ITSC 2025 Paper Abstract

Paper VP-VP.62

Hao, Jiuwu (Institute of Automation of the Chinese Academy of Sciences), Sun, Liguo (Institute of Automation, Chinese Academy of Sciences), Wan, Yuting (Institute of Automation, Chinese Academy of Sciences), Wu, Yueyang (Institute of Automation, Chinese Academy of Sciences), Xiang, Ti (Institute of Automation, Chinese Academy of Sciences), Song, Haolin (Institute of Automation, Chinese Academy of Sciences), Lv, Pin (Institute of Automation, Chinese Academy of Sciences)

Is Intermediate Fusion All You Need for UAV-Based Collaborative Perception?

Scheduled for presentation during the Video Session "On-Demand Video Presentations" (VP-VP), Saturday, November 22, 2025, 08:00−18:00, On-Demand Platform

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on April 2, 2026

Keywords Vehicle-to-Infrastructure (V2I) and Vehicle-to-Vehicle (V2V) Communication Applications for Traffic Management, Real-time Object Detection and Tracking for Dynamic Traffic Environments

Abstract

Collaborative perception enhances environmental awareness through inter-agent communication and is regarded as a promising solution to intelligent transportation systems. However, existing collaborative methods for Unmanned Aerial Vehicles (UAVs) overlook the unique characteristics of the UAV perspective, resulting in substantial communication overhead. To address this issue, we propose a novel communication-efficient collaborative perception framework based on late-intermediate fusion, dubbed LIF. The core concept is to exchange informative and compact detection results and shift the fusion stage to the feature representation level. In particular, we leverage vision-guided positional embedding (VPE) and box-based virtual augmented feature (BoBEV) to effectively integrate complementary information from various agents. Additionally, we innovatively introduce an uncertainty-driven communication mechanism that uses uncertainty evaluation to select high-quality and reliable shared areas. Experimental results demonstrate that our LIF achieves superior performance with minimal communication bandwidth, proving its effectiveness and practicality. Code and models are available at https://github.com/uestchjw/LIF.