While Deep Neural Network (DNN) models have provided remarkable advances in machine vision capabilities, their high computational complexity and model sizes present a formidable roadblock to deployment in AIoT-based sensing applications. In this paper, we propose a novel paradigm by which peer nodes in a network can collaborate to improve their accuracy on person detection, an exemplar machine vision task. The proposed methodology requires no re-training of the DNNs and incurs minimal processing latency as it extracts scene summaries from the collaborators and injects back into DNNs of the reference cameras, on-the-fly. Early results show promise with improvements in recall as high as 10% with a single collaborator, on benchmark datasets.
@article{arxiv.2012.08643,
title = {Enabling Collaborative Video Sensing at the Edge through Convolutional Sharing},
author = {Kasthuri Jayarajah and Dhanuja Wanniarachchige and Archan Misra},
journal= {arXiv preprint arXiv:2012.08643},
year = {2020}
}