{"id":{"repo_id":"calpoly","oai_identifier":"oai:digitalcommons.calpoly.edu:theses-4947"},"canonical_url":"https://search.ndltd.org/etd/calpoly/oai:digitalcommons.calpoly.edu:theses-4947","repository":{"repo_id":"calpoly","name":"Cal Poly","base_url":"https://digitalcommons.calpoly.edu/do/oai/"},"display":{"title":"Integer Quantization and Embedded Deployment of CNN Star Trackers for CubeSats","abstract":"A star tracker determines spacecraft orientation by photographing the star field, detecting stars in the image, matching them against a catalog, and computing the rotation between observed and cataloged directions. Convolutional neural networks (CNNs) have been proposed as replacements for the detection and centroiding stage, offering improved sub-pixel accuracy and recovering faint stars that classical thresholds lose to stray light and sensor noise. The improvement comes at higher computational cost; the PolySat systemboard targeted in this work lacks the floating-point hardware these networks assume. This thesis closes the gap between floating-point desktop evaluation and embedded integer deployment. Nine encoder-decoder CNN architectures are quantized to 8-bit integer precision, evaluated end to end against the classical Pyramid identifier and QUEST attitude solver, and the two highest-F1 architectures are deployed on the PolySat systemboard through a C inference engine. On a 500-image synthetic test set, eight of the nine networks recover detection F1 within 3.4 percentage points of the floating-point baseline; the quantized networks identify stars at 96 to 97 percent against approximately 82 percent for the best-tuned classical detector, with median attitude error between 0.019° and 0.032°. On the systemboard, the deployed model fits within roughly 16 MB of peak resident memory under a tiled-inference strategy. The results establish a path from floating-point prototype to integer on-target execution for CubeSat star trackers, with on-target inference latency as the principal target for follow-on work.","abstract_html":"A star tracker determines spacecraft orientation by photographing the star field, detecting stars in the image, matching them against a catalog, and computing the rotation between observed and cataloged directions. Convolutional neural networks (CNNs) have been proposed as replacements for the detection and centroiding stage, offering improved sub-pixel accuracy and recovering faint stars that classical thresholds lose to stray light and sensor noise. The improvement comes at higher computational cost; the PolySat systemboard targeted in this work lacks the floating-point hardware these networks assume. This thesis closes the gap between floating-point desktop evaluation and embedded integer deployment. Nine encoder-decoder CNN architectures are quantized to 8-bit integer precision, evaluated end to end against the classical Pyramid identifier and QUEST attitude solver, and the two highest-F1 architectures are deployed on the PolySat systemboard through a C inference engine. On a 500-image synthetic test set, eight of the nine networks recover detection F1 within 3.4 percentage points of the floating-point baseline; the quantized networks identify stars at 96 to 97 percent against approximately 82 percent for the best-tuned classical detector, with median attitude error between 0.019° and 0.032°. On the systemboard, the deployed model fits within roughly 16 MB of peak resident memory under a tiled-inference strategy. The results establish a path from floating-point prototype to integer on-target execution for CubeSat star trackers, with on-target inference latency as the principal target for follow-on work.","abstract_has_math":false,"creators":["Giusiano, Meora R"],"institution":null,"degree_name":"MS in Computer Science","degree_level":null,"degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["John Bellardo","Computer Science","College of Engineering"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T07:12:51Z","subjects":["Star tracker","attitude determination","CubeSat","INT8 quantization","embedded deployment","centroid detection","Artificial Intelligence and Robotics"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.calpoly.edu/theses/3288","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.calpoly.edu/theses/3288","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digitalcommons.calpoly.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.calpoly.edu%3Atheses-4947","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["John Bellardo","Computer Science","College of Engineering"]},{"key":"dc:creator","label":"Author","values":["Giusiano, Meora R"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2026-06-05T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2026-06-01T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_name","label":"Degree Name","values":["MS in Computer Science"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Star tracker","attitude determination","CubeSat","INT8 quantization","embedded deployment","centroid detection","Artificial Intelligence and Robotics"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.calpoly.edu/theses/3288"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["A star tracker determines spacecraft orientation by photographing the star field, detecting stars in the image, matching them against a catalog, and computing the rotation between observed and cataloged directions. Convolutional neural networks (CNNs) have been proposed as replacements for the detection and centroiding stage, offering improved sub-pixel accuracy and recovering faint stars that classical thresholds lose to stray light and sensor noise. The improvement comes at higher computational cost; the PolySat systemboard targeted in this work lacks the floating-point hardware these networks assume. This thesis closes the gap between floating-point desktop evaluation and embedded integer deployment. Nine encoder-decoder CNN architectures are quantized to 8-bit integer precision, evaluated end to end against the classical Pyramid identifier and QUEST attitude solver, and the two highest-F1 architectures are deployed on the PolySat systemboard through a C inference engine. On a 500-image synthetic test set, eight of the nine networks recover detection F1 within 3.4 percentage points of the floating-point baseline; the quantized networks identify stars at 96 to 97 percent against approximately 82 percent for the best-tuned classical detector, with median attitude error between 0.019° and 0.032°. On the systemboard, the deployed model fits within roughly 16 MB of peak resident memory under a tiled-inference strategy. The results establish a path from floating-point prototype to integer on-target execution for CubeSat star trackers, with on-target inference latency as the principal target for follow-on work."]},{"key":"dc:title","label":"Title","values":["Integer Quantization and Embedded Deployment of CNN Star Trackers for CubeSats"]}]}],"canonical_facts":{"dc:contributor":["John Bellardo","Computer Science","College of Engineering"],"dc:creator":["Giusiano, Meora R"],"dc:date.available":["2026-06-05T07:00:00Z"],"dc:date.created":["2026-06-01T07:00:00Z"],"dc:description.abstract":["A star tracker determines spacecraft orientation by photographing the star field, detecting stars in the image, matching them against a catalog, and computing the rotation between observed and cataloged directions. Convolutional neural networks (CNNs) have been proposed as replacements for the detection and centroiding stage, offering improved sub-pixel accuracy and recovering faint stars that classical thresholds lose to stray light and sensor noise. The improvement comes at higher computational cost; the PolySat systemboard targeted in this work lacks the floating-point hardware these networks assume. This thesis closes the gap between floating-point desktop evaluation and embedded integer deployment. Nine encoder-decoder CNN architectures are quantized to 8-bit integer precision, evaluated end to end against the classical Pyramid identifier and QUEST attitude solver, and the two highest-F1 architectures are deployed on the PolySat systemboard through a C inference engine. On a 500-image synthetic test set, eight of the nine networks recover detection F1 within 3.4 percentage points of the floating-point baseline; the quantized networks identify stars at 96 to 97 percent against approximately 82 percent for the best-tuned classical detector, with median attitude error between 0.019° and 0.032°. On the systemboard, the deployed model fits within roughly 16 MB of peak resident memory under a tiled-inference strategy. The results establish a path from floating-point prototype to integer on-target execution for CubeSat star trackers, with on-target inference latency as the principal target for follow-on work."],"dc:identifier":["https://digitalcommons.calpoly.edu/theses/3288"],"dc:subject":["Star tracker","attitude determination","CubeSat","INT8 quantization","embedded deployment","centroid detection","Artificial Intelligence and Robotics"],"dc:title":["Integer Quantization and Embedded Deployment of CNN Star Trackers for CubeSats"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_name":["MS in Computer Science"]},"updated_at":"2026-11-19T07:12:51Z"}