{"id":{"repo_id":"umn","oai_identifier":"oai:conservancy.umn.edu:11299/90851"},"canonical_url":"https://search.dev.ndltd.org/etd/umn/oai:conservancy.umn.edu:11299/90851","repository":{"repo_id":"umn","name":"University of Minnesota","base_url":"https://conservancy.umn.edu/server/oai/request"},"display":{"title":"Autonomous altitude estimation of a miniature helicopter using a single onboard camera.","abstract":"Autonomous estimation of the altitude of an Unmanned Aerial Vehicle (UAV) is extremely important when dealing with flight maneuvers like landing, steady flight, etc. Vision based techniques for solving this problem have been underutilized. In this thesis, we propose a new algorithm to estimate the altitude of a UAV from top-down aerial images taken from a single on-board camera. We use a semi-supervised machine learning approach to solve the problem. The basic idea of our technique is to learn the mapping between the texture information contained in an image to a possible altitude value. We learn an over complete sparse basis set from a corpus of unlabeled images capturing the texture variations. This is followed by regression of this basis set against a training set of altitudes. Finally, a spatio-temporal Markov Random Field is modeled over the altitudes in test images, which is maximized over the posterior distribution using the MAP estimate by solving a quadratic optimization problem with L1 regularity constraints. The method is evaluated in a laboratory setting with a real helicopter and is found to provide promising results with sufficiently fast turnaround time.","abstract_html":"Autonomous estimation of the altitude of an Unmanned Aerial Vehicle (UAV) is extremely important when dealing with flight maneuvers like landing, steady flight, etc. Vision based techniques for solving this problem have been underutilized. In this thesis, we propose a new algorithm to estimate the altitude of a UAV from top-down aerial images taken from a single on-board camera. We use a semi-supervised machine learning approach to solve the problem. The basic idea of our technique is to learn the mapping between the texture information contained in an image to a possible altitude value. We learn an over complete sparse basis set from a corpus of unlabeled images capturing the texture variations. This is followed by regression of this basis set against a training set of altitudes. Finally, a spatio-temporal Markov Random Field is modeled over the altitudes in test images, which is maximized over the posterior distribution using the MAP estimate by solving a quadratic optimization problem with L1 regularity constraints. The method is evaluated in a laboratory setting with a real helicopter and is found to provide promising results with sufficiently fast turnaround time.","abstract_has_math":false,"creators":["Cherian, Anoop"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2010,"date_issued":"2010-04","date_published":"2010-04","updated_at":"2026-07-24T05:19:42Z","subjects":["Unmanned Aerial Vehicle","Flight maneuvers","Landing","Steady flight","Computer Science and Engineering"],"languages":["en_US"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://purl.umn.edu/90851","outbound_label":"Repository record","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Cherian, Anoop"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2010-06-08T20:51:18Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2010-06-08T20:51:18Z"]},{"key":"dc:date.issued","label":"Date","values":["2010-04"]},{"key":"dc:type","label":"Dc Type","values":["Thesis or Dissertation"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Unmanned Aerial Vehicle","Flight maneuvers","Landing","Steady flight","Computer Science and Engineering"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en_US"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://purl.umn.edu/90851"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["University of Minnesota M.S. thesis. April 2010. Major: Computer Science and Engineering. Advisor: Nikolaos Papanikolopoulos. 1 computer file (PDF); v, 18 pages. Ill. (some col.)"]},{"key":"dc:description.abstract","label":"Abstract","values":["Autonomous estimation of the altitude of an Unmanned Aerial Vehicle (UAV) is extremely important when dealing with flight maneuvers like landing, steady flight, etc. Vision based techniques for solving this problem have been underutilized. In this thesis, we propose a new algorithm to estimate the altitude of a UAV from top-down aerial images taken from a single on-board camera. We use a semi-supervised machine learning approach to solve the problem. The basic idea of our technique is to learn the mapping between the texture information contained in an image to a possible altitude value. We learn an over complete sparse basis set from a corpus of unlabeled images capturing the texture variations. This is followed by regression of this basis set against a training set of altitudes. Finally, a spatio-temporal Markov Random Field is modeled over the altitudes in test images, which is maximized over the posterior distribution using the MAP estimate by solving a quadratic optimization problem with L1 regularity constraints. The method is evaluated in a laboratory setting with a real helicopter and is found to provide promising results with sufficiently fast turnaround time."]},{"key":"dc:title","label":"Title","values":["Autonomous altitude estimation of a miniature helicopter using a single onboard camera."]}]}],"canonical_facts":{"dc:creator":["Cherian, Anoop"],"dc:date.accessioned":["2010-06-08T20:51:18Z"],"dc:date.available":["2010-06-08T20:51:18Z"],"dc:date.issued":["2010-04"],"dc:description":["University of Minnesota M.S. thesis. April 2010. Major: Computer Science and Engineering. Advisor: Nikolaos Papanikolopoulos. 1 computer file (PDF); v, 18 pages. Ill. (some col.)"],"dc:description.abstract":["Autonomous estimation of the altitude of an Unmanned Aerial Vehicle (UAV) is extremely important when dealing with flight maneuvers like landing, steady flight, etc. Vision based techniques for solving this problem have been underutilized. In this thesis, we propose a new algorithm to estimate the altitude of a UAV from top-down aerial images taken from a single on-board camera. We use a semi-supervised machine learning approach to solve the problem. The basic idea of our technique is to learn the mapping between the texture information contained in an image to a possible altitude value. We learn an over complete sparse basis set from a corpus of unlabeled images capturing the texture variations. This is followed by regression of this basis set against a training set of altitudes. Finally, a spatio-temporal Markov Random Field is modeled over the altitudes in test images, which is maximized over the posterior distribution using the MAP estimate by solving a quadratic optimization problem with L1 regularity constraints. The method is evaluated in a laboratory setting with a real helicopter and is found to provide promising results with sufficiently fast turnaround time."],"dc:identifier.uri":["http://purl.umn.edu/90851"],"dc:language.iso":["en_US"],"dc:subject":["Unmanned Aerial Vehicle","Flight maneuvers","Landing","Steady flight","Computer Science and Engineering"],"dc:title":["Autonomous altitude estimation of a miniature helicopter using a single onboard camera."],"dc:type":["Thesis or Dissertation"]},"updated_at":"2026-07-24T05:19:42Z"}