Ongeveer 22 uur geleden - NWO-institutenorganisatie - Utrecht
You will develop new concepts for computational imaging and metrology, to advance the capabilities of semiconductor metrology and enable accurate …
Postdoc position: Vision Deep Learning algorithms, embedded hardware and software architectures. We are looking for a talented Postdoc with a PhD degree in Computer Science, Electrical Engineering or related disciplines with excellent grades, and good ...
Postdoc position: Vision Deep Learning algorithms, embedded hardware and software architectures.
We are looking for a talented Postdoc with a PhD degree in Computer Science, Electrical Engineering or related disciplines with excellent grades, and good publications.
Especially since the introduction of deep learning (DL) techniques, the advances in video analytics are going in a rapid pace. Deep learning is based on neural networks comprising multiple layers of connected neurons that can be trained to classify input signals. In the domain of video analysis, this technique is used to detect, analyze, recognize, or classify objects. The deep neural network requires a tremendous amount of compute power and huge memory bandwith. To satisfy these requirements DL algorithms and architectures have to be developed which exploit parallel processing, in particular vector parallism, specific accelerators, and advanced memory interfaces and memory hierarchy.
Surveillance systems to control traffic on highways typically contain thousands of cameras to collect data and to control the traffic. To make the intelligent video analysis scalable, and to limit the bandwidth that is needed for video streaming, video analysis will be processed in- or close to the camera. Moreover, in many use cases, no wired power sources are available for cameras. Hence, there is a need for ultra-low power implementations that can operate on solar energy or other local energy resources. At the TU/e research is performed to efficiently map deep neural networks to various low energy consuming heterogeneous hardware and processing platforms, including GPUs, FPGAs and ASICs (parse.ele.tue.nl).
The postdoc will be involved in the advanced scientific research and teaching responsibilities of the Electronic Systems (ES) Group of Eindhoven University of Technology. The ES group consists of seven full professors, one associate professor, eight assistant professors, several postdocs, about 30 PDEng and PhD candidates and support staff. The ES group is world-renowned for its design automation and embedded systems research.
The research will be executed in close collaboration with industry and several internal and external PhD students who work within the ZERO program for Energy Autonomous Systems for Internet of Things. The research in the Electronic Systems Group is performed in cooperation with the company Vinotion (www.vinotion.nl). Their focus is on the development of energy-autonomous programmable processing platforms for smart road-side monitoring systems that combine information obtained by cameras and radars. These systems will observe traffic on the road, interpret complex scenes, and communicate its findings with other road users and responsible authorities. The postdoc will be in charge of developing these systems, including necessary tool support. The research is supervised by prof.dr. Henk Corporaal (TU/e), dr. Sander Stuijk (TU/e), and dr.ir. Egbert Jaspers (Vinotion).
The research will be carried out in the Electronic Systems Group of Eindhoven University of Technology and in the research lab of Vinotion, also in Eindhoven.
The ideal candidate is pro-active, highly motivated, and independent, and has proven experience with the design of embedded systems. The candidate has also affinity with giving lectures and has good written and oral communication skills in English. We are looking for candidates that match the following profile: