2022/02/02 by Yanan Liu, Liu, Yanan, Laurie Bose +7
Computer Science · Engineering · #Advanced Memory and Neural Computing #Advanced Neural Network Applications #CCD and CMOS Imaging Sensors #Computer Vision and Pattern Recognition (cs.CV) #Emerging Technologies (cs.ET) #FOS: Computer and information sciences #FOS: Electrical engineering #Signal Processing (eess.SP) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2202.00836
openalex publication_date 2022/02/02 · openalex created_date 2022/04/03 · openalex updated_date 2026/07/28
This work presents a method to implement fully convolutional neural networks (FCNs) on Pixel Processor Array (PPA) sensors, and demonstrates coarse segmentation and object localisation tasks. We design and train binarized FCN for both binary weights and activations using batchnorm, group convolution, and learnable threshold for binarization, producing networks small enough to be embedded on the focal plane of the PPA, with limited local memory resources, and using parallel elementary add/subtract, shifting, and bit operations only. We demonstrate the first implementation of an FCN on a PPA device, performing three convolution layers entirely in the pixel-level processors. We use this architecture to demonstrate inference generating heat maps for object segmentation and localisation at over 280 FPS using the SCAMP-5 PPA vision chip.