tinyML Talks: Machine Learning for Event-cameras

Event-based cameras encodes visual information in a sparse and asynchronous stream of events, corresponding to log-luminosity intensity changes in the scene. By transmitting only changes, event-based cameras uniquely combine high temporal resolution, power and data efficiency.

However, to apply conventional machine learning methods on event cameras, one has to turn the asynchronous stream of events into a frame-like representation. This results in a loss of the power efficiency and non-redundant representation of the event data.

In this talk we will first present current advances in event-based technology and machine learning applications. Then we focus on alternative machine learning architectures, designed to fully exploit the properties of event-based data.

Date

October 26, 2021

Location

Virtual

Contact us

Discussion

Schedule

Timezone: PDT

Machine Learning for Event-cameras

Amos SIRONI, Chief Machine Learning Scientists

PROPHESEE

Event-based cameras encodes visual information in a sparse and asynchronous stream of events, corresponding to log-luminosity intensity changes in the scene. By transmitting only changes, event-based cameras uniquely combine high temporal resolution, power and data efficiency.

However, to apply conventional machine learning methods on event cameras, one has to turn the asynchronous stream of events into a frame-like representation. This results in a loss of the power efficiency and non-redundant representation of the event data.

In this talk we will first present current advances in event-based technology and machine learning applications. Then we focus on alternative machine learning architectures, designed to fully exploit the properties of event-based data.

Amos SIRONI, Chief Machine Learning Scientists

PROPHESEE

Amos Sironi has been leading the Artificial Intelligence team at Prophesee for the past 4 years. His work focuses on designing machine learning methods for even-based cameras, with applications in automotive, AR/VR and IoT. Before joining Prophesee he obtained a PhD in Computer Vision from the École polytechnique fédérale de Lausanne (EPFL) under the supervision of Prof. Pascal Fua 1and Prof. Vincent Lepetit. His research interests lie at the boundaries between Computer Vision, Artificial Intelligence and Neuromorphic systems.

Schedule subject to change without notice.