RC-AutoCalib: An End-to-End Radar-Camera Automatic Calibration Network

TL;DR

This paper introduces an innovative online radar-camera calibration network that effectively handles data sparsity and measurement uncertainty through dual-perspective features, selective fusion, and cross-attention mechanisms, outperforming existing methods.

Contribution

The paper presents the first online automatic calibration method for radar and camera systems, utilizing dual-perspective features and novel fusion and matching mechanisms for improved robustness.

Findings

Outperforms previous radar-camera calibration methods.

Establishes new benchmark on the nuScenes dataset.

Demonstrates robustness against data sparsity and height uncertainty.

Abstract

This paper presents a groundbreaking approach - the first online automatic geometric calibration method for radar and camera systems. Given the significant data sparsity and measurement uncertainty in radar height data, achieving automatic calibration during system operation has long been a challenge. To address the sparsity issue, we propose a Dual-Perspective representation that gathers features from both frontal and bird's-eye views. The frontal view contains rich but sensitive height information, whereas the bird's-eye view provides robust features against height uncertainty. We thereby propose a novel Selective Fusion Mechanism to identify and fuse reliable features from both perspectives, reducing the effect of height uncertainty. Moreover, for each view, we incorporate a Multi-Modal Cross-Attention Mechanism to explicitly find location correspondences through cross-modal matching. During the training phase, we also design a Noise-Resistant Matcher to provide better supervision and enhance the robustness of the matching mechanism against sparsity and height uncertainty. Our experimental results, tested on the nuScenes dataset, demonstrate that our method significantly outperforms previous radar-camera auto-calibration methods, as well as existing state-of-the-art LiDAR-camera calibration techniques, establishing a new benchmark for future research. The code is available at https://github.com/nycu-acm/RC-AutoCalib.