Deep Joint Transmission-Recognition for Multi-View Cameras

TL;DR

This paper introduces deep neural network-based joint transmission and recognition schemes for multi-view wireless cameras, enhancing person classification accuracy at the wireless edge under various channel conditions.

Contribution

It proposes novel DNN-based compression schemes combining digital transmission and JSCC for efficient edge inference in surveillance applications.

Findings

JSCC schemes improve end-to-end accuracy

They simplify encoding process

They provide graceful degradation with channel quality

Abstract

We propose joint transmission-recognition schemes for efficient inference at the wireless edge. Motivated by the surveillance applications with wireless cameras, we consider the person classification task over a wireless channel carried out by multi-view cameras operating as edge devices. We introduce deep neural network (DNN) based compression schemes which incorporate digital (separate) transmission and joint source-channel coding (JSCC) methods. We evaluate the proposed device-edge communication schemes under different channel SNRs, bandwidth and power constraints. We show that the JSCC schemes not only improve the end-to-end accuracy but also simplify the encoding process and provide graceful degradation with channel quality.