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

arXiv:2402.15272v1 Announce Type: new
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 …

3d object 3d object detection abstract arxiv autonomous autonomous driving beyond cameras challenges context cs.ai cs.cv detection driving feature fusion global image infrastructure major perception scale semantic type vantage vehicles view