Primary Investigator (PI) Name
Adeel Khalid
Department
SPCEET – Mechanical Engineering
Abstract
Unmanned Aerial Vehicles (UAVs) operating without authorization pose a serious risk, especially in areas like airports, military installations, and other critical infrastructure. UAVs are difficult to detect due to their small size, speed, and low altitude flight capabilities. While LiDAR, RGB imaging, and thermal sensing technologies are widely used in surveillance and object detection, limited research has directly evaluated their effectiveness in detecting UAVs of varying size at different distances. This research aims to systematically evaluate LiDAR, RGB, and thermal sensors to determine which detection modality has the highest detection accuracy for intruder UAV identification. In this project, a controlled test is established in which target UAVs of varying size are flown at varying altitudes and distances. Each sensor independently collects data on the target UAV. The data is processed using standardized algorithms to obtain evaluation metrics like detection accuracy and false positive rate. Comparative analysis is used to identify the strengths and limitations of each sensor type across distance and target UAV size. Expected results suggest that thermal imaging may outperform RGB due to background noise, while LiDAR may provide higher detection accuracy due to its nonreliance on background contrast. Findings from this study will contribute to the development of more effective counter UAV detection strategies and provide data driven recommendations for sensor selection in these strategies.
Presented at
2026 - The Thirtieth Annual Symposium of Student Scholars
Evaluation of LiDAR, RGB, and Thermal Sensors for UAV Detection
2026 - The Thirtieth Annual Symposium of Student Scholars
Unmanned Aerial Vehicles (UAVs) operating without authorization pose a serious risk, especially in areas like airports, military installations, and other critical infrastructure. UAVs are difficult to detect due to their small size, speed, and low altitude flight capabilities. While LiDAR, RGB imaging, and thermal sensing technologies are widely used in surveillance and object detection, limited research has directly evaluated their effectiveness in detecting UAVs of varying size at different distances. This research aims to systematically evaluate LiDAR, RGB, and thermal sensors to determine which detection modality has the highest detection accuracy for intruder UAV identification. In this project, a controlled test is established in which target UAVs of varying size are flown at varying altitudes and distances. Each sensor independently collects data on the target UAV. The data is processed using standardized algorithms to obtain evaluation metrics like detection accuracy and false positive rate. Comparative analysis is used to identify the strengths and limitations of each sensor type across distance and target UAV size. Expected results suggest that thermal imaging may outperform RGB due to background noise, while LiDAR may provide higher detection accuracy due to its nonreliance on background contrast. Findings from this study will contribute to the development of more effective counter UAV detection strategies and provide data driven recommendations for sensor selection in these strategies.