Imperial College London
Alternate

ProfessorPaulKelly

Faculty of Engineering, Department of Computing

Professor of Software Technology
 
 
 
//

Contact

 

+44 (0)20 7594 8332p.kelly Website

 
 
//

Location

 

Level 3 (upstairs), William Penney Building, room 304William Penney LaboratorySouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Stow:2022:10.1007/s10514-022-10053-w,
author = {Stow, E and Ahsan, A and Li, Y and Babaei, A and Murai, R and Saeedi, S and Kelly, PHJ},
doi = {10.1007/s10514-022-10053-w},
journal = {Autonomous Robots},
pages = {893--910},
title = {Compiling CNNs with Cain: focal-plane processing for robot navigation},
url = {http://dx.doi.org/10.1007/s10514-022-10053-w},
volume = {46},
year = {2022}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Focal-plane Sensor-processors (FPSPs) are a camera technology that enables low power, high frame rate computation in the image sensor itself, making them suitable for edge computation. To fit into the sensor array, FPSPs are highly resource-constrained, with limited instruction set and few registers - which makes developing complex algorithms difficult. In this work, we present Cain, a compiler for convolutional filters that targets SCAMP-5, a general-purpose FPSP. Cain generates code to evaluate multiple convolutional kernels at the same time. It generates code that avoids the need for hardware multipliers, while orchestrating the exploitation of common sub-terms—leading to a large reduction in instruction count compared to both straightforward and prior optimized approaches. We demonstrate the capability enabled by Cain on SCAMP-5 with robotic navigation for near-sensor high-speed and low-power computation, by using Cain to implement a neural network on the focal plane.
AU  - Stow,E
AU  - Ahsan,A
AU  - Li,Y
AU  - Babaei,A
AU  - Murai,R
AU  - Saeedi,S
AU  - Kelly,PHJ
DO  - 10.1007/s10514-022-10053-w
EP  - 910
PY  - 2022///
SN  - 0929-5593
SP  - 893
TI  - Compiling CNNs with Cain: focal-plane processing for robot navigation
T2  - Autonomous Robots
UR  - http://dx.doi.org/10.1007/s10514-022-10053-w
UR  - https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000852366900001&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=1ba7043ffcc86c417c072aa74d649202
UR  - https://link.springer.com/article/10.1007/s10514-022-10053-w
UR  - http://hdl.handle.net/10044/1/99998
VL  - 46
ER  -
Download