Abstract

High-definition angular marking maps (HDAM maps) are vital in large-scale environments with variable appearances. In these scenarios, unmanned ground vehicles (UGVs) can use angular markings for localization because they are easy to identify and informative for localization. However, creating such a marking map relies heavily on manual measurement and annotation, which is time-consuming and laborious. Although Inverse Perspective Mapping (IPM) offers a low-cost and automated alternative, its accuracy is compromised by vehicle motion and the arduous pre-calibration of the IPM matrix. To fill these gaps, we propose a pose-guided optimization framework for IPM. This framework enables the automated generation of HDAM maps, while concurrently refining the preliminary IPM matrix. We deployed the proposed method in two different automated ports, and the method yielded HDAM maps with near-centimeter precision. Moreover, the refined IPM matrix matched the accuracy of manual calibrations. The supplementary materials and videos are available at http://liuhongji.site/PGO-IPM/.

System Architecture

Main Video

Supplemental Videos

The original videos of the main video (using only front monocular camera). The left video is the original version of uncalibrated IPM. The right video is the original version of optimized IPM.

Use front and rear monocular cameras together. The left video shows the optimization mapping process. The right video is the comparison between uncalibrated IPM and optimized IPM.

The original videos of using front and rear monocular cameras together. The left video is the original version of uncalibrated IPM. The right video is the original version of optimized IPM.

Early demo videos. The left video is visualizing the whole map according to the location of the vehicle. The right video is the process of generating markings map automatically.

Overview of the Algorithm