Synchronized Object Detection for Autonomous Sorting, Mapping, and Quantification of Materials in Circular Healthcare

TL;DR

This paper presents a real-time synchronized object detection framework for autonomous sorting, mapping, and quantification of materials, supporting circular economy efforts through a prototype that detects multiple materials using synchronized vision units.

Contribution

It introduces a novel real-time synchronized detection framework and a prototype system for autonomous material monitoring and sorting in circular healthcare applications.

Findings

Prototype detects 4 materials from 5 inhaler models

Synchronization of vision units at 12-22 fps enables effective detection

Framework supports real-time material monitoring and mapping

Abstract

The circular economy paradigm is gaining interest as a solution to reducing both material supply uncertainties and waste generation. One of the main challenges in realizing this paradigm is monitoring materials, since in general, something that is not measured cannot be effectively managed. In this paper, we propose a real-time synchronized object detection framework that enables, at the same time, autonomous sorting, mapping, and quantification of solid materials. We begin by introducing the general framework for real-time wide-area material monitoring, and then, we illustrate it using a numerical example. Finally, we develop a first prototype whose working principle is underpinned by the proposed framework. The prototype detects 4 materials from 5 different models of inhalers and, through a synchronization mechanism, it combines the detection outputs of 2 vision units running at 12-22 frames per second (Fig. 1). This led us to introduce the notion of synchromaterial and to conceive a robotic waste sorter as a node compartment of a material network. Dataset, code, and demo videos are publicly available.