{"id":{"repo_id":"rowan","oai_identifier":"oai:rdw.rowan.edu:etd-4332"},"canonical_url":"https://search.ndltd.org/etd/rowan/oai:rdw.rowan.edu:etd-4332","repository":{"repo_id":"rowan","name":"Rowan University","base_url":"https://rdw.rowan.edu/do/oai/"},"display":{"title":"GENERATING REAL-TIME SYNTHETIC DATASETS TO IMPROVE AERIAL OBJECT DETECTION","abstract":"The widespread use of unmanned aerial vehicles (UAVs) across civilian and military applications has necessitated the advancement of real-time drone detection and tracking capabilities. Machine Learning (ML) addresses these requirements, however, to train a robust and generalizable model requires large and diverse video datasets. Curating these real-world datasets is often time-consuming and cost-prohibitive. Here, we present DyViR, a real-time customizable rendering application capable of automatically generating highly realistic synthetic, multi-modal video of aerial objects, digital environments, and automatic generation and labeling of bounding boxes. Synthetic data, coupled with real-world training sets, augment the ML training process, leading to increased performance and detection accuracy. DyViR is designed to enable non-technical users to generate datasets containing 47 different aerial objects, 4 flight patterns, and 8 environments. To verify the benefits of using synthetic data to augment existing real-world datasets, the YOLOv7-tiny model was employed to evaluate a fully real-world dataset and one augmented with synthetically generated data from DyViR, resulting in a 60.4% increase in mean average precision. This research demonstrates the potential of synthetic datasets, especially when it would be impossible or cost-prohibitive to obtain, opening the door to broader applications where data acquisition is challenging.","abstract_html":"The widespread use of unmanned aerial vehicles (UAVs) across civilian and military applications has necessitated the advancement of real-time drone detection and tracking capabilities. Machine Learning (ML) addresses these requirements, however, to train a robust and generalizable model requires large and diverse video datasets. Curating these real-world datasets is often time-consuming and cost-prohibitive. Here, we present DyViR, a real-time customizable rendering application capable of automatically generating highly realistic synthetic, multi-modal video of aerial objects, digital environments, and automatic generation and labeling of bounding boxes. Synthetic data, coupled with real-world training sets, augment the ML training process, leading to increased performance and detection accuracy. DyViR is designed to enable non-technical users to generate datasets containing 47 different aerial objects, 4 flight patterns, and 8 environments. To verify the benefits of using synthetic data to augment existing real-world datasets, the YOLOv7-tiny model was employed to evaluate a fully real-world dataset and one augmented with synthetically generated data from DyViR, resulting in a 60.4% increase in mean average precision. This research demonstrates the potential of synthetic datasets, especially when it would be impossible or cost-prohibitive to obtain, opening the door to broader applications where data acquisition is challenging.","abstract_has_math":false,"creators":["Williams, Garrett"],"institution":null,"degree_name":"Master of Science (M.S.)","degree_level":"Thesis","degree_discipline":"Electrical and Computer Engineering","degree_department":null,"school":null,"contributors":["George Lecakes, PhD","Nidhal Bouaynaya, PhD","Amanda Almon, MFA, CMI"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T08:59:52Z","subjects":["Drones;Object Detection;Synthetic Data;Virtual Reality","Computer Engineering","Engineering"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://rdw.rowan.edu/etd/3326","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://rdw.rowan.edu/etd/3326","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://rdw.rowan.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Ardw.rowan.edu%3Aetd-4332","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["George Lecakes, PhD","Nidhal Bouaynaya, PhD","Amanda Almon, MFA, CMI"]},{"key":"dc:creator","label":"Author","values":["Williams, Garrett"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2025-03-24T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2025-02-03T08:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical and Computer Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (M.S.)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Drones;Object Detection;Synthetic Data;Virtual Reality","Computer Engineering","Engineering"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://rdw.rowan.edu/etd/3326"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The widespread use of unmanned aerial vehicles (UAVs) across civilian and military applications has necessitated the advancement of real-time drone detection and tracking capabilities. Machine Learning (ML) addresses these requirements, however, to train a robust and generalizable model requires large and diverse video datasets. Curating these real-world datasets is often time-consuming and cost-prohibitive. Here, we present DyViR, a real-time customizable rendering application capable of automatically generating highly realistic synthetic, multi-modal video of aerial objects, digital environments, and automatic generation and labeling of bounding boxes. Synthetic data, coupled with real-world training sets, augment the ML training process, leading to increased performance and detection accuracy. DyViR is designed to enable non-technical users to generate datasets containing 47 different aerial objects, 4 flight patterns, and 8 environments. To verify the benefits of using synthetic data to augment existing real-world datasets, the YOLOv7-tiny model was employed to evaluate a fully real-world dataset and one augmented with synthetically generated data from DyViR, resulting in a 60.4% increase in mean average precision. This research demonstrates the potential of synthetic datasets, especially when it would be impossible or cost-prohibitive to obtain, opening the door to broader applications where data acquisition is challenging."]},{"key":"dc:title","label":"Title","values":["GENERATING REAL-TIME SYNTHETIC DATASETS TO IMPROVE AERIAL OBJECT DETECTION"]}]}],"canonical_facts":{"dc:contributor":["George Lecakes, PhD","Nidhal Bouaynaya, PhD","Amanda Almon, MFA, CMI"],"dc:creator":["Williams, Garrett"],"dc:date.available":["2025-03-24T07:00:00Z"],"dc:date.created":["2025-02-03T08:00:00Z"],"dc:description.abstract":["The widespread use of unmanned aerial vehicles (UAVs) across civilian and military applications has necessitated the advancement of real-time drone detection and tracking capabilities. Machine Learning (ML) addresses these requirements, however, to train a robust and generalizable model requires large and diverse video datasets. Curating these real-world datasets is often time-consuming and cost-prohibitive. Here, we present DyViR, a real-time customizable rendering application capable of automatically generating highly realistic synthetic, multi-modal video of aerial objects, digital environments, and automatic generation and labeling of bounding boxes. Synthetic data, coupled with real-world training sets, augment the ML training process, leading to increased performance and detection accuracy. DyViR is designed to enable non-technical users to generate datasets containing 47 different aerial objects, 4 flight patterns, and 8 environments. To verify the benefits of using synthetic data to augment existing real-world datasets, the YOLOv7-tiny model was employed to evaluate a fully real-world dataset and one augmented with synthetically generated data from DyViR, resulting in a 60.4% increase in mean average precision. This research demonstrates the potential of synthetic datasets, especially when it would be impossible or cost-prohibitive to obtain, opening the door to broader applications where data acquisition is challenging."],"dc:identifier":["https://rdw.rowan.edu/etd/3326"],"dc:subject":["Drones;Object Detection;Synthetic Data;Virtual Reality","Computer Engineering","Engineering"],"dc:title":["GENERATING REAL-TIME SYNTHETIC DATASETS TO IMPROVE AERIAL OBJECT DETECTION"],"thesis:degree_discipline":["Electrical and Computer Engineering"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science (M.S.)"]},"updated_at":"2026-11-19T08:59:52Z"}