Event-based vision enables the next revolution in visual perception for machines By C Posch and S Lavizzari, Prophesee
P
Intercon cables are VERY RELIABLE. In eight years, we have
HAD A FAILURE due to workmanship of the
cable assembly or cable bulk itself.”
Engineering Manager Leading Robotics Manufacturer
NEVER
rophesee has developed an image sensor, the output of which is not a sequence of images but a time-continuous stream of
individual pixel data, generated and transmitted conditionally, based on what is happening in the scene. Te sensor contains an array of autonomously
operating pixels that combine an asynchronous level-crossing detector with a separate exposure measurement circuit. Inspired by biology, every pixel in the sensor optimises its own sampling depending on the visual information it sees. In the case of rapid changes, the pixel samples at a high rate; if nothing happens, the pixel stops acquiring redundant data and goes idle. Hence each pixel independently samples its illuminance upon detection of a change of a certain magnitude in the light level. Te result of the exposure measurement
– i.e. the new grey level – is asynchronously output from the sensor, together with the pixel’s coordinates in the sensor array. As a result, image information is not acquired and transmitted frame-wise, but continuously, and conditionally only from parts of the scene where there is new visual information. In other words, only information that is relevant – because unknown – is acquired, transmitted, stored and eventually processed by machine vision algorithms. Pixel acquisition and readout times of
Precision Cable Assemblies for the Vision and High Speed Manufacturing Industries
(218) 828-3157
intercon@nortechsys.com
www.intercon-1.com
milliseconds to microseconds are achieved, resulting in temporal resolutions equivalent to conventional sensors running at tens to hundreds of thousands of frames per second. As the temporal resolution of the image data sampling process is no longer governed by a fixed clock driving all pixels, data volume depends on the dynamic contents of the scene. Visual data acquisition simultaneously becomes fast and sparse, leading to ultra-high-speed acquisition, combined with reduced power consumption, transmission bandwidth and memory requirements. In addition, processing
algorithms now work on continuous time events and features, instead of on discrete static images. Te mathematics that describe these features in
space and time are simple and elegant, and yield highly efficient algorithms and computational rules that allow for real-time operation of sensory processing systems, while minimising demand on computing power. And thanks to the time-based encoding of illumination information, very high dynamic range – intra- scene DR of 143dB static and 125dB at 30fps equivalent temporal resolution – is achieved. Prophesee has launched an advanced
event-based reference system called Onboard. It integrates a third-generation VGA sensor camera module with MIPI CSI interface, into
Each pixel independently samples its illuminance upon detection of a change of a certain magnitude in the light level
a powerful reference vision system Arm-based quad-core platform. It provides comprehensive connectivity including Ethernet, USB, HDMI, WiFi, operating under a Linux OS. Te embedded system runs dedicated
computer vision soſtware. Currently, it offers a tracking algorithm to detect motion, segment data into groups of spatio-temporal events, and track over time, taking two out of the four available cores. Te application layer comprises area monitoring, high-speed counting, vibration measurement and real-time inspection, which makes Onboard the perfect fit for the new artificial vision capabilities demanded by the fourth industrial revolution.
www.prophesee.ai
The exposure measurement is asynchronously output from the sensor, together with the pixel’s coordinates in the sensor array
@imveurope
www.imveurope.com
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72
