Dr. Donald Dansereau is a postdoctoral scholar at the Stanford
Computational Imaging Lab. His research is focused on computational
imaging for robotic vision, and he is the author of the Light Field
Toolbox for Matlab. In 2004, Dr. Dansereau received the Governor
General’s Gold Medal for his M.Sc. work on light field processing at
the University of Calgary. His industry experience includes physics
engines for video games, computer vision for microchip packaging, and
FPGA design for high-throughput automatic test equipment. In 2014 he
completed a Ph.D. in plenoptic imaging in the marine robotics group at
the Australian Centre for Field Robotics, University of Sydney, and in
2015 he joined on as a research fellow at the Australian Centre for
Robotic Vision in Brisbane. Dr. Dansereau's field work includes marine
archaeology on a Bronze Age city in Greece, seamount and hydrothermal
vent mapping in the Sea of Crete, habitat monitoring off the coast of
Tasmania, and hydrochemistry and wreck exploration in Lake Geneva.

AG 1, AG 2, AG 3, AG 4, AG 5, SWS, RG1, MMCI   Info

Expert Audience

English

60 Minutes

Saarbrücken

We are on the cusp of a robotics revolution that will dramatically
increase the variety of camera technologies deployed at large scales.
Manufacturing, health, and service robots including autonomous cars
and drones are set to transform how we live, and visual perception
will play a key role in this transformation. However, there are deep
challenges in how to best endow robotic autonomy with visual sensing.

This talk explores the tools of computational imaging as a means of
meeting the requirements of this next generation of visual perception.
As in nature specialized embodiments benefit from specialized sensing,
and I will explore how novel cameras can reduce computational burden
while delivering greater robustness. This approach makes for more
efficient robots and allows them to operate over a broader range of
conditions and with greater autonomy. The talk concludes by
highlighting key challenges at the intersection of optics, algorithms,
and robotic embodiment.

Piotr Didyk

--email hidden

passcode not visible

logged in users only