Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper addresses the challenge of high-altitude UAVs detecting small, partially observable ground targets by formulating the problem as a POMDP and solving it with POMCP. The approach leverages a PTZ camera for active sensing and employs selective ensemble detection for improved reasoning, outperforming baselines in detection efficiency and resolution independence. The method enables robust target identification even when targets are within the field of view but obscured by scale.
A PTZ camera's pan-tilt-zoom capability, guided by POMCP, unlocks efficient sparse ground target search for high-altitude UAVs, bypassing resolution limitations.
Unmanned aerial vehicles (UAVs) searching for ground targets from a high altitude face a unique challenge, particularly when the target is already within the field of view but effectively unobservable because of its small apparent scale. Standard object detectors often underperform in such scenarios because of resolution downscaling and limited context. In contrast, active object search frameworks address this challenge by directing the agent to a suitable pose to gather richer visual information. However, flight regulations in urban airspace often restrict such physical movements for UAVs. As an alternative active sensing approach, the UAV can leverage the pan-tilt-zoom (PTZ) mechanism of the onboard camera to dynamically adjust its field of view and sequentially gather enhanced visual information from specific regions of interest. Once the candidate locations of the target are identified, it can deploy more expensive object detection schemes, such as an ensemble of multiple models, to get better reasoning at a fixed scale. In this work, we formulate the sequential exploration with PTZ operation as a partially observable Markov decision process (POMDP), in which the agent maintains a belief state over the target's true location. To solve the POMDP, we deploy partially observable Monte Carlo planning (POMCP), where we condition the sensing reliability on target object scale and deploy selective ensemble detection as an additional reasoning step. We validate our methodology with experiments in a photorealistic simulator under different environmental conditions and vehicle states, showing detection of ground targets at variable scales with significantly fewer steps and minimal dependence on sensor resolution compared to baseline methods.