{"id":{"repo_id":"msu","oai_identifier":"oai:d.lib.msu.edu:etd_52967"},"canonical_url":"https://search.ndltd.org/etd/msu/oai:d.lib.msu.edu:etd_52967","repository":{"repo_id":"msu","name":"Michigan State University","base_url":"https://d.lib.msu.edu/oai"},"display":{"title":"ADVANCED COMPUTER VISION FOR HIGH-THROUGHPUT PLANT PHENOTYPING","abstract":"Thesis (Ph.D.)--Michigan State University. Electrical and Computer Engineering - Doctor of Philosophy, 2025","abstract_html":"Thesis (Ph.D.)--Michigan State University. Electrical and Computer Engineering - Doctor of Philosophy, 2025","abstract_has_math":false,"creators":["Li, Jiajia"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Li, Zhaojian","Srivastava, Vaibhav","Bopardikar, Shaunak D.","Morris, Daniel"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025","date_published":"2025","updated_at":"2026-11-18T18:59:34Z","subjects":["Electrical engineering"],"languages":["eng"],"rights":["Attribution-NonCommercial-ShareAlike 4.0 International"],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["etd:52967","local:Li_grad.msu_0128D_17950"],"render_values":[{"text":"etd:52967","href":null,"code":true},{"text":"local:Li_grad.msu_0128D_17950","href":null,"code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://doi.org/doi:10.25335/qzfe-4t86","outbound_label":"DOI","outbound_source":"dc:identifier","record_url":"https://doi.org/doi:10.25335/qzfe-4t86","record_label":"Repository record","record_kind":"doi","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://d.lib.msu.edu/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai%3Ad.lib.msu.edu%3Aetd_52967","prefix":"oai_dc"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Li, Zhaojian","Srivastava, Vaibhav","Bopardikar, Shaunak D.","Morris, Daniel"]},{"key":"dc:creator","label":"Author","values":["Li, Jiajia"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025"]},{"key":"dc:relation","label":"Dc Relation","values":["Electronic Theses & Dissertations"]},{"key":"dc:type","label":"Dc Type","values":["text","Electronic dissertations"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Electrical engineering"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Attribution-NonCommercial-ShareAlike 4.0 International"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["etd:52967","local:Li_grad.msu_0128D_17950","https://doi.org/doi:10.25335/qzfe-4t86"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis (Ph.D.)--Michigan State University. Electrical and Computer Engineering - Doctor of Philosophy, 2025","Plant phenotyping plays a pivotal role in understanding plant traits and their interactions with the environment, serving as a cornerstone for precision agriculture and crop improvement. Both 2D and 3D imaging techniques have been widely adopted to capture essential morphological traits such as size, shape, texture, and color. In this dissertation, we investigate plant phenotyping from multiple perspectives, including strawberry plant height and canopy size estimation, multi-fruit high-throughput detection, apple fruit ripeness and size assessment, and soybean pod counting for yield prediction. Our work spans from object- and fruit-level phenotyping to field-scale, high-throughput analysis using aerial sensing, covering diverse conditions from indoor environments to natural field settings with real weather and lighting variations. By integrating 3D Gaussian Splatting for detailed 3D reconstruction, vision foundation models for semantic understanding, and transformer-based architectures for large-scale aerial analysis, this dissertation establishes a comprehensive framework for scalable, accurate, and non-destructive plant trait estimation. Together, these contributions lay the foundation for next-generation automated phenotyping systems that support data-driven crop improvement and precision agriculture.","Description based on online resource. Title from PDF t.p. (Michigan State University Fedora Repository, viewed ).","Includes bibliographical references."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf","1 online resource (120 p.) : ill."]},{"key":"dc:title","label":"Title","values":["ADVANCED COMPUTER VISION FOR HIGH-THROUGHPUT PLANT PHENOTYPING"]}]}],"canonical_facts":{"dc:contributor":["Li, Zhaojian","Srivastava, Vaibhav","Bopardikar, Shaunak D.","Morris, Daniel"],"dc:creator":["Li, Jiajia"],"dc:date":["2025"],"dc:description":["Thesis (Ph.D.)--Michigan State University. Electrical and Computer Engineering - Doctor of Philosophy, 2025","Plant phenotyping plays a pivotal role in understanding plant traits and their interactions with the environment, serving as a cornerstone for precision agriculture and crop improvement. Both 2D and 3D imaging techniques have been widely adopted to capture essential morphological traits such as size, shape, texture, and color. In this dissertation, we investigate plant phenotyping from multiple perspectives, including strawberry plant height and canopy size estimation, multi-fruit high-throughput detection, apple fruit ripeness and size assessment, and soybean pod counting for yield prediction. Our work spans from object- and fruit-level phenotyping to field-scale, high-throughput analysis using aerial sensing, covering diverse conditions from indoor environments to natural field settings with real weather and lighting variations. By integrating 3D Gaussian Splatting for detailed 3D reconstruction, vision foundation models for semantic understanding, and transformer-based architectures for large-scale aerial analysis, this dissertation establishes a comprehensive framework for scalable, accurate, and non-destructive plant trait estimation. Together, these contributions lay the foundation for next-generation automated phenotyping systems that support data-driven crop improvement and precision agriculture.","Description based on online resource. Title from PDF t.p. (Michigan State University Fedora Repository, viewed ).","Includes bibliographical references."],"dc:format":["application/pdf","1 online resource (120 p.) : ill."],"dc:identifier":["etd:52967","local:Li_grad.msu_0128D_17950","https://doi.org/doi:10.25335/qzfe-4t86"],"dc:language":["eng"],"dc:relation":["Electronic Theses & Dissertations"],"dc:rights":["Attribution-NonCommercial-ShareAlike 4.0 International"],"dc:subject":["Electrical engineering"],"dc:title":["ADVANCED COMPUTER VISION FOR HIGH-THROUGHPUT PLANT PHENOTYPING"],"dc:type":["text","Electronic dissertations"]},"updated_at":"2026-11-18T18:59:34Z"}