C2F-Net: Coarse-to-Fine Multidrone Collaborative Perception Network for Object Trajectory Prediction

Multidrone collaborative perception network can forecast the motion trajectories of grounded objects by aggregating intragroup communication and interaction, exhibiting significant potential across various applications. Existing collaborative perception methods struggle to address the nonuniform spa...

Full description

Saved in:
Bibliographic Details
Main Authors: Mingxin Chen, Zhirui Wang, Zhechao Wang, Liangjin Zhao, Peirui Cheng, Hongqi Wang
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10883025/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849709032139390976
author Mingxin Chen
Zhirui Wang
Zhechao Wang
Liangjin Zhao
Peirui Cheng
Hongqi Wang
author_facet Mingxin Chen
Zhirui Wang
Zhechao Wang
Liangjin Zhao
Peirui Cheng
Hongqi Wang
author_sort Mingxin Chen
collection DOAJ
description Multidrone collaborative perception network can forecast the motion trajectories of grounded objects by aggregating intragroup communication and interaction, exhibiting significant potential across various applications. Existing collaborative perception methods struggle to address the nonuniform spatial distribution of targets and the spatial heterogeneity of multisource perception information typical in remote sensing scenarios. To tackle these challenges, we propose a coarse-to-fine feature fusion network C2F-Net, utilizing coarse-grained information interaction to guide the fusion of fine-grained features. Our approach includes a selective coarse-to-fine feature collaboration module that estimates perception levels of specific areas based on bird's-eye-view features, selectively collaborates on sparse features according to complementary information principles, and achieves efficient spatial feature interaction and fusion. In addition, we employ a region-aware effectiveness enhancement module, leveraging the differences between swarm and individual perception as prior knowledge to guide regional perception level estimation, improving comprehensive environmental understanding. We also introduce a simulation dataset named CoD-Pred for multidrone collaborative trajectory prediction. Extensive experiments demonstrate that C2F-Net significantly improves the accuracy of multidrone collaborative trajectory prediction, which increases mIoU by 2.7% to 3.3% and VPQ by 1.0% to 9.1% under comparable information transmission conditions, offering an effective and efficient solution for multidrone collaborative perception.
format Article
id doaj-art-0830bb6023b842d7a0ca555dc536fd18
institution DOAJ
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-0830bb6023b842d7a0ca555dc536fd182025-08-20T03:15:27ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01186314632810.1109/JSTARS.2025.354124910883025C2F-Net: Coarse-to-Fine Multidrone Collaborative Perception Network for Object Trajectory PredictionMingxin Chen0Zhirui Wang1https://orcid.org/0000-0003-2877-0384Zhechao Wang2https://orcid.org/0009-0003-9019-5031Liangjin Zhao3https://orcid.org/0000-0002-2590-591XPeirui Cheng4https://orcid.org/0000-0002-4993-6753Hongqi Wang5Aerospace Information Research Institute and the Key Laboratory of Target Cognition and Application Technology (TCAT), Chinese Academy of Sciences, Beijing, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaAerospace Information Research Institute and the Key Laboratory of Target Cognition and Application Technology (TCAT), Chinese Academy of Sciences, Beijing, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaMultidrone collaborative perception network can forecast the motion trajectories of grounded objects by aggregating intragroup communication and interaction, exhibiting significant potential across various applications. Existing collaborative perception methods struggle to address the nonuniform spatial distribution of targets and the spatial heterogeneity of multisource perception information typical in remote sensing scenarios. To tackle these challenges, we propose a coarse-to-fine feature fusion network C2F-Net, utilizing coarse-grained information interaction to guide the fusion of fine-grained features. Our approach includes a selective coarse-to-fine feature collaboration module that estimates perception levels of specific areas based on bird's-eye-view features, selectively collaborates on sparse features according to complementary information principles, and achieves efficient spatial feature interaction and fusion. In addition, we employ a region-aware effectiveness enhancement module, leveraging the differences between swarm and individual perception as prior knowledge to guide regional perception level estimation, improving comprehensive environmental understanding. We also introduce a simulation dataset named CoD-Pred for multidrone collaborative trajectory prediction. Extensive experiments demonstrate that C2F-Net significantly improves the accuracy of multidrone collaborative trajectory prediction, which increases mIoU by 2.7% to 3.3% and VPQ by 1.0% to 9.1% under comparable information transmission conditions, offering an effective and efficient solution for multidrone collaborative perception.https://ieeexplore.ieee.org/document/10883025/Collaborative perceptiondrone swarmremote sensingtrajectory prediction
spellingShingle Mingxin Chen
Zhirui Wang
Zhechao Wang
Liangjin Zhao
Peirui Cheng
Hongqi Wang
C2F-Net: Coarse-to-Fine Multidrone Collaborative Perception Network for Object Trajectory Prediction
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Collaborative perception
drone swarm
remote sensing
trajectory prediction
title C2F-Net: Coarse-to-Fine Multidrone Collaborative Perception Network for Object Trajectory Prediction
title_full C2F-Net: Coarse-to-Fine Multidrone Collaborative Perception Network for Object Trajectory Prediction
title_fullStr C2F-Net: Coarse-to-Fine Multidrone Collaborative Perception Network for Object Trajectory Prediction
title_full_unstemmed C2F-Net: Coarse-to-Fine Multidrone Collaborative Perception Network for Object Trajectory Prediction
title_short C2F-Net: Coarse-to-Fine Multidrone Collaborative Perception Network for Object Trajectory Prediction
title_sort c2f net coarse to fine multidrone collaborative perception network for object trajectory prediction
topic Collaborative perception
drone swarm
remote sensing
trajectory prediction
url https://ieeexplore.ieee.org/document/10883025/
work_keys_str_mv AT mingxinchen c2fnetcoarsetofinemultidronecollaborativeperceptionnetworkforobjecttrajectoryprediction
AT zhiruiwang c2fnetcoarsetofinemultidronecollaborativeperceptionnetworkforobjecttrajectoryprediction
AT zhechaowang c2fnetcoarsetofinemultidronecollaborativeperceptionnetworkforobjecttrajectoryprediction
AT liangjinzhao c2fnetcoarsetofinemultidronecollaborativeperceptionnetworkforobjecttrajectoryprediction
AT peiruicheng c2fnetcoarsetofinemultidronecollaborativeperceptionnetworkforobjecttrajectoryprediction
AT hongqiwang c2fnetcoarsetofinemultidronecollaborativeperceptionnetworkforobjecttrajectoryprediction