Please use this identifier to cite or link to this item:
https://doi.org/10.3389/fnins.2018.00118
DC Field | Value | |
---|---|---|
dc.title | A noise filtering algorithm for event-based Asynchronous change detection image sensors on TrueNorth and its implementation on TrueNorth | |
dc.contributor.author | Padala, V | |
dc.contributor.author | Basu, A | |
dc.contributor.author | Orchard, G | |
dc.date.accessioned | 2020-10-30T02:09:15Z | |
dc.date.available | 2020-10-30T02:09:15Z | |
dc.date.issued | 2018 | |
dc.identifier.citation | Padala, V, Basu, A, Orchard, G (2018). A noise filtering algorithm for event-based Asynchronous change detection image sensors on TrueNorth and its implementation on TrueNorth. Frontiers in Neuroscience 12 (MAR) : 118. ScholarBank@NUS Repository. https://doi.org/10.3389/fnins.2018.00118 | |
dc.identifier.issn | 16624548 | |
dc.identifier.uri | https://scholarbank.nus.edu.sg/handle/10635/182090 | |
dc.description.abstract | Asynchronous event-based sensors, or "silicon retinae," are a new class of vision sensors inspired by biological vision systems. The output of these sensors often contains a significant number of noise events along with the signal. Filtering these noise events is a common preprocessing step before using the data for tasks such as tracking and classification. This paper presents a novel spiking neural network-based approach to filtering noise events from data captured by an Asynchronous Time-based Image Sensor on a neuromorphic processor, the IBM TrueNorth Neurosynaptic System. The significant contribution of this work is that it demonstrates our proposed filtering algorithm outperforms the traditional nearest neighbor noise filter in achieving higher signal to noise ratio (~10 dB higher) and retaining the events related to signal (~3X more). In addition, for our envisioned application of object tracking and classification under some parameter settings, it can also generate some of the missing events in the spatial neighborhood of the signal for all classes of moving objects in the data which are unattainable using the nearest neighbor filter. © 2018 Padala, Basu and Orchard. | |
dc.rights | Attribution 4.0 International | |
dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | |
dc.source | Unpaywall 20201031 | |
dc.subject | algorithm | |
dc.subject | Article | |
dc.subject | artificial neural network | |
dc.subject | data processing | |
dc.subject | human | |
dc.subject | image display | |
dc.subject | image sensor | |
dc.subject | noise filtering algorithm | |
dc.subject | noise reduction | |
dc.subject | refractory period | |
dc.subject | signal noise ratio | |
dc.subject | software | |
dc.subject | videorecording | |
dc.type | Article | |
dc.contributor.department | TEMASEK LABORATORIES | |
dc.description.doi | 10.3389/fnins.2018.00118 | |
dc.description.sourcetitle | Frontiers in Neuroscience | |
dc.description.volume | 12 | |
dc.description.issue | MAR | |
dc.description.page | 118 | |
Appears in Collections: | Elements Staff Publications |
Show simple item record
Files in This Item:
File | Description | Size | Format | Access Settings | Version | |
---|---|---|---|---|---|---|
10_3389_fnins_2018_00118.pdf | 3.18 MB | Adobe PDF | OPEN | None | View/Download |
This item is licensed under a Creative Commons License