The aim of our system is to distinguish packaging from other kind of plastic. The first one in fact is recyclable while the others are used as fuel in waste-to-energy plants. This process result useful for the environment because both kind of plastic are often thrown together. The expensive industrial process provided by waste recycle companies is replaced by the action of users. The money saved in this way can be invested to spread this system in as many shopping center as possible. Moreover the system will improve the efficiency in the waste disposal both of waste transportation companies and users. In fact the user is assisted by notification on smartphone and some visual interfaces like LED stripes.

The separation is made by using a portable infrared scanner that can recognize the polymeric composition of plastic material. So the user throws the material in the right bin. The system periodically checks the amount of trash in every bin. Once anyone reaches a determined level it will notify the user through the smartphone application.

When the user decides to empty the bin, the system assigns him a color. At the same time, it turns on the right led strip with the corresponding color. The system chooses the waste container in which the contents best fit or alternatively an empty one.

It also takes care of notify the waste disposal society to send a disposal truck when one or more waste container are full.


  • User:the employee of each shop in the shopping center
  • Bin: small container for the different kind of waste in each shop
  • Waste container: general container in the ecological area of the shopping center where each bin is emptied
  • Waste recycle company: recycle center where the plastic is sorted
  • Packaging: kind of plastic which is recyclable
  • Waste-to-energy plants: process that uses plastic as fuel to generate energy
  • Waste plastic: any other kind of plastic that isn't recyclable
  • Shop: any store in the shopping center
  • Ecological Area:the zone of the shopping center where are located all the waste container
  • Analyzer for plastic identification: the sensor used to distinguish all kind of plastics
  • Led stripe: stripe made up with led lights. It leads the user to the waste container selected by the system showing the corresponding color provided by the smartphone application.

AmI Main Steps

AmI Step Description
Sensing Distinguish the packaging from the other types of plastic.
Detecting the volume of trash in each bin and waste container.
Reasoning Keep track of the amount of trash in each waste container and define the most suitable one.
(*) Optimize the retirement of the trash minimizing the number of calls to the waste transportation company.
Acting The system will indicate with a light path the correct waste container.
(*) In case of simultaneous use of different employee the light paths will be of different colors.
Call the waste transport company when a container is full.
Interacting At the end of the day or when a bin is almost full the system will remind the user to throw out the trash.

AmI Features

AmI Feature Description
Sensitive Receive data from each bin of any commercial activity and also from the waste containers.
Understand when a bin or a waste container is full.
Responsive Indicate the best waste container in which the content of the bin best fit and the colour of the respective stripe.
Transparent It is embedded in every bin and waste container.
Ubiquitous The system could be applied to any shopping center's collecting area.
Intelligent It’s able to identify the ideal waste container and let it know to the employee.
(*) A simple algorithm manages the minimizing of the number of call to the waste transport company.

(*) These properties of the system would not be implemented in the simulation because the model have only one stripe (so, only a waste container is effectively available) and we will test the system with only one user.


Functional Requirements

APP: user access system and interface, handling notification system, setting user preference.
SERVER: collecting data from bin and waste container sensors, handle lighting of light path, monitoring the amount of waste, realize actions.

The user can chose the time when he will receive the reminder notification
FR ID Title Description Priority
APP-1 "Login" System User has to select his own store 1
APP-2 Plastic Analyzer It provides an analyzer for the distinguish about packaging and other kind of plastics 1
APP-3 User decision It allow the user to empty the bin even if the bin is not full 2
APP-4 Notification It notifies the user to throw the trash whenever the bin is almost full 1
APP-5 Notification Clicking on the notification the user can see details about the associated bin and can start the procedure of emptying 3
APP-6 Notification A notification will be send at a certain time 2
APP-7 Data retrieving Show a summary of the information about the bins (associated to the store) and all the common waste containers 3
APP-8 Initial configuration 3
SERVER-1 Level Detector It recognize information about trash level in every waste container and bin 1
SERVER-2 Waste disposal center It automatically calls the waste recycle company whenever a waste container is full 1
SERVER-3 Light guide It guides the user to the right waste container by using a colored light path 2
SERVER-4 Light assignment It assignes a different color to every user whenever they are going to empty the bin 4
SERVER-5 Waste Container Selection When a bin is full, the system point out the correct waste container in which throwing the waste 1
SERVER-6 Initial configuration The initial configuration of the system is provided by reading a database 1
SERVER-7 Response Provide details about a single bin/waste container identified by his sensor ID 1
SERVER-8 Response Provide details about bins (of the requiring shop) / all the waste containers 1
SERVER-9 Response Provide the assigned colour and the chosen waste container 1

