Time and Date: 8:15 - 5:00PM - June 2nd, 2017

Location: room 4613/4713 - Sands Expo and Convention Centre

Schedule:

8:15 Introduction to the workshop: Davide Scaramuzza
  SESSION 1: Devices and Companies
8:30 Tobi Delbruck, ETH Zurich / University of Zurich, lead inventor of the DVS/DAVIS sensors,
The development of the DVS and DAVIS sensors, PDF, YouTube
9:00 Yoel Yaffe, Samsung Israel Research Center, Samsung Electronics,
Dynamic Vision Sensor - The Road to Market
9:20 Brian Taba, IBM Research,
Object and Action Recognition on the Event-based IBM TrueNorth Processor, YouTube
9:40 Xavier Lagorce, Chronocam,
The ATIS Sensor, PDF
10:00 Live Demos and Coffee break
  SESSION 2: Algorithms
10:30 Andrew Davison, Imperial College London,
Reconstruction, Motion Estimation and SLAM from Events, PDF, YouTube
11:00 Kostas Daniilidis, University of Pennsylvania,
Event-based Feature Tracking and Visual Inertial Odometry, PDF, YouTube
11:30 Davide Scaramuzza, University of Zurich,
Event-based Algorithms for Robust and High-speed Robotics, PDF, YouTube
12:00 Live Demos and Lunch Break
  SESSION 3: Bio-inspired and embedded vision
13:30 Chiara Bartolozzi, Istituto Italiano di Tecnologia,
Event-driven Sensing for a Humanoid Robot, PDF, YouTube
14:00 Jörg Conradt, Technical University of Munich,
Miniaturized, Embedded Event-based Vision for High-speed Robots, PDF, YouTube
14:30 Garrick Orchard , National University of Singapore,
Bio-Inspired Embedded Event-based Visual Processing, PDF, YouTube
15:00 Live Demos and Coffee break
  SESSION 4: Companies
15:30 Christian Brandli, CEO and co-founder of Insightness,
From Event-based Visions to Real Systems, PDF, YouTube
15:50 Hanme Kim, co-founder of Slamcore,
Event-based SLAM at Slamcore, PDF, YouTube
16:10 Sven-Erik Jacobsen, founder of iniVation,
iniVation – Market-driven Technology Staircase for Event-based Vision, PDF
16:30 Panel discussion

Live Demos

  • Tobi Delbruck, ETH Zurich / University of Zurich, lead inventor of the DVS/DAVIS sensors,
    Play with newest DAVIS prototype from INI and inilabs
  • Christian Brandli, CEO and founder of Insightness,
    Insightness Drone Collision Avoidance Evaluation Kit
  • Yoel Yaffe, Samsung Israel Research Center, Samsung Electronics
    Samsung; Experience Dynamic Vision Sensor (Gen2) on Mobile and PC platforms
  • Xavier Lagorce, Chronocam
    Chronocam and the ATIS sensor
  • Shoushun Chen, Hillhouse Technology
    CeleX: Revolutionary Smart Sensor for Smart Mobility
  • Jörg Conradt, Technical University of Munich
    Small and light embedded event-based vision for mobile systems
  • Garrick Orchard and Xie Zhen, National University of Singapore
    Event-based optical flow in FPGA
  • Alex Zhu, University of Pennsylvania
    Event-based feature tracking with probabilistic feature association
  • Piotr Dudek (University of Manchester) and Laurie Bose (University of Bristol)
    Cellular Processor Array cameras
  • Henri Rebecq, University of Zurich
    EVO: Event-based Visual Odometry
  • Timo Horstschaefer, University of Zurich
    Real-time Visual-Inertial Odometry with an Event Camera
  • Chiara Bartolozzi, Istituto Italiano di Tecnologia
    Fast Event-based Corner Detection
  • Guillermo Gallego, University of Zurich
    Motion estimation by contrast maximization

Objectives:
This workshop is dedicated to event-based vision sensors and algorithms. Event-based cameras are revolutionary vision sensors with three key advantages: a measurement rate that is almost 1 million times faster than standard cameras, a latency of microseconds, and a high dynamic range that is six orders of magnitude larger than that of standard cameras. Event-based sensors open frontiers which are unthinkable with standard cameras (which have been the main sensing technology of the past 50 years). These revolutionary sensors enable the design of a new class of algorithms to track a baseball in the moonlight, build a flying robot with the same agility of a fly, localizing and mapping in challenging lighting conditions and at remarkable speeds. These sensors became commercially available in 2008 and are slowly being adopted in mobile robotics. They covered the main news in 2016 with Intel and Bosch announcing a $15 million investment in event-camera company Chronocam and Samsung announcing its use with the IBM's brain-inspired TrueNorth processor to recognize human gestures. This workshop will cover the sensing hardware as well as the processing, learning, and control methods needed to take advantage of these sensors.


FAQs:

  • What is an event camera? Watch this video explanation! More info here.
  • What are possible applications of event cameras? A non-comprehensive list can be found here and here.
  • Where can I buy an event camera? From IniLabs.
  • Is there a event-camera dataset I can play with, so that I don't have to buy the sensor? Yes, here.

Organizers:


Previous related workshops: