ARC-D2: AI for Automatic Highway Condition Detection

AI
Machine Learning
Infrastructure
Development of an AI-based application for automated detection of inventory and condition data in highway environments to support early maintenance measures through anomaly detection and object detection based on video data.
Author

Palaimon

Published

December 22, 2022

ARC-D2

Development of an AI-based Application for Automatic Detection of Inventory and Condition Data in Highway Environments – ARC-D2

ARC-D2 Environmental detection using AI on video data of a highway
Source: Palaimon GmbH

Problem Statement

Federal highways and highway-like roads are a crucial economic factor for Germany. To ensure the road network of over 13,000 km withstands daily demands, it must be regularly maintained and modernized. Currently, there is no automated, video-based detection of inventory and condition data in this road environment. An up-to-date database and automated assessment of the quality of individual road sections are important to initiate timely maintenance measures and prevent costly long-term damage.

Project Goal

The project’s goal is to develop an AI-based application for the automatic damage detection in inventory and condition data in the road environment that can easily be integrated into existing standard systems. The project partners, Palaimon GmbH and the University of Kiel (AG Intelligent Systems, Prof. Tomforde), are developing AI for road condition comparison (anomaly detection) and object detection based on video data.

Implementation

Together with the associated partners – the Federal Highway Research Institute (BASt), the Ministry of Transport of North Rhine-Westphalia, the Ministry for Infrastructure and Digitalization of Saxony-Anhalt, and the Saxon State Ministry for Economic Affairs, Labor, and Transport – the requirements for condition monitoring and the necessary data for developing the AI models are defined. Subsequently, various machine learning models are trained, and the algorithms are extended according to the specific problem.

Project Details

  • Consortium Coordinator: Palaimon GmbH, Berlin
  • Funding Code: 19F2236A
  • Project Volume: €839,076.18 (78.57% subsidized by BMDV)
  • Project Duration: 12/2022 – 11/2025

Project Partners

  • Palaimon GmbH, Berlin
  • Christian-Albrechts-University of Kiel, Kiel

Associated Partners

  • Federal Highway Research Institute (BASt)
  • Ministry of Transport of North Rhine-Westphalia
  • Ministry for Infrastructure and Digitalization of Saxony-Anhalt
  • Saxon State Ministry for Economic Affairs, Labor, and Transport