Master Assignment
[M] Object detection for water pipeline detection @ROSEN Enschede
Location: (Enschede)
Student: (Unassigned)
If you are interested please contact :
Introduction
The worldwide operating company ROSEN inspects several assets using self-developed techniques and devices. As part of ROSEN R&D, the sensor data gathered by inspecting tank bottoms with high resolution Magnetic Flux Leakage (MFL) technology are processed to recognize possible anomalies by the help of machine learning. For this field of expertise, we’re looking for a graduation student (Computer Science/Data Science) to further improve existing algorithms.
Situation
The ROSEN water pipeline inspection tool is used in several types of water pipelines and gathers data with the help of several sensor systems such as a camera, ultrasonic, hydrophonic and internally developed sensors. Inside the water pipelines, there can be images with several types of situations (for instance joints, valves, defects etc.) found which are different from the more normal images as found within the pipeline. Accurately selecting these specific objects and reporting them for further evaluation is one of the most important tasks for a better, consistent inspection method with less effort.
Project Target
This project is aiming to design an algorithmic object detection tool, which finds all unusual situations within a pipeline. A dynamic system is foreseen which responses also to changes in the main system; that means automatically redefining the ‘usual/unusual’ discrimination method from pipeline to pipeline or even in several sections of one single pipeline. The main considered approach here is to use video processing so using the camera; but if needed we can also benefit from the other sensors as well. More specifically, the recommended topics to be covered are as below:
- Designing a model to detect/segment objects seen by the camera in the pipeline
- Investigating the usability and if helpful actually using of other different sensors which are helpful for detection
- Classification of the found objects having known patterns
Requirements
Are you a student who is interested to bring technical creativity into a practical challenge? Then, to do this project in the innovative company ROSEN, you should bring with you:
- Background of image processing, computer vision and machine learning
- Good Python programming skills
- Pro-active and team-oriented attitude
Our Offer
We offer various career development opportunities of an international, innovative and sustainability-oriented company. In an open corporate culture with rapid decision-making, you can implement your ideas successfully. Moreover, you can expect enthusiastic support by experienced engineers and scientist, working in a dedicated team with a ‘can-do’ mentality.
We attach great importance to a balance between work and family life. Moreover, flexible working hours and different working time models are standard for ROSEN.