UH Biocomputation Group - Heuristic algorithmshttp://biocomputation.herts.ac.uk/2021-05-12T13:13:07+01:00Event-Driven Sensing for Efficient Perception: Vision and Audition Algorithms2021-05-12T13:13:07+01:002021-05-12T13:13:07+01:00Nik Dennlertag:biocomputation.herts.ac.uk,2021-05-12:/2021/05/12/event-driven-sensing-for-efficient-perception-vision-and-audition-algorithms.html<p class="first last">Nik Dennler's Journal Club session where he will talk about a paper "Event-Driven Sensing for Efficient Perception: Vision and Audition Algorithms"</p>
<p>This week on Journal Club session Nik Dennler will talk about a paper "Event-Driven Sensing for Efficient Perception: Vision and Audition Algorithms".</p>
<hr class="docutils" />
<p>Event sensors implement circuits that capture partial functionality of
biological sensors, such as the retina and cochlea. As with their
biological counterparts, event sensors are drivers of their own
output. That is, they produce dynamically sampled binary events to
dynamically changing stimuli. Algorithms and networks that process
this form of output representation are still in their infancy, but
they show strong promise. This article illustrates the unique form of
the data produced by the sensors and demonstrates how the properties
of these sensor outputs make them useful for power-efficient,
low-latency systems working in real time.</p>
<div class="line-block">
<div class="line"><br /></div>
</div>
<p>Papers:</p>
<ul class="simple">
<li>S. Liu, B. Rueckauer, E. Ceolini, A. Huber, T. Delbruck, <a class="reference external" href="https://doi.org/10.1109/MSP.2019.2928127">"Event-Driven Sensing for Efficient Perception: Vision and Audition Algorithms"</a>, 2019, IEEE Signal Processing Magazine, 36, 29--37</li>
</ul>
<p><strong>Date:</strong> 2021/05/14 <br />
<strong>Time:</strong> 14:00 <br />
<strong>Location</strong>: online</p>