trACT (temporal revelation Airborne Camera Trap) is a lightweight, real‑time aerial robotics framework for autonomous consumer drones. It uses Temporal Max Pooling to convert subtle ground motion into robust signals, coupled with self‑supervised motion anomaly detection to separate target movement from environmental noise. The system also incorporates motion prediction, gimbal‑stabilized optical zoom verification, and balanced multi‑target verification, enabling precise target confirmation in challenging forested and surveillance environments.
arXiv:2606. 08249v1 Announce Type: cross Abstract: Reliable wildlife monitoring is essential for ecology and conservation, yet many existing methods, such as tagging, capture, and close-range observation, can alter the very behaviors they aim to measure.
The paper introduces a decentralized, vision-based system using multiple quadrotors equipped with a single RGB camera for monitoring wildlife. It emphasizes scalability, low bandwidth, and minimal sensor requirements, enabling robust identification and tracking of large species in natural habitats. The authors present novel coordination and tracking algorithms that operate without centralized communication, and validate the approach with real-world field experiments.
arXiv:2606. 03441v1 Announce Type: cross Abstract: Autonomous vision-based perching of quadrotors on moving inclined platforms is critical for air-ground collaboration but remains challenging due to the limited field of view (FOV).
The paper presents a method for tracking insects in the field using a stereoscopic event-based camera setup. By converting asynchronous events into conventional video formats, the authors combine the high temporal resolution of event cameras with standard video processing techniques to capture detailed insect flight movements. The stereoscopic configuration enables continuous, low‑latency 3D tracking, reducing motion blur and improving accuracy in natural environments.
Event cameras offer microsecond-level temporal resolution and high dynamic range for low-altitude UAV perception. However, long-range UAVs often produce sparse, fragmented, and noise-contaminated event responses, where one semantic target may appear as multiple spatially separated blobs.
arXiv:2609.15171v1 Announce Type: new Abstract: Airborne optical tracking of uncrewed aerial vehicle (UAV) swarms is challenging due to extremely small target scales, rapid viewpoint changes, and clu...
arXiv:2606. 06147v1 Announce Type: new Abstract: End-to-end Vision-Language-Action (VLA) models have shown promise in UAV navigation.
FlyingDrones is a newly released dataset and benchmark for optical flow estimation from UAV motion, featuring dense ground‑truth flow and segmentation masks generated via physically based rendering. The benchmark introduces resolution‑normalized metrics (EPE Norm) and evaluates 16 state‑of‑the‑art model families on a stratified subset of 999 flow pairs across three resolutions, revealing that model performance diverges more at higher resolutions. Complementary studies demonstrate that the synthetic ranking correlates moderately with real‑world UAV footage performance and that fine‑tuning with FlyingDrones data can significantly reduce drone‑region error and improve localization.
arXiv:2608. 15259v1 Announce Type: cross Abstract: Unmanned Aerial Vehicles (UAVs) play a crucial role in various scenarios ranging from disaster response to traffic surveillance.
arXiv:2608. 19866v1 Announce Type: new Abstract: This paper presents a novel data-driven approach to camera-based autonomy for micro-drones in GPS-denied, radio-challenging indoor environments.
arXiv:2607. 10180v1 Announce Type: cross Abstract: We introduce ActiveFly-Bench, the first benchmark to bridge cyberspace reasoning and physical-world interaction for UAV embodied perception.
arXiv:2607. 12065v1 Announce Type: cross Abstract: While visual navigation has been extensively studied in agricultural robotics, most existing systems assume daytime conditions.