Roadside Monocular 3D Detection via 2D Detection Prompting

arXiv:2404.01064v1 Announce Type: new
Abstract: The problem of roadside monocular 3D detection requires detecting objects of interested classes in a 2D RGB frame and predicting their 3D information such as locations in bird's-eye-view (BEV). It has broad applications in traffic control, vehicle-vehicle communication, and vehicle-infrastructure cooperative perception. To approach this problem, we present a novel and simple method by prompting the 3D detector using 2D detections. Our method builds on a key insight that, compared with 3D detectors, a 2D …

abstract applications arxiv bird communication control cs.cv detection information infrastructure locations objects perception prompting traffic type via view