Bi, Y;
Andreopoulos, Y;
(2017)
PIX2NVS: Parameterized conversion of pixel-domain video frames to neuromorphic vision streams.
In:
Proceedings of the 2017 IEEE International Conference on Image Processing (ICIP).
(pp. pp. 1990-1994).
IEEE: Beijing, China.
Preview |
Text
PIX2NVS_preprint.pdf - Published Version Download (6MB) | Preview |
Abstract
We propose and make available a generic pixel-to-neuromorphic vision stream (PIX2NVS) framework in order to allow for the generation of neuromorphic data streams from conventional pixel-domain video frames. In order to quantify the accuracy of our framework against experimentallyderived NVS data from previous work, we also propose and validate two metrics, the Chamfer distance and �-repeatability. The most important application of PIX2NVS will be in the generation of artificial NVS from large annotated video frame collections used in machine learning research, e.g., YouTube8M, YFCC100m, YouTube-BoundingBoxes, thereby transferring these datasets to the neuromorphic domain
| Type: | Proceedings paper |
|---|---|
| Title: | PIX2NVS: Parameterized conversion of pixel-domain video frames to neuromorphic vision streams |
| Event: | 24th IEEE International Conference on Image Processing (ICIP) |
| Location: | Beijing, PEOPLES R CHINA |
| Dates: | 17 September 2017 - 20 September 2017 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1109/ICIP.2017.8296630 |
| Publisher version: | https://doi.org/10.1109/ICIP.2017.8296630 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | dynamic vision sensing, neuromorphic vision, software, video analysis |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Electronic and Electrical Eng |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10056312 |
Archive Staff Only
 |
View Item |
