{"id":{"repo_id":"calpoly","oai_identifier":"oai:digitalcommons.calpoly.edu:theses-4140"},"canonical_url":"https://search.ndltd.org/etd/calpoly/oai:digitalcommons.calpoly.edu:theses-4140","repository":{"repo_id":"calpoly","name":"Cal Poly","base_url":"https://digitalcommons.calpoly.edu/do/oai/"},"display":{"title":"Deep Learning for Detecting Trees in the Urban Environment from Lidar","abstract":"Cataloguing and classifying trees in the urban environment is a crucial step in urban and environmental planning. However, manual collection and maintenance of this data is expensive and time-consuming. Algorithmic approaches that rely on remote sensing data have been developed for tree detection in forests, though they generally struggle in the more varied urban environment. This work proposes a novel method for the detection of trees in the urban environment that applies deep learning to remote sensing data. Specifically, we train a PointNet-based neural network to predict tree locations directly from LIDAR data augmented with multi-spectral imaging. We compare this model to numerous high-performant baselines on a large and varied dataset in the Southern California region. We find that our best model outperforms all baselines with a 75.5\\% F-score and 2.28 meter RMSE, while being highly efficient. We then analyze and compare the sources of errors, and how these reveal the strengths and weaknesses of each approach.","abstract_html":"Cataloguing and classifying trees in the urban environment is a crucial step in urban and environmental planning. However, manual collection and maintenance of this data is expensive and time-consuming. Algorithmic approaches that rely on remote sensing data have been developed for tree detection in forests, though they generally struggle in the more varied urban environment. This work proposes a novel method for the detection of trees in the urban environment that applies deep learning to remote sensing data. Specifically, we train a PointNet-based neural network to predict tree locations directly from LIDAR data augmented with multi-spectral imaging. We compare this model to numerous high-performant baselines on a large and varied dataset in the Southern California region. We find that our best model outperforms all baselines with a 75.5\\% F-score and 2.28 meter RMSE, while being highly efficient. We then analyze and compare the sources of errors, and how these reveal the strengths and weaknesses of each approach.","abstract_has_math":false,"creators":["Rice, Julian R"],"institution":null,"degree_name":"MS in Computer Science","degree_level":null,"degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Jonathan Ventura","Computer Science","College of Engineering"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T07:12:23Z","subjects":["Deep Learning","Machine Learning","Forestry","Remote Sensing","AI","Trees","Data Science"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["10.15368/theses.2022.92"],"render_values":[{"text":"10.15368/theses.2022.92","href":"https://doi.org/10.15368/theses.2022.92","code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.calpoly.edu/theses/2569","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.calpoly.edu/theses/2569","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-4140","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Jonathan Ventura","Computer Science","College of Engineering"]},{"key":"dc:creator","label":"Author","values":["Rice, Julian R"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2022-08-21T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2022-08-01T07:00:00Z"]},{"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":["Deep Learning","Machine Learning","Forestry","Remote Sensing","AI","Trees","Data Science"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.calpoly.edu/theses/2569","10.15368/theses.2022.92"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Cataloguing and classifying trees in the urban environment is a crucial step in urban and environmental planning. However, manual collection and maintenance of this data is expensive and time-consuming. Algorithmic approaches that rely on remote sensing data have been developed for tree detection in forests, though they generally struggle in the more varied urban environment. This work proposes a novel method for the detection of trees in the urban environment that applies deep learning to remote sensing data. Specifically, we train a PointNet-based neural network to predict tree locations directly from LIDAR data augmented with multi-spectral imaging. We compare this model to numerous high-performant baselines on a large and varied dataset in the Southern California region. We find that our best model outperforms all baselines with a 75.5\\% F-score and 2.28 meter RMSE, while being highly efficient. We then analyze and compare the sources of errors, and how these reveal the strengths and weaknesses of each approach."]},{"key":"dc:title","label":"Title","values":["Deep Learning for Detecting Trees in the Urban Environment from Lidar"]}]}],"canonical_facts":{"dc:contributor":["Jonathan Ventura","Computer Science","College of Engineering"],"dc:creator":["Rice, Julian R"],"dc:date.available":["2022-08-21T07:00:00Z"],"dc:date.created":["2022-08-01T07:00:00Z"],"dc:description.abstract":["Cataloguing and classifying trees in the urban environment is a crucial step in urban and environmental planning. However, manual collection and maintenance of this data is expensive and time-consuming. Algorithmic approaches that rely on remote sensing data have been developed for tree detection in forests, though they generally struggle in the more varied urban environment. This work proposes a novel method for the detection of trees in the urban environment that applies deep learning to remote sensing data. Specifically, we train a PointNet-based neural network to predict tree locations directly from LIDAR data augmented with multi-spectral imaging. We compare this model to numerous high-performant baselines on a large and varied dataset in the Southern California region. We find that our best model outperforms all baselines with a 75.5\\% F-score and 2.28 meter RMSE, while being highly efficient. We then analyze and compare the sources of errors, and how these reveal the strengths and weaknesses of each approach."],"dc:identifier":["https://digitalcommons.calpoly.edu/theses/2569","10.15368/theses.2022.92"],"dc:subject":["Deep Learning","Machine Learning","Forestry","Remote Sensing","AI","Trees","Data Science"],"dc:title":["Deep Learning for Detecting Trees in the Urban Environment from Lidar"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_name":["MS in Computer Science"]},"updated_at":"2026-11-19T07:12:23Z"}