A late-intermediate fusion method that transmits only 2D and 3D detection boxes and confidence scores among UAVs, then injects them into the receiver's BEV features, achieves 72.1% mAP on UAV3D with minimal bandwidth.
Drones Help Drones: A Collaborative Framework for Multi-Drone Object Trajectory Prediction and Beyond
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Collaborative trajectory prediction can comprehensively forecast the future motion of objects through multi-view complementary information. However, it encounters two main challenges in multi-drone collaboration settings. The expansive aerial observations make it difficult to generate precise Bird's Eye View (BEV) representations. Besides, excessive interactions can not meet real-time prediction requirements within the constrained drone-based communication bandwidth. To address these problems, we propose a novel framework named "Drones Help Drones" (DHD). Firstly, we incorporate the ground priors provided by the drone's inclined observation to estimate the distance between objects and drones, leading to more precise BEV generation. Secondly, we design a selective mechanism based on the local feature discrepancy to prioritize the critical information contributing to prediction tasks during inter-drone interactions. Additionally, we create the first dataset for multi-drone collaborative prediction, named "Air-Co-Pred", and conduct quantitative and qualitative experiments to validate the effectiveness of our DHD framework.The results demonstrate that compared to state-of-the-art approaches, DHD reduces position deviation in BEV representations by over 20% and requires only a quarter of the transmission ratio for interactions while achieving comparable prediction performance. Moreover, DHD also shows promising generalization to the collaborative 3D object detection in CoPerception-UAVs.
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Is Intermediate Fusion All You Need for UAV-based Collaborative Perception?
A late-intermediate fusion method that transmits only 2D and 3D detection boxes and confidence scores among UAVs, then injects them into the receiver's BEV features, achieves 72.1% mAP on UAV3D with minimal bandwidth.