Robotics Graduate Student Seminars
Bio-Inspired Vision Systems for Real-World Robotics
Francisco Barranco, PhD
Postdoctoral Research Associate, Computer Science
Advisors: Prof. Yiannis Aloimonos and Dr. Cornelia Fermüller
The visual information that we receive is not limited so that we are only passive observers, but active agents in our environment. In the real world, active robots continuously need to interact with a dynamic environment. In such case, it is required to close perception-action loops in real time. In the case of vision, shortening the latency of vision processing is one of the most important issues that robotic systems need to overcome. There, it is a potential niche for a new generation of bio-inspired active vision devices that work at very high frequencies generating sparse information. These sensors work at maximum temporal frequencies of a few microseconds and still have high-dynamic range. This last property is very important for real-world applications since it reduces artifacts due to changes in the illumination. In our case, we will present the advantages of using DVS (Dynamic Vision Sensor) and DAVIS (Dynamic and Active Pixel Vision Sensor). We will also present some results of our latest work on event-driven motion estimation and border detection and proto-segmentation based only on events.
About the Robotics Graduate Student Seminars
The Robotics Graduate Student Seminars at the University of Maryland College Park are a student-run series of talks given by current graduate students.
The purpose of these talks is to:
- Encourage interaction between Robotics students from different subfields;
- Provide an opportunity for Robotics students to be aware of and possibly get involved in the research their peers are conducting;
- Provide an opportunity for Robotics students to receive feedback on their current research;
- Provide speaking opportunities for Robotics students.