At S[&]T we are specialized in R&D solutions for space, science, and defence. Orbital Eye is a high-tech start-up founded by S[&]T Group (stcorp.nl) and housed at the ground floor of the S&T offices in Delft, the Netherlands. Its core product, PIMSyS, is a complete solution for reliable and cost-effective pipeline monitoring. It combines accurate and up-to-date monitoring data, acquired by synthetic aperture radar (SAR) and high-resolution optical satellites, with smart tools for planned third-party activities and inspection planning.
We are currently looking for an Intern located in Delft to join Orbital Eye for at least 5 months.
PIMSyS is based on Synthetic Aperture Radar Coherent Change Detection (SAR-CCD) technology. It enables us to detect activities in the vicinity of the assets being monitored, independent of cloud cover and daylight at virtually any location on Earth. For this, SAR-CCD uses satellite images taken at different times to map locations where things have changed.
A crucial step in maximizing the value for our customers, is to further process the SAR-CCD change maps in order to extract all relevant changes, while minimizing the number of false positives (agricultural activities, parking/loading areas, etc.). This is a challenging goal, since there exists a delicate balance between reducing false positives and not introducing false negatives (relevant changes not being detected). Therefore, the further enhancement of our systems performance with respect to these false positives and negatives, is and will remain an ongoing R&D topic for Orbital Eye.
- Currently studying Data/Computer Science, Applied Physics, Aerospace Engineering, Electrical Engineering (or similar);
- R&D enthusiast with a broad range of interests and interdisciplinary skills;
- Advantage to have experience in some of the following disciplines: data analysis, programming (Python, Matlab), filter design (both frequency and spatial domain), image processing, system design, earth observation/satellite imagery processing and/or radar processing;
- Eager to obtain some true R&D experience;
- EU citizen, or in possession of a valid EU student/working permit;
- Available for at least 5 months, full-time.
Brief description of some possible internship topics currently available:
- Detection and filtering improvements
You will work on improvements of the PIMSyS change detection and filtering algorithms to enhance detection of relevant changes/events and reduce the number of irrelevant activities detected/reported by the system (false alarm reduction). This work will mostly involve prototyping and development in Matlab and will be executed together with the OE-R&D team.
- Integration and validation of new SAR data sources
Currently the PIMSyS system supports and is validated for use of SAR data coming from the Sentinel-1, RadarSat-2 and Terrasar-X satellite constellations. This topic deals with the embarking of new upcoming SAR sources like ICE-EYE, Capella Space and data acquired by pseudo-satellites (high altitude UAV’s). It will require the use and validation of new versions of open source tools like the ESA s1tbx-toolbox. Will require to work with both Python and Matlab. Also we can look at possible new applications that these additional sensors enable.
- Exploit other data-types via fusion techniques
This topic is related to topic one, but instead focusses completely on using additional types of data to improve detection and filtering. Here we can think of the use of Sentinel-2 data to be fused with the Sentinel-1 detections to differentiate between events types via color changes. Also more advanced fusion techniques like deep learning can be considered.
- Validation campaign & AI
Crucial to the advancement of our detection and filtering capabilities, as well as our plans in the direction of AI, is the availability of high-quality ground truth. One way of collecting ground truth is via the pilot projects we run with our customers in which they classify the detections we report. However, the best ground truth data still comes from ground truth collection campaigns done by ourselves. These can consist of actively following up detections done by our monitoring system in the Delft surroundings as well as mining high resolution optical images together with well-chosen matching SAR data processing jobs. The internship assignment would then consist of collecting this ground truth and applying it in AI together with the team to improve the PIMSyS performance.
- Computational efficiency and infrastructure advancements (focus on software engineering)
This involves developments to improve the computational efficiency and thus runtime of the PIMSyS analysis. Reducing computation time allows quicker delivery of alerts to our customers which is of great value to them. This can be achieved by improving our software efficiency as well as by migrating our system onto an auto-scaling infrastructure. In addition, improving the overview and maintainability of the system when multiple customers are serviced at once is a topic at which improvements can be worked on. This internship will give you the opportunity to gain experience with the latest technologies in large scale cloud computing.
Would you like to hear more? Send your CV and motivational letter to firstname.lastname@example.org, or apply directly through our website!
Please note that if you are not an EU citizen, or in possession of a valid EU student/working permit, then we cannot accommodate your internship.