# A Fiducial-Marker-Based Localization Method for Automotive Chassis Bolt Assembly

## TL;DR

This paper introduces a method using fiducial markers to accurately locate bolts during automotive assembly, improving reliability in challenging industrial conditions.

## Contribution

A novel localization method using a concentric ring marker and optimized ellipse fitting for automotive bolt assembly.

## Key findings

- The improved Retinex-based algorithm enhances ROI extraction under uneven lighting.
- Optimized ellipse fitting increases accuracy and reliability of bolt localization.
- The method achieves high precision, meeting industrial automatic assembly requirements.

## Abstract

To address the difficulty of accurately localizing automotive chassis bolts during the assembly process—caused by non-uniform illumination, limited camera installation space, and occlusions from the vehicle body structure—a fiducial-marker-based localization method is proposed. In this method, a concentric ring-shaped fiducial marker is affixed to the bottom of the assembly wrench, and its region of interest (ROI) is extracted using an HSV color space segmentation algorithm. To overcome interference from uneven lighting and insufficient brightness in industrial environments, an improved Retinex-based image enhancement algorithm is introduced, which significantly improves the robustness and accuracy of ROI extraction. The extracted ROI image is subjected to ellipse fitting, and the fitting process is optimized by incorporating the Leitz criterion. Experimental results show that the optimized ellipse fitting algorithm achieves higher accuracy and significantly enhances the reliability of fitting. Since perspective projection of spatial circles leads to displacement of the circle center, the actual projected center of the fiducial marker in the image is calculated by estimating the normal vector of the circular plane using vanishing lines and the ellipse parameter matrix. This enables spatial localization of the bolt end. The proposed method is validated by comparing the localization results with the theoretical coordinates of the bolt holes. Experimental results demonstrate that the method offers high localization accuracy and strong robustness, meeting the practical precision requirements for automatic bolt assembly in industrial applications.