Short Biography

I studied computer science at the Technical University of Darmstadt and successfully graduated with a Master of Science in 2017. In addition to my university education, I gained practical experience in the field of advanced development of driver assistant systems during an internship at AUDI AG in 2015 and a subsequent employment as a working student until the end of my studies. Since 2017, I am working as a research scientist at the Institute of Photogrammetry und GeoInformation (IPI) at Leibniz University Hannover. I received a doctoral degree there with distinction in 2021 on the topic of Uncertainty Estimation for Dense Stereo Matching using Bayesian Deep Learning. Afterwards, I have started working as a PostDoc in the DFG Research Training Group i.c.sens and I am the Leader of the Image Sequence Analysis Group at IPI since February 2022.

Besides my research, I am particularly interested in politics. I have been a member of a democratic party for many years and I am actively involved at municipal level. I am also an enthusiastic sports shooter and a licensed trainer.

Research

Research Focus

  • 3D Reconstruction
  • Machine Learning / Deep Learning
  • Semantic Scene Understanding
  • Uncertainty Estimation
  • Tracking of Dynamic Objects

Projects

Integrity and Collaboration in Dynamic Sensor Networks (i.c.sens)
The Research Training Group 2159 "Integrity and Collaboration in Dynamic Sensor Networks" (i.c.sens) is a joint research and doctoral program at Leibniz University Hannover funded by the German Research Foundation (DFG). In the context of this research training group, nine PhD students and one PostDoc investigate the aspects of trustworthiness of automated and autonomous systems (integrity) and collaboration betwenn multiple such systems as well as their individual sensors. [Website]

MOBILISE – Mobility in Engineering and Science: Mobile Human
Within the framework of the joint master plan "MOBILISE - Mobility in Engineering and Science", two universities of Lower Saxony, Leibniz University Hannover and TU Braunschweig, cooperate in the field of "Digitization". The field "Mobile Human: Intelligent Mobility in the Balance of Autonomy, Linkage and Security" under the direction of Prof. Kurt Schneider brings together a group of junior researchers investigating seminal, previously unestablished topics of social relevance. A total of 13 professorships from five LUH faculties with their specific, complementary areas of focus are involved in the project. [Website]

Publications

2023:
Ali, R., Mehltretter, M., Heipke, C. (2023): Integrating Motion Priors for End-To-End Attention-based Multi-Object Tracking. ISPRS Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences.
El Amrani Abouelassad, S., Mehltretter, M., Rottensteiner, F. (2023): Vehicle Pose and Shape Estimation in UAV Imagery Using a CNN. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences.
Iqbal, W., Paffenholz, J., Mehltretter, M. (2023): Guiding Deep Learning with Expert Knowledge for Dense Stereo Matching. PFG – Journal of Photogrammetry, Remote Sensing and Geoinformation Science.
2022:
Mehltretter, M. (2022): Joint Estimation of Depth and its Uncertainty from Stereo Images Using Bayesian Deep Learning. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, V-2-2022, pp. 69-78. [More]
Trusheim, P., Mehltretter, M., Rottensteiner, F., Heipke, C. (2022): Cooperative Visual Localisation Considering Dynamic Objects. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, V-1-2022, pp. 169-177. [More]
Ali, R., Dorozynski, M., Stracke, J., Mehltretter, M. (2022): Deep Learning-based Tracking of Multiple Objects in the Context of Farm Animal Ethology. ISPRS Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, XLIII-B2-2022, pp. 509-516. [More]
2021:
Mehltretter, M., Heipke, C. (2021): Aleatoric Uncertainty Estimation for Dense Stereo Matching via CNN-based Cost Volume Analysis. ISPRS Journal of Photogrammetry and Remote Sensing, 171, pp. 63-75. [More]
Zhong, Z., Mehltretter, M. (2021): Mixed Probability Models for Aleatoric Uncertainty Estimation in the Context of Dense Stereo Matching. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, V-2-2021, pp. 17-26. [More]
Heinrich, K., Mehltretter, M. (2021): Learning Multi-Modal Features for Dense Matching-Based Confidence Estimation. ISPRS Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, XLIII-B2-2021, pp. 91-99. [More]
Mehltretter, M. (2021): Uncertainty Estimation for Dense Stereo Matching Using Bayesian Deep Learning. PhD thesis. [More]
2020:
Mehltretter, M. (2020): Uncertainty Estimation for End-To-End Learned Dense Stereo Matching via Probabilistic Deep Learning. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, V-2-2020, pp. 161-169. [More]
Höllmann, M., Mehltretter, M., Heipke, C. (2020): Geometry-Based Regularisation for Dense Image Matching via Uncertainty-Driven Depth Propagation. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, V-2-2020, pp. 151-159. [More]
2019:
Mehltretter, M., Heipke, C. (2019): CNN-based Cost Volume Analysis as Confidence Measure for Dense Matching. Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 2070-2079. [More]
2018:
Mehltretter, M., Heipke, C. (2018): Illumination Invariant Dense Image Matching based on Sparse Features. 38. Wissenschaftlich-Technische Jahrestagung der DGPF und PFGK18 Tagung, pp. 584-596. [More]
Behmann, N., Mehltretter, M., Kleinschmidt, S., Wagner, B., Heipke, C., Blume, H. (2018): GPU-enhanced Multimodal Dense Matching. IEEE Nordic Circuits and Systems Conference: NORCHIP and International Symposium of System-on-Chip. [More]
Mehltretter, M., Kleinschmidt, S., Wagner, B., Heipke, C. (2018): Multimodal Dense Stereo Matching. Proceedings of the German Conference on Pattern Recognition, pp. 407-421. [More]

Contact

I am always happy to receive questions and feedback!
Get in contact with me using one of the following services: