Automatic Image Annotation for Mapped Features Detection

TL;DR

This paper presents a multi-modal automatic annotation approach combining vector maps, lidar, and image segmentation to improve pole detection in road environments, reducing manual effort and enhancing perception models for autonomous driving.

Contribution

It introduces a novel fusion of three automatic annotation methods and demonstrates their effectiveness in improving pole detection accuracy and model training.

Findings

Multi-modal annotation fusion improves pole detection accuracy.

Enhanced annotations lead to better perception model training.

The approach reduces manual annotation efforts significantly.

Abstract

Detecting road features is a key enabler for autonomous driving and localization. For instance, a reliable detection of poles which are widespread in road environments can improve localization. Modern deep learning-based perception systems need a significant amount of annotated data. Automatic annotation avoids time-consuming and costly manual annotation. Because automatic methods are prone to errors, managing annotation uncertainty is crucial to ensure a proper learning process. Fusing multiple annotation sources on the same dataset can be an efficient way to reduce the errors. This not only improves the quality of annotations, but also improves the learning of perception models. In this paper, we consider the fusion of three automatic annotation methods in images: feature projection from a high accuracy vector map combined with a lidar, image segmentation and lidar segmentation. Our experimental results demonstrate the significant benefits of multi-modal automatic annotation for pole detection through a comparative evaluation on manually annotated images. Finally, the resulting multi-modal fusion is used to fine-tune an object detection model for pole base detection using unlabeled data, showing overall improvements achieved by enhancing network specialization. The dataset is publicly available.