Wissenschaftliche/r Mitarbeiter/in im Bereich "Muster- und Schädenerkennung von Straßenunterbauten mittels Maschinelles Lernen" (m/w/d)

About us

The chair of Prof. Bajcinca focuses on research of modern methods and advanced applications of control and system theory, involving three main pillars: cyber-physical systems, complex dynamical systems and machine learning. Through networking with a large number of national and international research, academic and industrial partners, funding projects with exotic and highly interesting tasks regarding model-based and data-driven control have been acquired on a regular basis. The research work is supported with an excellent laboratory equipment and high-performance computation in the areas of autonomous systems, robotics and energy systems, which is continuously being further developed.

https://www.mv.uni-kl.de/mec/home.

 

Research Scope

Road health monitoring has been an important topic for municipalities for a long time. It is a challenge for them to figure out a right time for repairs, because most of the damages start from the underground road surfaces that we cannot find out without specialised sensors like Ground Penetrating Radars and suitable algorithms to process the collected data. If not detected on time, these damages aggravate over time and lead to severe damages therefore increasing the maintenance costs. The goal of this project is to develop machine learning algorithms to analyse the GPR radargrams to detect sub-surface damages with a high accuracy. Our mission is to advance the state-of-the-art in computer vision algorithms for GPR radargrams. Also, our work is critical to delivering such algorithms to the municipalities for improving the current road health monitoring systems. The research topics of interest include, but are not limited to, convolutional neural networks (CNNs), generative methods (GANs), semantic understanding (such as object detection), multi task learning, etc.

 

Research Task / Work Description

You will work on innovative projects in the area of machine learning and computer vision. The project goal is to develop an automated system to detect sub-surface damages in ground penetrating radar images using pattern recognition techniques. As part of the programme, you will be working on deep learning methods for object detection and classification. 

Your area of ​​responsibility includes:

  • Review the literature in the field of object detection, road damage detection, etc.
  • Collect and pre-process the ground penetrating radar images and prepare the datasets
  • Design neural network architectures (CNNs, RNNs) to learn signature patterns present in GPR radargrams that correspond to damages
  • Train and evaluate deep/machine learning models to detect subsurface damages
  • Use GPU and CUDA capabilities for the training purposes. Our chair possesses high computational resources from NVIDIA including 4 x Nvidia A100s and 4 x Nvidia V100s (DGX Station)
  • Evaluate the developed model and publish the results
  • Integrate the developed model in our test vehicle
  • Develop an automated pipeline for detecting subsurface damages on all roads of the city of Kaiserslautern and store results in a centralised database

 

Qualification Requirements

  • Above-average university degree in computer science or mathematics
  • Proven research experience in the field of computer vision
  • Practical experience with neural network design, deep learning libraries e.g. Pytorch, Tensorflow
  • Excellent programming skills in Python or C++
  • Organisational and collaborative skills with scientific and industrial partners from different disciplines.
  • Proficiency in English is essential. Knowing German is an advantage.

 

We offer

  • Payment according to TV-L E13 with an initial one-year time limit
  • The possibility to do a PhD and to teach is given in case of scientific aptitude
  • TUK strongly encourages qualified female academics to apply
  • Severely disabled persons will be given preference in the case of appropriate suitability (please enclose proof)
  • Electronic application is preferred. Please attach only one coherent PDF.

You can expect an interesting, diversified and responsible task within a young, highly motivated and interdisciplinary team of a growing chair with great personal creativity freedom.

Contact

Prof. Dr.-Ing. Naim Bajcinca
Phone: +49 (0)631/205-3230
Mobile: +49 (0)172/614-8209
Fax:  +49 (0)631/205-4201
Email: mec-apps(at)mv.uni-kl.de

 

Keywords

Damage Detection
Computer Vision
Image Processing
Deep Learning
Convolutional Neural Networks

 

Application Papers

Cover Letter
CV
University Certificates
References
List of Publications

 

Application Deadline

31. Oktober 2023

 

Job Availability

Immediate