Manuel Martinez

Since I was a child, Robots have always been a passionate source of inspiration for me, and I thrive for the day when sharing the streets with androids is as mainstream as computers are now. I hope that day will arrive soon, and my plan is to help it happen as soon as possible.

One of the biggest unsolved challenges Robots must face when dealing with humans is perceiving the world as it is.

Humans, like most animals, deal with world perception by getting an overwhelming amount of information from our eyes and ears and matching it to a huge database of objects and known patterns, and then applying a physics model to it to check if the representation we got in our heads is trustworthy. And we do it extremely fast.

So unless a new breakthrough technology appears, we won't be able to replicate the human perception model in Robots. Therefore my main goal is to develop new perception algorithms that allow Robots to better interact with humans.

VIPSAFE Automated Visual Monitoring for Improving Patient SAFEty

VIPSAFE is a project fruit of a collaboration between two research centers, Karlsruhe Institute of Technology and Sabanci University, and two companies, Videmo GmbH and Vistek ISRA, with the main goal of improving patients’ safety by the means of automated visual monitoring.

Population ageing is taking place in every country and region across the globe due to the rising life expectancy and the declining of birth rates. At the same time, the nations are facing an explosion of costs in the health-care sector as threating elderly people is 3 to 5 times more expensive than for those under 65. The dramatic increase of the elderly population along with the explosion of costs poses extreme challenges to society.

Thus under VIPSAFE we develop novel techniques for automated visual monitoring of patients and elder people living in nursing homes or in their (assisted) home environments. We are developing vision-based sensors to determine if someone has fallen, if someone has not arisen from bed, whether a patient in the intensive care unit is showing unusual behavior or whether a patient is about to hurt himself by removing life-keeping devices or cables from his body.

Such automated techniques to detect critical and possibly life-threatening situations can then be used to automatically alert clinical personnel or care providers. This systems will thus have a direct impact in improving patient safety in hospitals and nursing homes.

CVHCI Praktikum

CVHCI Programming Project

The MOPED framework: Object recognition and pose estimation for manipulation

MOPED: A Scalable and Low Latency Object Recognition and Pose Estimation System