introduces a dataset which is a representative sample of the kind of use cases that are problematic for most available systems. This dataset is used in both modalities to train, evaluate and benchmark results in pedestrian dead reckoning. The main contributions of this thesis are the proposed algorithms and data. This thesis shows that multiple modalities of information and multiple approaches to state estimation can be used to complement each other. The complementary use of sequential Bayesian estimation and deep learning has been explored further by the community, and many opportunities to improve on it are still to be discovered.en
dc.format.extent56 + app. 72
dc.identifier.isbn978-952-64-0557-5 (electronic)
dc.identifier.isbn978-952-64-0556-8 (printed)
dc.identifier.issn1799-4942 (electronic)
dc.identifier.issn1799-4934 (printed)
dc.identifier.issn1799-4934 (ISSN-L)
dc.opnBlösch, Michael, Dr., DeepMind, UK
dc.publisherAalto Universityen
dc.relation.haspart[Publication 1]: Arno Solin, Santiago Cortés, Esa Rahtu, and Juho Kannala. Inertial odometry on handheld smartphones. In Proceedings of the International Conference on Information Fusion (FUSION), pages 1–5, Cambridge, UK, July 2018. Full text in Acris/Aaltodoc: DOI: 10.23919/ICIF.2018.8455482
dc.relation.haspart[Publication 2]: Santiago Cortés, Yuxin Hou, Juho Kannala, and Arno Solin. Iterative path reconstruction for large-scale inertial navigation on smartphones. In Proceedings of the International Conference on Information Fusion (FUSION), Ottawa, Canada, July 2019
dc.relation.haspart[Publication 3]: Santiago Cortés, Arno Solin, and Juho Kannala. Deep learning based speed estimation for constraining strapdown inertial navigation on smartphones. In IEEE International Workshop on Machine Learning for Signal Processing (MLSP), pages 1–6, Aalborg, Denmark, September 2018. Full text in Acris/Aaltodoc: DOI: 10.1109/MLSP.2018.8516710
dc.relation.haspart[Publication 4]: Arno Solin, Santiago Cortés, Esa Rahtu, and Juho Kannala. PIVO: Probabilistic inertial-visual odometry for occlusion-robust navigation. In IEEE Winter Conference on Applications of Computer Vision (WACV), pages 616–625, Lake Tahoe, NV, March 2018. DOI: 10.1109/WACV.2018.00073
dc.relation.haspart[Publication 5]: Santiago Cortés, Arno Solin, Esa Rahtu, and Juho Kannala. ADVIO: An authentic dataset for visual-inertial odometry. In Proceedings of European Conference on Computer Vision (ECCV), Lecture Notes in Computer Science, 11214:425–440. Munich, Germany, September 2018. DOI: 10.1007/978-3-030-01249-6_26
dc.relation.haspart[Publication 6]: Santiago Cortés, Arno Solin, and Juho Kannala. Robust gyroscope- aided camera self-calibration. In Proceedings of the International Conference on Information Fusion (FUSION), pages 772–779. Cambridge, UK, July 2018. DOI: 10.23919/ICIF.2018.8455353
dc.relation.ispartofseriesAalto University publication series DOCTORAL DISSERTATIONSen
dc.revFurukawa, Yasutaka, Prof., Simon Fraser University, Canada
dc.revSkog, Isaac, Prof., Linköping University, Sweden
dc.subject.keyworddead reckoningen
dc.subject.keywordKalman filteren
dc.subject.otherComputer scienceen
dc.titleModels and Methods for Inertial and Visual Odometryen
dc.typeG5 Artikkeliväitöskirjafi
dc.type.ontasotDoctoral dissertation (article-based)en
dc.type.ontasotVäitöskirja (artikkeli)fi
local.aalto.acrisexportstatuschecked 2021-11-12_0844
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
7.03 MB
Adobe Portable Document Format