Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wu, Xianke, Bai, Songlin, Li, Chengxiang, Luo, Zhiyao, Tian, Yulin, Zhu, Fenghua, Lv, Yisheng, Tian, Yonglin
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2603.13919
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866918388122517504
author Wu, Xianke
Bai, Songlin
Li, Chengxiang
Luo, Zhiyao
Tian, Yulin
Zhu, Fenghua
Lv, Yisheng
Tian, Yonglin
author_facet Wu, Xianke
Bai, Songlin
Li, Chengxiang
Luo, Zhiyao
Tian, Yulin
Zhu, Fenghua
Lv, Yisheng
Tian, Yonglin
contents While Vehicle-to-Vehicle (V2V) collaboration extends sensing ranges through multi-agent data sharing, its reliability remains severely constrained by ground-level occlusions and the limited perspective of chassis-mounted sensors, which often result in critical perception blind spots. We propose OpenCOOD-Air, a novel framework that integrates UAVs as extensible platforms into V2V collaborative perception to overcome these constraints. To mitigate gradient interference from ground-air domain gaps and data sparsity, we adopt a transfer learning strategy to fine-tune UAV weights from pre-trained V2V models. To prevent the spatial information loss inherent in this transition, we formulate ground-air collaborative perception as a heterogeneous integration task with explicit altitude supervision and introduce a Cross-Domain Spatial Converter (CDSC) and a Spatial Offset Prediction Transformer (SOPT). Furthermore, we present the OPV2V-Air benchmark to validate the transition from V2V to Vehicle-to-Vehicle-to-UAV. Compared to state-of-the-art methods, our approach improves 2D and 3D AP@0.7 by 4% and 7%, respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2603_13919
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle OpenCOOD-Air: Prompting Heterogeneous Ground-Air Collaborative Perception with Spatial Conversion and Offset Prediction
Wu, Xianke
Bai, Songlin
Li, Chengxiang
Luo, Zhiyao
Tian, Yulin
Zhu, Fenghua
Lv, Yisheng
Tian, Yonglin
Computer Vision and Pattern Recognition
While Vehicle-to-Vehicle (V2V) collaboration extends sensing ranges through multi-agent data sharing, its reliability remains severely constrained by ground-level occlusions and the limited perspective of chassis-mounted sensors, which often result in critical perception blind spots. We propose OpenCOOD-Air, a novel framework that integrates UAVs as extensible platforms into V2V collaborative perception to overcome these constraints. To mitigate gradient interference from ground-air domain gaps and data sparsity, we adopt a transfer learning strategy to fine-tune UAV weights from pre-trained V2V models. To prevent the spatial information loss inherent in this transition, we formulate ground-air collaborative perception as a heterogeneous integration task with explicit altitude supervision and introduce a Cross-Domain Spatial Converter (CDSC) and a Spatial Offset Prediction Transformer (SOPT). Furthermore, we present the OPV2V-Air benchmark to validate the transition from V2V to Vehicle-to-Vehicle-to-UAV. Compared to state-of-the-art methods, our approach improves 2D and 3D AP@0.7 by 4% and 7%, respectively.
title OpenCOOD-Air: Prompting Heterogeneous Ground-Air Collaborative Perception with Spatial Conversion and Offset Prediction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.13919