In this section
Below is a list of all relevant publications authored by Robotics Forum members.
@article{Debrunner:2019:10.1145/3291055,
author = {Debrunner, T and Saeedi, Gharahbolagh S and Kelly, P},
doi = {10.1145/3291055},
journal = {ACM Transactions on Architecture and Code Optimization},
title = {AUKE: Automatic Kernel Code Generation for an analogue SIMD Focal-plane Sensor-Processor Array},
url = {http://dx.doi.org/10.1145/3291055},
volume = {15},
year = {2019}
}
TY - JOUR
AB - Focal-plane Sensor-Processor Arrays (FPSPs) are new imaging devices with parallel Single Instruction Multiple Data (SIMD) computational capabilities built into every pixel. Compared to traditional imaging devices, FPSPs allow for massive pixel-parallel execution of image processing algorithms. This enables the application of certain algorithms at extreme frame rates (>10,000 frames per second). By performing some early-stage processing in-situ, systems incorporating FPSPs can consume less power compared to conventional approaches using standard digital cameras. In this article, we explore code generation for an FPSP whose 256 × 256 processors operate on analogue signal data, leading to further opportunities for power reduction—and additional code synthesis challenges.While rudimentary image processing algorithms have been demonstrated on FPSPs before, progress with higher-level computer vision algorithms has been sparse due to the unique architecture and limits of the devices. This article presents a code generator for convolution filters for the SCAMP-5 FPSP, with applications in many high-level tasks such as convolutional neural networks, pose estimation, and so on. The SCAMP-5 FPSP has no effective multiply operator. Convolutions have to be implemented through sequences of more primitive operations such as additions, subtractions, and multiplications/divisions by two. We present a code generation algorithm to optimise convolutions by identifying common factors in the different weights and by determining an optimised pattern of pixel-to-pixel data movements to exploit them. We present evaluation in terms of both speed and energy consumption for a suite of well-known convolution filters. Furthermore, an application of the method is shown by the implementation of a Viola-Jones face detection algorithm.
AU - Debrunner,T
AU - Saeedi,Gharahbolagh S
AU - Kelly,P
DO - 10.1145/3291055
PY - 2019///
SN - 1544-3973
TI - AUKE: Automatic Kernel Code Generation for an analogue SIMD Focal-plane Sensor-Processor Array
T2 - ACM Transactions on Architecture and Code Optimization
UR - http://dx.doi.org/10.1145/3291055
UR - http://hdl.handle.net/10044/1/65831
VL - 15
ER -
Join our mailing list - sharing robotics-related activities at Imperial.
Robotics Forum
For all enquiries, please contact our Forum Manager, Dr Ana Cruz Ruiz
robotics-manager@imperial.ac.uk