DCP-Net: A Distributed Collaborative Perception Network for Remote Sensing Semantic Segmentation

TL;DR

DCP-Net is a novel distributed collaborative perception network that enhances remote sensing semantic segmentation by integrating multi-platform features, selecting collaboration partners, and addressing feature misalignment, leading to state-of-the-art performance.

Contribution

The paper introduces DCP-Net, a distributed network with modules for feature integration, partner selection, and feature fusion, advancing multi-platform remote sensing perception.

Findings

DCP-Net improves mIoU by up to 16.89%.

It outperforms existing methods across three datasets.

The approach enhances perception accuracy and collaboration efficiency.

Abstract

Onboard intelligent processing is widely applied in emergency tasks in the field of remote sensing. However, it is predominantly confined to an individual platform with a limited observation range as well as susceptibility to interference, resulting in limited accuracy. Considering the current state of multi-platform collaborative observation, this article innovatively presents a distributed collaborative perception network called DCP-Net. Firstly, the proposed DCP-Net helps members to enhance perception performance by integrating features from other platforms. Secondly, a self-mutual information match module is proposed to identify collaboration opportunities and select suitable partners, prioritizing critical collaborative features and reducing redundant transmission cost. Thirdly, a related feature fusion module is designed to address the misalignment between local and collaborative features, improving the quality of fused features for the downstream task. We conduct extensive experiments and visualization analyses using three semantic segmentation datasets, including Potsdam, iSAID and DFC23. The results demonstrate that DCP-Net outperforms the existing methods comprehensively, improving mIoU by 2.61%~16.89% at the highest collaboration efficiency, which promotes the performance to a state-of-the-art level.