Computer vision for anomaly detection and damage detection

Using image-based methods, a deep learning pipeline for damage detection was developed between April 2020 and December 2020.


  • It should be possible to carry out the steps of the inspection at the ICE4 using AI procedures in order to enable the automation of the inspection.

  • The approaches developed should be so universal that they can be transferred to other series with less effort


  • Object recognition for all components to be found

  • Anomaly detection for all operations performed

  • Graphical tools for testing and evaluating the generated models

  • Tensorflow-based machine learning environment for computer vision use cases (other technologies: MLFlow, CVAT, S3, MSSQL)


  • In-depth understanding of the structure of the ICE4 and the work steps to be carried out

  • Modular and flexibly adaptable to other/new work steps toolbox for camera exploration allows porting our solution to other train types and other use cases

  • Even the intermediate results of the anomaly detection can support factory employees in their findings

Are you interested in your own use cases?


An automotive company would like to visualise various market-specific data in order to create a Competitive analysis for the US market.


There will be a interactive and Flexible application, including of different maps with two different views implemented.


Relevant markets are identifies, analyses and visualises. The dealer or the respective sales department have the possibility to compare the direct competition with their own product and to visualise the relevant data.