A Camera That CNNs: Towards Embedded Neural Networks on Pixel Processor Arrays

by   Laurie Bose, et al.

We present a convolutional neural network implementation for pixel processor array (PPA) sensors. PPA hardware consists of a fine-grained array of general-purpose processing elements, each capable of light capture, data storage, program execution, and communication with neighboring elements. This allows images to be stored and manipulated directly at the point of light capture, rather than having to transfer images to external processing hardware. Our CNN approach divides this array up into 4x4 blocks of processing elements, essentially trading-off image resolution for increased local memory capacity per 4x4 "pixel". We implement parallel operations for image addition, subtraction and bit-shifting images in this 4x4 block format. Using these components we formulate how to perform ternary weight convolutions upon these images, compactly store results of such convolutions, perform max-pooling, and transfer the resulting sub-sampled data to an attached micro-controller. We train ternary weight filter CNNs for digit recognition and a simple tracking task, and demonstrate inference of these networks upon the SCAMP5 PPA system. This work represents a first step towards embedding neural network processing capability directly onto the focal plane of a sensor.


page 1

page 2

page 3

page 4

page 5

page 7

page 8


A Camera That CNNs: Towards Embedded Neural Networks onPixel Processor Arrays

We present a convolutional neural network implementation for pixel proce...

Fully Embedding Fast Convolutional Networks on Pixel Processor Arrays

We present a novel method of CNN inference for pixel processor array (PP...

On-Sensor Binarized Fully Convolutional Neural Network with A Pixel Processor Array

This work presents a method to implement fully convolutional neural netw...

Agile Reactive Navigation for A Non-Holonomic Mobile Robot Using A Pixel Processor Array

This paper presents an agile reactive navigation strategy for driving a ...

Neural Network Generalization: The impact of camera parameters

We quantify the generalization of a convolutional neural network (CNN) t...

Toward Efficient Hyperspectral Image Processing inside Camera Pixels

Hyperspectral cameras generate a large amount of data due to the presenc...

Deep Demosaicing for Polarimetric Filter Array Cameras

Polarisation Filter Array (PFA) cameras allow the analysis of light pola...

Please sign up or login with your details

Forgot password? Click here to reset