CoFeatNet: An Efficient Multimodal Feature Extraction Network for Cooperative Vehicle-to-Infrastructure 3-D Object Detection
- 6 February 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (8) , 17393-17404
Abstract
Accurate 3-D object detection in cooperative vehicle-to-infrastructure (V2X) scenarios presents significant challenges due to heterogeneous sensor modalities, semantic inconsistency across domains, and the need for efficient information transmission in real time. To address these issues, we propose CoFeatNet, a unified and lightweight multimodal feature extraction network tailored for cooperative perception tasks. CoFeatNet integrates depthwise separable convolutions, adaptive pyramid sampling, transposed convolutions, and both channel-wise and cross-scale attention mechanisms into a cohesive framework that effectively reduces structural discrepancies among heterogeneous features, enhances semantic interactions between vehicle- and infrastructure-side inputs, and minimizes computational overhead. In addition, a geometry-aware compensation mechanism is introduced to mitigate distortion effects in monocular imagery by leveraging intrinsic camera parameters through an attention-guided strategy. Extensive experiments conducted on the DAIR-V2X dataset demonstrate the effectiveness of our approach, with CoFeatNet achieving 17.40% AP ${}_{\text {3-D}}$ and 23.92% APBEV, outperforming the EMIFF baseline by 1.79% and 2.48%, respectively. These results highlight the superior accuracy and efficiency of CoFeatNet in complex V2X cooperative environments.Keywords
This publication has 40 references indexed in Scilit:
- Dp-M3D: Monocular 3D object detection algorithm with depth perception capabilityKnowledge-Based Systems, 2025
- Real-time semantic segmentation network with an enhanced backbone based on Atrous spatial pyramid pooling moduleEngineering Applications of Artificial Intelligence, 2024
- BEVFormer: Learning Bird’s-Eye-View Representation from Multi-camera Images via Spatiotemporal Transformers2022
- V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer2022
- Perception synergy optimization with deep reinforcement learning for cooperative perception in C-V2V scenariosVehicular Communications, 2022
- A comprehensive survey of recent trends in deep learning for digital images augmentationArtificial Intelligence Review, 2021
- Cascaded hierarchical atrous spatial pyramid pooling module for semantic segmentationPattern Recognition, 2021
- Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D2020
- V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Prediction2020
- When2com: Multi-Agent Perception via Communication Graph Grouping2020