About an Automating Annotation Method for Robot Markers

TL;DR

This paper introduces an automated annotation method leveraging ArUco marker detection to train deep learning models for robot marker recognition, significantly reducing manual effort and improving robustness under challenging imaging conditions.

Contribution

The paper presents a novel automated annotation approach using ArUco markers to facilitate deep learning training, eliminating manual labeling and enhancing recognition accuracy in noisy environments.

Findings

Automated annotation reduces human labeling effort.

Deep learning models trained with this method outperform traditional techniques.

Recognition robustness improves under noise, blur, and defocus conditions.

Abstract

Factory automation has become increasingly important due to labor shortages, leading to the introduction of autonomous mobile robots for tasks such as material transportation. Markers are commonly used for robot self-localization and object identification. In the RoboCup Logistics League (RCLL), ArUco markers are employed both for robot localization and for identifying processing modules. Conventional recognition relies on OpenCV-based image processing, which detects black-and-white marker patterns. However, these methods often fail under noise, motion blur, defocus, or varying illumination conditions. Deep-learning-based recognition offers improved robustness under such conditions, but requires large amounts of annotated data. Annotation must typically be done manually, as the type and position of objects cannot be detected automatically, making dataset preparation a major bottleneck. In contrast, ArUco markers include built-in recognition modules that provide both ID and positional information, enabling automatic annotation. This paper proposes an automated annotation method for training deep-learning models on ArUco marker images. By leveraging marker detection results obtained from the ArUco module, the proposed approach eliminates the need for manual labeling. A YOLO-based model is trained using the automatically annotated dataset, and its performance is evaluated under various conditions. Experimental results demonstrate that the proposed method improves recognition performance compared with conventional image-processing techniques, particularly for images affected by blur or defocus. Automatic annotation also reduces human effort and ensures consistent labeling quality. Future work will investigate the relationship between confidence thresholds and recognition performance.