Litcius/Paper detail

EMIFF: Enhanced Multi-scale Image Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detection

Zhe Wang, Siqi Fan, Xiaoliang Huo, Tongda Xu, Yan Wang, Jingjing Liu, Yilun Chen, Yaqin Zhang

202413 citationsDOI

Abstract

In autonomous driving, cooperative perception makes use of multi-view cameras from both vehicles and infrastructure, providing a global vantage point with rich semantic context of road conditions beyond a single vehicle viewpoint. Currently, two major challenges persist in vehicle-infrastructure cooperative 3D (VIC3D) object detection: 1) inherent pose errors when fusing multi-view images, caused by time asynchrony across cameras; 2) information loss in transmission process resulted from limited communication bandwidth. To address these issues, we propose a novel camera-based 3D detection framework for VIC3D task, Enhanced Multi-scale Image Feature Fusion (EMIFF). To fully exploit holistic perspectives from both vehicles and infrastructure, we propose Multi-scale Cross Attention (MCA) and Camera-aware Channel Masking (CCM) modules to enhance infrastructure and vehicle features at scale, spatial, and channel levels to correct the pose error introduced by camera asynchrony. We also introduce a Feature Compression (FC) module with channel and spatial compression blocks for transmission efficiency. Experiments show that EMIFF achieves SOTA on DAIR-V2X-C datasets, significantly outperforming previous early-fusion and late-fusion methods with comparable transmission costs.

Topics & Concepts

Computer scienceObject detectionComputer visionArtificial intelligenceScale (ratio)Image fusionFeature (linguistics)FusionObject (grammar)Image (mathematics)Sensor fusionFeature detection (computer vision)Pattern recognition (psychology)Image processingGeographyPhilosophyCartographyLinguisticsAdvanced Neural Network ApplicationsVehicle License Plate RecognitionInfrastructure Maintenance and Monitoring
EMIFF: Enhanced Multi-scale Image Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detection | Litcius