CloudTrack: Scalable UAV Tracking with Cloud Semantics
This addresses the need for more autonomous and faster search and rescue operations using UAVs, though it appears incremental as it builds on existing tracking methods with semantic conditioning.
The paper tackles the problem of automatically identifying and tracking a missing person in UAV aerial footage using verbal descriptions, such as shirt color, without requiring dedicated training, and demonstrates its versatility and efficacy in experimental results.
Nowadays, unmanned aerial vehicles (UAVs) are commonly used in search and rescue scenarios to gather information in the search area. The automatic identification of the person searched for in aerial footage could increase the autonomy of such systems, reduce the search time, and thus increase the missed person's chances of survival. In this paper, we present a novel approach to perform semantically conditioned open vocabulary object tracking that is specifically designed to cope with the limitations of UAV hardware. Our approach has several advantages. It can run with verbal descriptions of the missing person, e.g., the color of the shirt, it does not require dedicated training to execute the mission and can efficiently track a potentially moving person. Our experimental results demonstrate the versatility and efficacy of our approach.