| Summary: | Utilizing Unmanned Aerial Vehicles (UAVs) plays a pivotal role in the localization of ground construction personnel targets within the specialized operational environments of the energy industry. To ensure the safety of personnel in these areas effectively, this study introduces an innovative dual UAV cooperative positioning system designed to address the challenges of personnel localization in various complex settings. In the first place, the research establishes a dual UAV collaborative remote sensing platform, specifically tailored for executing dual UAV flight control and ground personnel identification and localization tasks. Subsequently, this study proposes a high-precision ground personnel localization solution. This solution integrates the flight data of two UAVs with the pixel coordinates of targets in natural remote sensing imagery, enabling the precise localization of moving targets within complex environments. Moreover, due to the irregularity of ground personnel shapes in imagery, this research introduces an improved rotating target detection network based on the YOLOv7 architecture. This network is specifically optimized for detecting ground targets in remote sensing imagery, significantly enhancing the accuracy of target localization. Extensive experimental validation has demonstrated that this localization system can maintain target localization errors within a 5-meter threshold, effectively enhancing the safety and efficiency of personnel in specific operational areas of the energy industry.
|
|---|