Deep ArUco: AI/ML-based Real-Time Marker Pose Tracking

dc.contributor.advisor	Kristian Muri Knausgård
dc.contributor.advisor	Andreas Klausen
dc.contributor.advisor	Sondre Sanden Tørdal
dc.contributor.author	Hebnes, Silje Wetrhus
dc.date.accessioned	2022-09-26T16:24:38Z
dc.date.available	2022-09-26T16:24:38Z
dc.date.issued	2022
dc.identifier	no.uia:inspera:109927222:70437059
dc.identifier.uri	https://hdl.handle.net/11250/3021479
dc.description.abstract	Machine learning is commonly used in varoius types of machine vision. Convolutional neural network (CNN) are models that can be trained in different lighting, colors, changes and motion blur. This study generates data containing images with ArUco markers to be detected in different real-world scenarios. Environments created to detect the markers in this study is different lighting, motion blur, rain drops, different contrasts and fog. The ArUco markers will be detected by an existing detection algorithm using machine learning and artificial intelligence.
dc.description.abstract
dc.language
dc.publisher	University of Agder
dc.title	Deep ArUco: AI/ML-based Real-Time Marker Pose Tracking
dc.type	Master thesis