Image based road condition estimation

Municipalities and Cities face many challenges with infrastructure management. Various assets like traffic signs and the road network need to be maintained.

With the accessibility of mobil cameras like smartphones and modern computer vision algorithms it is now possible to gather and evaluate large amounts of images.

This project focuses on evaluating the road condition based on smartphone images and making this information accessible in a web system. The next steps focus on summarizing the gathered information for a given time interval. Additionally we are aiming to detect, analyze and predict changes in the future condition of the road network.

Publications


2024
Adaptable Accelerometer Signal Processing Pipelines for Smartphone based Evenness Estimation
Münke, F. R.; Schenk, M.; Murr, S.; Reischl, M.
2024. Journal of Signal Processing Systems, 96 (10), 617–626. doi:10.1007/s11265-024-01939-2
A Review of Adaptable Conventional Image Processing Pipelines and Deep Learning on limited Datasets
Münke, F. R.; Schützke, J.; Berens, F.; Reischl, M.
2024. Machine vision and applications, 35, Article no: 25. doi:10.1007/s00138-023-01501-3
Accelerating Materials Discovery: Automated Identification of Prospects from X‐Ray Diffraction Data in Fast Screening Experiments
Schuetzke, J.; Schweidler, S.; Muenke, F. R.; Orth, A.; Khandelwal, A. D.; Breitung, B.; Aghassi-Hagmann, J.; Reischl, M.
2024. Advanced Intelligent Systems, 6 (3), Art.-Nr.: 2300501. doi:10.1002/aisy.202300501
2023
A Lightweight Framework for Semantic Segmentation of Biomedical Images
Münke, F. R.; Rettenberger, L.; Popova, A.; Reischl, M.
2023. Current Directions in Biomedical Engineering, 9 (1), 190–193. doi:10.1515/cdbme-2023-1048
Mask R-CNN Outperforms U-Net in Instance Segmentation for Overlapping Cells
Rettenberger, L.; Münke, F. R.; Bruch, R.; Reischl, M.
2023. Current Directions in Biomedical Engineering, 9 (1), 335–338. doi:10.1515/cdbme-2023-1084
2022
Automated Annotator Variability Inspection for Biomedical Image Segmentation
Schilling, M. P.; Scherr, T.; Munke, F. R.; Neumann, O.; Schutera, M.; Mikut, R.; Reischl, M.
2022. IEEE access, 10, 2753–2765. doi:10.1109/ACCESS.2022.3140378
2021
Label Assistant: A Workflow for Assisted Data Annotation in Image Segmentation Tasks
Schilling, M. P.; Rettenberger, L.; Münke, F.; Cui, H.; Popova, A. A.; Levkin, P. A.; Mikut, R.; Reischl, M.
2021, November 26. 31. Workshop Computational Intelligence (2021), Berlin, Germany, November 25–26, 2021
Evaluierung von Merkmalen zur Abbildung von Veränderungen in ungeordneten Bilddaten = Evaluating features to represent changes in unstructured image data
Münke, F. R.; Schilling, M. P.; Mikut, R.; Reischl, M.
2021. Automatisierungstechnik, 69 (10), 892–902. doi:10.1515/auto-2021-0038
Label Assistant: A Workflow for Assisted Data Annotation in Image Segmentation Tasks
Schilling, M. P.; Rettenberger, L.; Münke, F.; Cui, H.; Popova, A. A.; Levkin, P. A.; Mikut, R.; Reischl, M.
2021. Proceedings - 31. Workshop Computational Intelligence : Berlin, 25. - 26. November 2021. Hrsg.: H. Schulte; F. Hoffmann; R. Mikut, 211–234, KIT Scientific Publishing
2019
Evaluation of Features for Change Detection in Unstructured Image Data
Münke, F. R.; Bartschat, A.; Chen, Y.; Mikut, R.; Reischl, M.
2019. Proceedings - 29. Workshop Computational Intelligence, Dortmund, 28. - 29. November 2019. Ed.: F. Hoffmann, E. Hüllermeier, R. Mikut, 1–23, KIT Scientific Publishing
Completed Project