{"id":{"repo_id":"clemson","oai_identifier":"oai:open.clemson.edu:all_theses-5773"},"canonical_url":"https://search.ndltd.org/etd/clemson/oai:open.clemson.edu:all_theses-5773","repository":{"repo_id":"clemson","name":"Clemson University","base_url":"https://open.clemson.edu/do/oai/"},"display":{"title":"Multimodal Aerial Image-based Ground Object Detection and Classification using YOLO","abstract":"Object detection in unmanned aerial vehicles (UAVs) present a unique challenge due to small object sizes, varying viewpoints, and changing environmental conditions. These challenges are exacerbated when operating during daytime and nighttime scenarios where illumination differences can heavily impact detection performance. This work is motivated by military object detection applications where the ability to reliably identify small objects such as landmines or unexploded ordnance from aerial imagery presents a critical safety need and a significant technical challenge. In this paper, we investigate object detection using both visible (RGB) and infrared (IR) imagery to improve robustness and reliability across diverse operating conditions. Various YOLO-based object detection models are trained and evaluated on aerial data collected using a multimodal sensor UAV platform. Experiments were conducted separately during daylight, low-light, and twilight scenarios. The results demonstrate a high level of accuracy achieving 90.8% on the daytime dataset, 98.5% on the nighttime dataset, and over 64% on the semi-illuminated dataset where material classification is employed. This study highlights the challenges and insights into the role of illumination and sensor modality in UAV-based object detection towards reliable perception.","abstract_html":"Object detection in unmanned aerial vehicles (UAVs) present a unique challenge due to small object sizes, varying viewpoints, and changing environmental conditions. These challenges are exacerbated when operating during daytime and nighttime scenarios where illumination differences can heavily impact detection performance. This work is motivated by military object detection applications where the ability to reliably identify small objects such as landmines or unexploded ordnance from aerial imagery presents a critical safety need and a significant technical challenge. In this paper, we investigate object detection using both visible (RGB) and infrared (IR) imagery to improve robustness and reliability across diverse operating conditions. Various YOLO-based object detection models are trained and evaluated on aerial data collected using a multimodal sensor UAV platform. Experiments were conducted separately during daylight, low-light, and twilight scenarios. The results demonstrate a high level of accuracy achieving 90.8% on the daytime dataset, 98.5% on the nighttime dataset, and over 64% on the semi-illuminated dataset where material classification is employed. This study highlights the challenges and insights into the role of illumination and sensor modality in UAV-based object detection towards reliable perception.","abstract_has_math":false,"creators":["Nielsen, Erik"],"institution":null,"degree_name":"Master of Science (MS)","degree_level":"Thesis","degree_discipline":"Electrical and Computer Engineering","degree_department":null,"school":null,"contributors":["Goutam Koley","Adam Hoover","Yongkai Wu"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T07:34:07Z","subjects":["YOLO","UAV","small object","object detection","military object","deep learning","infrared","RGB","Computer Engineering","Computer Sciences"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://open.clemson.edu/all_theses/4742","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://open.clemson.edu/all_theses/4742","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://open.clemson.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Aopen.clemson.edu%3Aall_theses-5773","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Goutam Koley","Adam Hoover","Yongkai Wu"]},{"key":"dc:creator","label":"Author","values":["Nielsen, Erik"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2026-04-15T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2026-05-01T07:00:00Z"]},{"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 (MS)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["YOLO","UAV","small object","object detection","military object","deep learning","infrared","RGB","Computer Engineering","Computer Sciences"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://open.clemson.edu/all_theses/4742"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Object detection in unmanned aerial vehicles (UAVs) present a unique challenge due to small object sizes, varying viewpoints, and changing environmental conditions. These challenges are exacerbated when operating during daytime and nighttime scenarios where illumination differences can heavily impact detection performance. This work is motivated by military object detection applications where the ability to reliably identify small objects such as landmines or unexploded ordnance from aerial imagery presents a critical safety need and a significant technical challenge. In this paper, we investigate object detection using both visible (RGB) and infrared (IR) imagery to improve robustness and reliability across diverse operating conditions. Various YOLO-based object detection models are trained and evaluated on aerial data collected using a multimodal sensor UAV platform. Experiments were conducted separately during daylight, low-light, and twilight scenarios. The results demonstrate a high level of accuracy achieving 90.8% on the daytime dataset, 98.5% on the nighttime dataset, and over 64% on the semi-illuminated dataset where material classification is employed. This study highlights the challenges and insights into the role of illumination and sensor modality in UAV-based object detection towards reliable perception."]},{"key":"dc:title","label":"Title","values":["Multimodal Aerial Image-based Ground Object Detection and Classification using YOLO"]}]}],"canonical_facts":{"dc:contributor":["Goutam Koley","Adam Hoover","Yongkai Wu"],"dc:creator":["Nielsen, Erik"],"dc:date.available":["2026-04-15T07:00:00Z"],"dc:date.created":["2026-05-01T07:00:00Z"],"dc:description.abstract":["Object detection in unmanned aerial vehicles (UAVs) present a unique challenge due to small object sizes, varying viewpoints, and changing environmental conditions. These challenges are exacerbated when operating during daytime and nighttime scenarios where illumination differences can heavily impact detection performance. This work is motivated by military object detection applications where the ability to reliably identify small objects such as landmines or unexploded ordnance from aerial imagery presents a critical safety need and a significant technical challenge. In this paper, we investigate object detection using both visible (RGB) and infrared (IR) imagery to improve robustness and reliability across diverse operating conditions. Various YOLO-based object detection models are trained and evaluated on aerial data collected using a multimodal sensor UAV platform. Experiments were conducted separately during daylight, low-light, and twilight scenarios. The results demonstrate a high level of accuracy achieving 90.8% on the daytime dataset, 98.5% on the nighttime dataset, and over 64% on the semi-illuminated dataset where material classification is employed. This study highlights the challenges and insights into the role of illumination and sensor modality in UAV-based object detection towards reliable perception."],"dc:identifier":["https://open.clemson.edu/all_theses/4742"],"dc:subject":["YOLO","UAV","small object","object detection","military object","deep learning","infrared","RGB","Computer Engineering","Computer Sciences"],"dc:title":["Multimodal Aerial Image-based Ground Object Detection and Classification using YOLO"],"thesis:degree_discipline":["Electrical and Computer Engineering"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-11-19T07:34:07Z"}