UVCPNet: A UAV-Vehicle Collaborative Perception Network for 3D Object Detection

TL;DR

UVCPNet is a novel UAV-ground collaborative perception framework that enhances 3D object detection accuracy by addressing cross-domain disparities and depth estimation challenges through specialized modules and a virtual dataset.

Contribution

The paper introduces a new framework with the CDCA and CDO modules for improved aerial-ground perception and provides a virtual dataset for training and evaluation.

Findings

Improves detection accuracy by 6.1% on V2U-COO dataset.

Enhances detection accuracy by 2.7% on DAIR-V2X dataset.

Validates effectiveness through extensive experiments.

Abstract

With the advancement of collaborative perception, the role of aerial-ground collaborative perception, a crucial component, is becoming increasingly important. The demand for collaborative perception across different perspectives to construct more comprehensive perceptual information is growing. However, challenges arise due to the disparities in the field of view between cross-domain agents and their varying sensitivity to information in images. Additionally, when we transform image features into Bird's Eye View (BEV) features for collaboration, we need accurate depth information. To address these issues, we propose a framework specifically designed for aerial-ground collaboration. First, to mitigate the lack of datasets for aerial-ground collaboration, we develop a virtual dataset named V2U-COO for our research. Second, we design a Cross-Domain Cross-Adaptation (CDCA) module to align the target information obtained from different domains, thereby achieving more accurate perception results. Finally, we introduce a Collaborative Depth Optimization (CDO) module to obtain more precise depth estimation results, leading to more accurate perception outcomes. We conduct extensive experiments on both our virtual dataset and a public dataset to validate the effectiveness of our framework. Our experiments on the V2U-COO dataset and the DAIR-V2X dataset demonstrate that our method improves detection accuracy by 6.1% and 2.7%, respectively.