A Low-Power Distributed Visual Sensor Network for Real-Time Barcode Localization and Identification.

Bruno Cornelis,Leander Hendrikx,Rui Zhong,Adrian Munteanu

doi:10.3390/s22041433

Abstract

A novel low-power distributed Visual Sensor Network (VSN) system is proposed, which performs real-time collaborative barcode localization, tracking, and robust identification. Due to a dynamic triggering mechanism and efficient transmission protocols, communication is organized amongst the nodes themselves rather than being orchestrated by a single sink node, achieving lower congestion and significantly reducing the vulnerability of the overall system. Specifically, early detection of the moving barcode is achieved through a dynamic triggering mechanism. A hierarchical transmission protocol is designed, within which different communication protocols are used, depending on the type of data exchanged among nodes. Real-Time Transport Protocol (RTP) is employed for video communication, while the Transmission Control Protocol (TCP) and Long Range (LoRa) protocol are used for passing messages amongst the nodes in the VSN. Through an extensive experimental evaluation, we demonstrate that the proposed distributed VSN brings substantial advantages in terms of accuracy, power savings, and time complexity compared to an equivalent system performing centralized processing.

Highlights

The increased availability of cheap electronics has enabled the construction of low-costVisual Sensor Network (VSN) platforms that are able to capture, process, and disseminate visual data collectively [1]
Due to the lack of appropriate triggering mechanisms and a comprehensive transmission protocol, the method suffered from low frame rates when the tracker was deployed on low-power embedded devices. To achieve both robust and real-time barcode tracking in a low-power VSN, we presented a distributed visual processing system via substantial algorithmic changes in collaborative barcode localization [9]
In contrast to the centralized coordination for barcode tracking in [8], we propose a completely distributed system with collaborative processing among nodes based on the proposed dynamic triggering mechanism and the hierarchical transmission protocol

Summary

Introduction

The increased availability of cheap electronics has enabled the construction of low-costVisual Sensor Network (VSN) platforms that are able to capture, process, and disseminate visual data collectively [1]. A VSN consists of a multitude of small, connected camera sensor nodes, each with their own computation and communication components and power source, which aggregate visual data, process it collaboratively, and transmit useful information to a control center [2]. These platforms provide an excellent solution for many applications, such as video surveillance, personal care, virtual reality, and logistics [3]. The triggering mechanism that controls how to activate or deactivate the nodes is a critical factor affecting the overall energy and bandwidth consumption. In [6], the prediction of a node’s state is performed via the fusion of states passed from multiple nodes to a sink node

Methods

Results

Conclusion