As the “visual perception hub” of unmanned aerial vehicles (UAVs), electro-optical (EO) pods play an increasingly critical role in tasks such as intelligence gathering, situational awareness, target tracking, and localization. With the expanding scope and depth of UAV applications, higher demands are placed on the precision and adaptability of installation error calibration techniques for EO pods. Current mainstream calibration methods typically require specialized procedures under constrained conditions, while few approaches integrate existing UAV system capabilities and mission requirements, which leads to cumbersome, time-consuming processes and suboptimal alignment between calibration outcomes and task objectives. This paper proposes an online calibration method for UAV EO pod installation errors based on target tracking, which can rapidly compute the optimal closed-form solution for installation errors by leveraging UAV tracking missions. First, an observation equation for pod installation errors is established using tracking results. Second, multi-temporal observations are combined to model the calibration problem as an optimal rotation matrix estimation task, and then the optimal closed-form solution for installation errors is derived. Concurrently, a statistics-based approximate calibration method is introduced specifically for tracking missions. Furthermore, an online calibration system compatible with diverse UAV platforms is designed, along with different rapid calibration schemes for emergency response scenarios, fully incorporating existing system capabilities and mission needs. Finally, a fixed-wing UAV experimental platform is developed, with calibration tests conducted under various flight regimes. Experimental results validate the feasibility and robustness of the proposed methodology.

Air-to-ground visual target persistent tracking technology for swarm drones, as a crucial interdisciplinary research area integrating computer vision, autonomous systems, and swarm collaboration, has gained increasing prominence in anti-terrorism operations, disaster relief, and other emergency response applications. While recent advancements have predominantly concentrated on improving long-term visual tracking through image algorithmic optimizations, insufficient exploration has been conducted on developing system-level persistent tracking architectures, leading to a high target loss rate and limited tracking endurance in complex scenarios. This paper designs an asynchronous multi-task parallel architecture for drone-based long-term tracking in air-to-ground scenarios, and improves the persistent tracking capability from three levels. At the image algorithm level, a long-term tracking system is constructed by integrating existing object detection YOLOv10, multi-object tracking DeepSort, and single-object tracking ECO algorithms. By leveraging their complementary strengths, the system enhances the performance of the detection and multi-object tracking while mitigating model drift in single-object tracking. At the drone system level, ground target absolute localization and geolocation-based drone spiral tracking strategies are conducted to improve target reacquisition rates after tracking loss. At the swarm collaboration level, an autonomous task allocation algorithm and relay tracking handover protocol are proposed, further enhancing the long-term tracking capability of swarm drones while boosting their autonomy. Finally, a practical swarm drone system for persistent air-to-ground visual tracking is developed and validated through extensive flight experiments under diverse scenarios. Results demonstrate the feasibility and robustness of the proposed persistent tracking framework and its adaptability to wild real-world applications.