Power transmission line inspection is essential for maintaining the safety and reliability of modern infrastructure, yet traditional methods remain costly, slow, and potentially hazardous. With the increasing use of unmanned aerial vehicles (UAVs), automated vision systems have emerged as a promising alternative for large-scale aerial inspection. A key component of these systems is power line segmentation, which supports downstream tasks such as clearance analysis, vegetation monitoring, damage assessment, and navigation. However, power lines are difficult to segment in aerial imagery because they are narrow, low-contrast, and often obscured by cluttered backgrounds and changing environmental conditions.
This thesis presents a unified study of trustworthy power line perception from aerial imagery through two complementary directions. First, it examines promptable and foundation-model-based segmentation for power line extraction. Experiments using zero-shot, text-prompt-based, and segmentation-prompt-based settings show that stronger spatial guidance improves performance, but current promptable models still struggle to preserve the continuity, thickness, and geometric precision required in complex scenes. Second, this thesis introduces an LLM-as-a-Judge watchdog framework for monitoring segmentation quality during deployment. The framework evaluates segmentation overlays for repeatability, perceptual sensitivity, and semantic coherence under realistic corruptions such as fog, rain, snow, shadow, and sun flare. Results show that the judge produces stable categorical assessments while appropriately lowering confidence as visual reliability degrades. Together, these findings show that trustworthy power line inspection requires both accurate segmentation and an independent mechanism for detecting unreliable outputs.
","abstract_html":"<p>Power transmission line inspection is essential for maintaining the safety and reliability of modern infrastructure, yet traditional methods remain costly, slow, and potentially hazardous. With the increasing use of unmanned aerial vehicles (UAVs), automated vision systems have emerged as a promising alternative for large-scale aerial inspection. A key component of these systems is power line segmentation, which supports downstream tasks such as clearance analysis, vegetation monitoring, damage assessment, and navigation. However, power lines are difficult to segment in aerial imagery because they are narrow, low-contrast, and often obscured by cluttered backgrounds and changing environmental conditions.</p> <p>This thesis presents a unified study of trustworthy power line perception from aerial imagery through two complementary directions. First, it examines promptable and foundation-model-based segmentation for power line extraction. Experiments using zero-shot, text-prompt-based, and segmentation-prompt-based settings show that stronger spatial guidance improves performance, but current promptable models still struggle to preserve the continuity, thickness, and geometric precision required in complex scenes. Second, this thesis introduces an LLM-as-a-Judge watchdog framework for monitoring segmentation quality during deployment. The framework evaluates segmentation overlays for repeatability, perceptual sensitivity, and semantic coherence under realistic corruptions such as fog, rain, snow, shadow, and sun flare. Results show that the judge produces stable categorical assessments while appropriately lowering confidence as visual reliability degrades. Together, these findings show that trustworthy power line inspection requires both accurate segmentation and an independent mechanism for detecting unreliable outputs.</p>","abstract_has_math":false,"creators":["Hossain, Akram"],"institution":null,"degree_name":"Master of Science (MS)","degree_level":"Masters Thesis","degree_discipline":null,"degree_department":null,"school":null,"contributors":["Dr. Rabab Abdelfattah","Dr. Sarah Lee","Dr. Chaoyang Zhang"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026-05-01T07:00:00Z","date_published":"2026-05-01T07:00:00Z","updated_at":"2026-07-24T05:45:55Z","subjects":["power line segmentation","autonomous UAV inspection","LLM-as-a-judge","Infrastructure monitoring","Machine vision","foundation model based power line segmentation","Computer and Systems Architecture","Hardware Systems","Robotics"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://aquila.usm.edu/masters_theses/1188","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Dr. Rabab Abdelfattah","Dr. Sarah Lee","Dr. Chaoyang Zhang"]},{"key":"dc:creator","label":"Author","values":["Hossain, Akram"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2027-05-31T07:00:00Z"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Masters 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":["power line segmentation","autonomous UAV inspection","LLM-as-a-judge","Infrastructure monitoring","Machine vision","foundation model based power line segmentation","Computer and Systems Architecture","Hardware Systems","Robotics"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://aquila.usm.edu/masters_theses/1188"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Power transmission line inspection is essential for maintaining the safety and reliability of modern infrastructure, yet traditional methods remain costly, slow, and potentially hazardous. With the increasing use of unmanned aerial vehicles (UAVs), automated vision systems have emerged as a promising alternative for large-scale aerial inspection. A key component of these systems is power line segmentation, which supports downstream tasks such as clearance analysis, vegetation monitoring, damage assessment, and navigation. However, power lines are difficult to segment in aerial imagery because they are narrow, low-contrast, and often obscured by cluttered backgrounds and changing environmental conditions.