Non Functional Requirements

# Area Description
1 Portability The user interface is compatible with Android 5.0 or above phones
2 Portability The system could be easily installed in every large retailer center
3 Interoperability The server receive data from the sensors in every bin and waste container
4 Usability User interface will be in English
5 Usability The system requires an internet connection
6 Efficiency The plastic sensor should response within 5 seconds
7 Efficiency The system optimize waste management reducing, when it’s possible, the number of travel made by waste disposal truck
7 Compatibility The stripes must be compatible with the Philips Hue Bridge
7 Compatibility The sensors must be compatible and interfaciable with the central computational node


Hardware Architecture

Raspberry Pi
Central Computational Node and Server

  • Gets information from the ultrasonic ranging sensors
  • Elaborate data and manage the calls of the waste disposal center
  • Handles the turn on/off of the stripes
  • Respond at the various client through a REST interface
  • Connected through Ethernet or WiFi to the web

User Mobile Phone
Mobile Computational Node

  • Receives notification
  • Interact with the Server
  • Interface with the user through an Android application

Analyzer for Plastic/Polymer Identification
Sensing Node

  • It distinguishes packaging from other kind of plastic
  • The result will be shown on an integrated screen
  • In the simulated system it will be implemented in the PSDM app with the use of Google Vision API

Ultrasonic ranging sensors
Sensing Node

  • It is located on the internal part of the lid of the bin
  • It measures the level of fullness through ultrasonic waves
  • It is connected with the central node (server)

Led stripes indicator System
Acting Node
  • Led stripes are controlled by the Raspberry Pi

Software Architecture

Mobile Application (Android Application)
A simple interface allows the user to:
  • Receive notifications that reminds him to throw the waste at the closing time or when a bin is almost full.
  • Decide to throw the waste in an arbitrary moment.
  • Know the colour he must follow to reach the right waste container.
  • Know the level of waste in his bins and in the common waste containers.
  • Interact with the server running on Raspberry.
  • Exploit the Google Vision API
Runs on all devices with AndroidOS 5.0 or later.

Google Cloud Vision API
It enables developers to understand the content of an image by encapsulating powerful machine learning models in an easy to use REST API. It quickly classifies images into thousands of categories (e.g., "sailboat", "lion", "Eiffel Tower"), detects individual objects and faces within images, and finds and reads printed words contained within images
Through this API we make our application able to recognize a small number of typical recyclable and unrecyclable objects.

Server (Python Web Application)
  • Initialize the information on the trash container with the interaction with a database
  • Receive data about the level of trash from all the sensor
  • Send a mail to waste disposal center to notify the full (or almost) fill of a waste container.
  • When an user is going to throw the trash, it calculates the right waste container and light up the stripe to lead him.
  • Interact with the mobile devices and the sensors.
Runs on Raspberry Pi 3.

Network Architecture

The mobile devices will connect to the server via WiFi.
The server running on a Raspberry Pi 3, which has an integrated WiFi module.
The Raspberry will interact with the sensors via cable (in the demo). In a real context the sensors will have a wireless connection to the Raspberry.

# Selected Component Availability
1 Plastic Analyzer Not available
2 Raspberry Pi 3 We bought it
3 Ranging Sensor (HC SR04) Available on Ladispe
4 WiFi module for Raspberry Integrated in the Raspberry Pi 3
5 Some electronic components (breadboard or resistence) Available on Ladispe

Open issues

  • We need to find out the availability and the dimensions of the sensor that recognize the plastic.
  • We don’t know the price of the sensor that recognize the plastic, so we use the Google Vision API instead. Unfortunately, this service provides a less accurate recognition.
  • We have already met some employees and we are going to talk with a couple of activities’ director.
  • We will show our project with a scaled model on the LADISPE.


Download a quick presentation of the project


Simone Brigante
Git: SimoneBrigante
SW Developer

Francesco L. Casciaro
Git: flcasciaro
SW Developer

Alessandro Chiotti
Git: alechiotti
SW Developer

Giacomo De Leo
Git: GiacomoDeleo
HW Developer