NEW  Introduction to Event Detection Camera
Instructor: Keigo Hirakawa, University of Dayton
Level: Intermediate
Duration: 2 Hours plus 15-minute break and 30-minute post-class discussion
Course Time:
    New York: Wednesday 13 January, 18:30 – 20:45
    Paris: Thursday 14 January, 00:30 – 02:45
    Tokyo: Thursday 14 January, 08:30 – 10:45

Prerequisites: Working knowledge of image processing in general.

Benefits
This course enables the attendee to:

• Understand the key benefits and characteristics of event detection cameras.
• Be able to interpret the event data and import event data into Matlab and C++.
• Have a working knowledge of how event detection sensor data is processed.
• Be exposed to a few examples.

Event detection cameras that emerged out of biologically inspired visual perception offer a rich area of engineering innovation, research, and applications. Dynamic vision sensor (DVS) in an event detection camera generates a sparse asynchronous data stream reporting temporal log-intensity changes (or events) of the pixel-sized photodiodes. DVS enjoys a far wider dynamic range (>100dB) and temporal resolution (>800kHz) compared to the familiar active pixel sensors (APS), while lacking the notion of pixel intensity. Because conventional intensity-based image processing and computer vision techniques designed for APS will fail for DVS, a new set of DVS-specific tools need to be developed. In this tutorial, we characterize operating characteristics of DVS, and establish details needed for researchers to begin working with event data. We cover common computational technique to work with sparse event data, as well as examples of state-of-the-art applications of event cameras.

Intended Audience
Researchers (students, practitioners) with working knowledge of image processing in general that are interested in working with event detection cameras.

Keigo Hirakawa is an associate professor and undergraduate program director of electrical and computer engineering at the University of Dayton. He received BS in electrical engineering from Princeton University and MS and PhD in electrical and computer engineering from Cornell University. He was a research associate at Harvard University prior to joining the University of Dayton. His research focus is on computational imaging and sensing modalities in particular, including work in camera processing pipeline, polarimetric imaging, multispectral imaging, and event detection cameras.

COST

Discounts given for multiple classes. See Registration page for details and to register.

For office use only: