PhD Position in sensor fusion for object detection and scene analysis

Ghent University – imec Image Processing and Interpretation Group (IPI)

The Image Processing Group at Ghent University-imec (http://ipi.ugent.be) consists of +/- 40 experienced researchers, post-docs and professors. IPI conducts research in a wide array of both fundamental and applied image processing topics. Application domains of this research include intelligent & autonomous vehicles, surveillance and sensor networks, industrial automation, remote sensing, medical image analysis, video analysis and scene reconstruction.
 
Ghent University (www.ugent.be/en) consistently ranks among the best 100 universities in the world, including, 69th by the Academic Ranking of World Universities (or Shanghai ranking) and 88th by U.S. News & World Report. The IPI Lab is location on the university’s UFO campus in the center of Ghent, Belgium, a city recently rated as one of the best places to visit in Europe for culture (https://www.lonelyplanet.com/articles/ghent-belgiums-best-kept-secret).

What you will do

Imec IPI is looking for a qualified and motivated PhD student to work on sensor fusion for object detection and scene analysis. As a PhD student with IPI, you will be located at the TELIN offices at Campus UFO in Ghent.  You will be offered an initial contract of 12 months, to be extended up a period of 4 years in total with the aim of obtaining a PhD. The research will be partly fundamental (furthering the state of the art) and partly applied. You will collaborate with international industrial partners while embedded in a university research team that is internationally recognized for its extensive expertise regarding sensor fusion for autonomous driving, traffic monitoring and industrial safety.  

Topic 

Many smart mobility and industrial automation applications rely on object detection and tracking. Examples include autonomous vehicles, smart traffic infrastructure, mobile robots, security & surveillance. Sensor fusion is essential for safety-critical systems, both to ensure robustness (through considering redundant information) and accuracy (through considering complementary information). Typical approaches in literature for both single sensor and multi-modal detection focus on achieving maximum accuracy, averaged over large and relatively easy datasets. Furthermore, the detection and tracking aspects are generally decoupled because processing time series of inputs in a similar manner requires models of immense complexity; instead the tracking is limited to semantic objects. These standard approaches fall short for truly difficult tasks like detection of objects in extremely low visibility conditions or at great distances. To tackle those challenges, the time dimension should be modelled explicitly: effective features that would allow reliable detection and tracking are to be found in statistical variations of the input signals over time. 

In this research, we will research deep learning methods that combine the spatial feature extraction methods of traditional CNNs with novel descriptors operating over variable time windows. These concepts will be applied to and validated using multiple configurations of sensors including thermal and RGB cameras, lidar and radar. You will have the opportunity to work with international academic and industrial partners on use cases that include detection of hazards and wildlife at sea (which is often partially or entirely submerged) and autonomous vehicle perception under difficult circumstances. 

What we do for you

At IPI, we offer you the opportunity to conduct research in a highly international and friendly working environment. We provide ample opportunity for researchers to take initiative in their work and to develop their professional networks. 

The salary is competitive and will be determined by the university salary scales. Staff members can count on a number of benefits, such as a broad range of training and educational opportunities, 36 days of vacation leave (on an annual basis for a full-time position), bicycle allowance, and more. 

Who you are

• You hold a Master of Science degree in computer science, electrical engineering or equivalent. You possess strong knowledge of mathematics, probability theory, image processing, machine learning, and computer vision and are well versed in Python and/or C++. You have experience with original algorithm design that goes beyond the mere application of methods from literature.
• You combine a strong interest in engineering and scientific research with a desire to see your work applied (in industrial, academic or (N)GO collaboration). You are able to learn quickly and independently. You aspire to become an expert in your field, while simultaneously collaborating with other researchers and senior staff to efficiently generate state-of-the-art results.
• You are fluent in written and oral English and able to communicate your original ideas and results clearly and concisely.

Interested?

Please submit your application by email to Prof. Wilfried Philips at Wilfried.philips@ugent.be and Dr. David Van Hamme at david.vanhamme@ugent.be.

In your email, please include the following:

• A cover letter with a brief motivation of your application: what do you consider the best aspects of your CV that demonstrate your academic excellence during your university education? What are your reasons for pursuing a PhD? Why would you like to work at UGent?
• A detailed CV, describing your earlier experience and studies;
• A list of publications (if available);
• A transcript of your educational record (list of courses per year, number of obtained credits, obtained marks) if available. This need not be official documentation at this stage;
• If available: 1-3 English language documents describing your earlier research or technical work (e.g., scientific papers, master thesis, report on project work, etc.). These documents need not be on the topic of the advertised position.

Applications remain welcome until the position is filled.