{"id":{"repo_id":"uwo","oai_identifier":"oai:uwo.scholaris.ca:20.500.14721/37216"},"canonical_url":"https://search.dev.ndltd.org/etd/uwo/oai:uwo.scholaris.ca:20.500.14721/37216","repository":{"repo_id":"uwo","name":"Western University","base_url":"https://uwo.scholaris.ca/server/oai/request"},"display":{"title":"Automatic Classification and Segmentation of Patterned Martian Ground Using Deep Learning Techniques","abstract":"Science autonomy onboard spacecraft can optimize image return by prioritizing downlink of meaningful data. Martian polygonally cracked ground is actively studied by planetary geologists and may be indicative of subsurface water. Filtering images containing these polygonal features can be used as a case study for science autonomy and to reduce the overhead associated with parsing through Martian surface images. This thesis demonstrates the use of deep learning techniques in the classification of Martian polygonally patterned ground from HiRISE images. Three tasks are considered, a binary classification to identify images containing polygons, multiclass classification distinguishing different polygon types and semantic segmentation of polygon regions. Due to time and resource constraints, transfer learning is employed on state-of-the-art deep learning networks. Convolutional neural network model architectures are compared for the binary and multiclass scenarios. UNet was used for semantic segmentation. Overall, the models show promising results as a first filter method.","abstract_html":"Science autonomy onboard spacecraft can optimize image return by prioritizing downlink of meaningful data. Martian polygonally cracked ground is actively studied by planetary geologists and may be indicative of subsurface water. Filtering images containing these polygonal features can be used as a case study for science autonomy and to reduce the overhead associated with parsing through Martian surface images. This thesis demonstrates the use of deep learning techniques in the classification of Martian polygonally patterned ground from HiRISE images. Three tasks are considered, a binary classification to identify images containing polygons, multiclass classification distinguishing different polygon types and semantic segmentation of polygon regions. Due to time and resource constraints, transfer learning is employed on state-of-the-art deep learning networks. Convolutional neural network model architectures are compared for the binary and multiclass scenarios. UNet was used for semantic segmentation. Overall, the models show promising results as a first filter method.","abstract_has_math":false,"creators":["Brito, Ruthy"],"institution":"The University of Western Ontario","degree_name":"M Eng Sci","degree_level":null,"degree_discipline":"Electrical and Computer Engineering","degree_department":null,"school":null,"contributors":[],"advisors":["McIsaac, Kenneth"],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023-06-29","date_published":"2023-06-29","updated_at":"2026-07-27T21:56:20Z","subjects":["Semantic segmentation","deep learning","transfer learning","image classification","convolutional neural networks","Martian polygon ground"],"languages":["en_ca"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/20.500.14721/37216","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["McIsaac, Kenneth"]},{"key":"dc:creator","label":"Author","values":["Brito, Ruthy"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-07-10T21:32:18Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-07-10T21:32:18Z"]},{"key":"dc:date.issued","label":"Date","values":["2023-06-29"]},{"key":"dc:publisher","label":"Institution","values":["The University of Western Ontario"]},{"key":"dc:type","label":"Dc Type","values":["thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical and Computer Engineering"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M Eng Sci"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Semantic segmentation","deep learning","transfer learning","image classification","convolutional neural networks","Martian polygon ground"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en_ca"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/20.500.14721/37216"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Collaborative Specialization: Planetary Science and Exploration","The thesis cover page in the PDF document includes references to Western University’s previous institutional repository platform, known as Scholarship@Western, and links to that platform (beginning with ir.lib.uwo.ca). In citing or referring to this thesis, use the DOI or handle from this page instead. Sample citation: Author name, \"Thesis title.\" (Year). Western University Open Repository. https://doi.org/10.71858/123456."]},{"key":"dc:description.abstract","label":"Abstract","values":["Science autonomy onboard spacecraft can optimize image return by prioritizing downlink of meaningful data. Martian polygonally cracked ground is actively studied by planetary geologists and may be indicative of subsurface water. Filtering images containing these polygonal features can be used as a case study for science autonomy and to reduce the overhead associated with parsing through Martian surface images. This thesis demonstrates the use of deep learning techniques in the classification of Martian polygonally patterned ground from HiRISE images. Three tasks are considered, a binary classification to identify images containing polygons, multiclass classification distinguishing different polygon types and semantic segmentation of polygon regions. Due to time and resource constraints, transfer learning is employed on state-of-the-art deep learning networks. Convolutional neural network model architectures are compared for the binary and multiclass scenarios. UNet was used for semantic segmentation. Overall, the models show promising results as a first filter method."]},{"key":"dc:title","label":"Title","values":["Automatic Classification and Segmentation of Patterned Martian Ground Using Deep Learning Techniques"]}]}],"canonical_facts":{"dc:contributor.advisor":["McIsaac, Kenneth"],"dc:creator":["Brito, Ruthy"],"dc:date.accessioned":["2025-07-10T21:32:18Z"],"dc:date.available":["2025-07-10T21:32:18Z"],"dc:date.issued":["2023-06-29"],"dc:description":["Collaborative Specialization: Planetary Science and Exploration","The thesis cover page in the PDF document includes references to Western University’s previous institutional repository platform, known as Scholarship@Western, and links to that platform (beginning with ir.lib.uwo.ca). In citing or referring to this thesis, use the DOI or handle from this page instead. Sample citation: Author name, \"Thesis title.\" (Year). Western University Open Repository. https://doi.org/10.71858/123456."],"dc:description.abstract":["Science autonomy onboard spacecraft can optimize image return by prioritizing downlink of meaningful data. Martian polygonally cracked ground is actively studied by planetary geologists and may be indicative of subsurface water. Filtering images containing these polygonal features can be used as a case study for science autonomy and to reduce the overhead associated with parsing through Martian surface images. This thesis demonstrates the use of deep learning techniques in the classification of Martian polygonally patterned ground from HiRISE images. Three tasks are considered, a binary classification to identify images containing polygons, multiclass classification distinguishing different polygon types and semantic segmentation of polygon regions. Due to time and resource constraints, transfer learning is employed on state-of-the-art deep learning networks. Convolutional neural network model architectures are compared for the binary and multiclass scenarios. UNet was used for semantic segmentation. Overall, the models show promising results as a first filter method."],"dc:identifier.uri":["https://hdl.handle.net/20.500.14721/37216"],"dc:language.iso":["en_ca"],"dc:publisher":["The University of Western Ontario"],"dc:subject":["Semantic segmentation","deep learning","transfer learning","image classification","convolutional neural networks","Martian polygon ground"],"dc:title":["Automatic Classification and Segmentation of Patterned Martian Ground Using Deep Learning Techniques"],"dc:type":["thesis"],"thesis:degree_discipline":["Electrical and Computer Engineering"],"thesis:degree_name":["M Eng Sci"]},"updated_at":"2026-07-27T21:56:20Z"}