This thesis presents a unified study of trustworthy power line perception from aerial imagery through two complementary directions. First, it examines promptable and foundation-model-based segmentation for power line extraction. Experiments using zero-shot, text-prompt-based, and segmentation-prompt-based settings show that stronger spatial guidance improves performance, but current promptable models still struggle to preserve the continuity, thickness, and geometric precision required in complex scenes. Second, this thesis introduces an LLM-as-a-Judge watchdog framework for monitoring segmentation quality during deployment. The framework evaluates segmentation overlays for repeatability, perceptual sensitivity, and semantic coherence under realistic corruptions such as fog, rain, snow, shadow, and sun flare. Results show that the judge produces stable categorical assessments while appropriately lowering confidence as visual reliability degrades. Together, these findings show that trustworthy power line inspection requires both accurate segmentation and an independent mechanism for detecting unreliable outputs.
"]},{"key":"dc:title","label":"Title","values":["Toward Trustworthy Power Line Perception from Aerial Imagery: Segmentation and Reliability Monitoring"]}]}],"canonical_facts":{"dc:contributor":["Dr. Rabab Abdelfattah","Dr. Sarah Lee","Dr. Chaoyang Zhang"],"dc:creator":["Hossain, Akram"],"dc:date.available":["2027-05-31T07:00:00Z"],"dc:description.abstract":["Power transmission line inspection is essential for maintaining the safety and reliability of modern infrastructure, yet traditional methods remain costly, slow, and potentially hazardous. With the increasing use of unmanned aerial vehicles (UAVs), automated vision systems have emerged as a promising alternative for large-scale aerial inspection. A key component of these systems is power line segmentation, which supports downstream tasks such as clearance analysis, vegetation monitoring, damage assessment, and navigation. However, power lines are difficult to segment in aerial imagery because they are narrow, low-contrast, and often obscured by cluttered backgrounds and changing environmental conditions.
This thesis presents a unified study of trustworthy power line perception from aerial imagery through two complementary directions. First, it examines promptable and foundation-model-based segmentation for power line extraction. Experiments using zero-shot, text-prompt-based, and segmentation-prompt-based settings show that stronger spatial guidance improves performance, but current promptable models still struggle to preserve the continuity, thickness, and geometric precision required in complex scenes. Second, this thesis introduces an LLM-as-a-Judge watchdog framework for monitoring segmentation quality during deployment. The framework evaluates segmentation overlays for repeatability, perceptual sensitivity, and semantic coherence under realistic corruptions such as fog, rain, snow, shadow, and sun flare. Results show that the judge produces stable categorical assessments while appropriately lowering confidence as visual reliability degrades. Together, these findings show that trustworthy power line inspection requires both accurate segmentation and an independent mechanism for detecting unreliable outputs.
"],"dc:identifier":["https://aquila.usm.edu/masters_theses/1188"],"dc:subject":["power line segmentation","autonomous UAV inspection","LLM-as-a-judge","Infrastructure monitoring","Machine vision","foundation model based power line segmentation","Computer and Systems Architecture","Hardware Systems","Robotics"],"dc:title":["Toward Trustworthy Power Line Perception from Aerial Imagery: Segmentation and Reliability Monitoring"],"thesis:degree_level":["Masters Thesis"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-07-24T05:45:55Z"}