A Camera That CNNs : Towards Embedded Neural Networks on Pixel Processor Arrays
- Submitting institution
-
University of Bristol
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 218834220
- Type
- E - Conference contribution
- DOI
-
10.1109/ICCV.2019.00142
- Title of conference / published proceedings
- 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
- First page
- 1335
- Volume
- -
- Issue
- -
- ISSN
- 2380-7504
- Open access status
- Compliant
- Month of publication
- February
- Year of publication
- 2020
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
4
- Research group(s)
-
C - Visual Information Lab
- Citation count
- 4
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper was the first to demonstrate (https://www.youtube.com/watch?v=sZvVhS7130) a CNN on a re-programmable image plane of a hardware sensor-processor array. Selected as oral (https://www.youtube.com/watch?v=9Sx2qWKGzlc&feature=youtu.be&t=1791) for ICCV2019. A main result of research grant: EPSRC EP/M019454/1. Live demo at CVPR2019 and follow up publications at ECCV2020 (https://www.springerprofessional.de/en/fully-embedding-fast-convolutional-networks-on-pixel-processor-a/18454756) and BMVC2020 (https://www.bmvc2020-conference.com/conference/papers/paper_0126.html), that building on this work, enabled CNN operation at tens of thousands of frames per second. Led to keynote invites for IEEE/CVF WACV workshop on Autonomous Vehicle Vision2021 and IEEE ICRA2021 workshop On- and Near-sensor Vision Processing, from Photons to Applications.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -