Framework and Multi-modal Dataset for Roadwork Zone Detection and Geo-localization

2026-07-05

AI Summary

High-definition maps often fail to promptly update semi-static information such as road construction zones, adversely affecting the perception and localization capabilities of autonomous driving systems. To address this challenge, this work introduces RZDG, the first public multimodal dataset dedicated to road construction zone detection and geolocation, and proposes an end-to-end pipeline that integrates semantic segmentation, 3D object detection, and multi-object tracking. By extending the AB3DMOT framework, the method achieves high-precision transformation from local coordinates to global geographic coordinates. Experimental results demonstrate that the approach attains F1-scores of 0.597 and 0.665 on real-world and synthetic data, respectively, with geolocation errors consistently maintained below one meter, thereby validating its effectiveness and practicality.

Abstract

Autonomous vehicles often rely on high-definition (HD) maps for navigation; however, these maps are not frequently updated and often lack semi-static information, such as temporary roadwork zones, which can significantly alter the road network. This limitation underscores the urgent need for an accurate global position of roadwork zones. However, the absence of publicly available datasets for evaluating roadwork zone detection and geo-localization models has hindered the development of reliable autonomous driving systems. To address this challenge, we propose the Roadwork Zone Detection and Geo-localization (RZDG) dataset, which includes both simulated and real-world data, providing multimodal sensor inputs along with comprehensive annotations. The dataset supports multiple perception tasks, including image semantic segmentation, 3D object detection, and object geo-localization. In addition, we introduce a tracker-based roadwork zone detection and geo-localization (RZDG) pipeline, an extension of AB3DMOT, for accurate object geo-localization in roadwork zones. We benchmark our approach on the RZDG dataset, demonstrating its effectiveness in detecting roadwork zones and transforming object positions from the local coordinate system to the global coordinate system. A prediction is considered a true positive (TP) if its estimated position falls within one meter of the ground truth. Our experimental results show that our approach achieves high accuracy on both real and simulated data. Specifically, we report: Precision: 0.565 (real) / 0.615 (simulated) Recall: 0.898 (real) / 0.809 (simulated) F1-score: 0.597 (real) / 0.665 (simulated).

Problem

• roadwork zone
• geo-localization
• autonomous driving
• HD maps
• dataset

Innovation

• roadwork zone detection
• geo-localization
• multi-modal dataset
• AB3DMOT extension
• autonomous driving