Li, Chengmin (Tongji university), Wang, Junhua (Tongji University), Fu, Ting (Tongji university), Yao, Bo (Tongji University)

A Novel Adaptive Calibration Method for Distributed Roadside Millimeter-Wave Radar Pairs

Scheduled for presentation during the Poster Session "Transportation Data Analysis and Calibration" (FrAT17), Friday, September 27, 2024, 10:30−12:30, Foyer

2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), September 24- 27, 2024, Edmonton, Canada

This information is tentative and subject to change. Compiled on December 26, 2024

Abstract

A large number of roadside Millimeter-Wave Radars (MMRs) serve Intelligent Transportation Systems (ITS), where adaptive calibration is a crucial foundation for long-term roadside ITS services. In distributed radar pairs, overlapping regions between two radars complement each other's information, thereby rapidly expanding coverage. We propose a novel adaptive distributed radar pair calibration method, which considers the similarity between trajectory and road geometry, and vehicle motion consistency, employing a stepwise calibration approach in a simplified transformation model. The mean of residuals standard deviation (MRSD) metric is applied to assess the calibration effectiveness in both lateral and longitudinal directions. The results demonstrate that our proposed algorithm not only achieves high accuracy but also exhibits relatively efficient convergence speed, and we elucidate the mechanism of each module in the final ablation experiment. The dataset in this paper is available online at: https://github.com/tuqing123/radarpairs-calibration-data-sh are