Sort it Out: Using Artificial Intelligence for a Better Litter Collection

A solution that can help turn a litter into the data

Cleaning cities is a time and costs intensive business that affects our life’s in cities and of course the planet as a whole. How could cleaning be innovated and improved? How can AI technology help with that?

Optimizing trash collection is key to reduce costs and ensures that garbage collection and cleaning are optimized with maps and data about where trash accumulates and when. 

The EdgeX AI can help to track and count items such as cigarette buts and bottle caps.

EdgeX with a high precision detects cigarette butts among another litter. All this information (what? where? when?) will be sent to public services across the city using an LPWAN gateway for data processing and visualization.

The idea of using AI for improving the process of cleaning streets from a small litter was brought to the table by CleenR – German tech company engineering the world’s first smart litter platform that integrates data, devices, and services. After months of intensive workshops, MatchX and CleenR have successfully developed an end-to-end solution to help municipalities and cleaning workers to harness the power of data to reduce littering.

Every time, a cleaning team is working around the city, the AI camera attached to the cleaning vehicle or cleaning equipment pointed at the ground, analyses the area.

This helps to get data on which and how much garbage accumulates; creating daily, weekly and monthly trends and identifying hot spots. Accurate data can reduce the number of trucks on the streets, time spent cleaning and make cleaning pricing more accurate.

Within 10 years our cities, oceans and beaches can heal from pollution, if we train our eye to become sensitive to pollution. Technology can help change our attitudes and bad habits. Smart sensors are enabling us to save our planet and reemerge as a healthier society as a whole., said Victor Fischer, Founder & CEO at CleenR

Energy-efficient and privacy-preserving AI

EdgeX AI Kits designed for running artificial intelligence (AI) models on edge devices such as sensor nodes. It has a built-in camera, is ideal to cope with vast amounts of data generated.

The processed data from the camera never leaves the device, no privacy or personal data can be transmitted, making the camera GDPR compliant.  

The MatchX LPWAN gateway takes care of transmitting processed data from AI Kit to MatchX Cloud at low-power usage & long-distance communication. 

EdgeX AI Kit has a RISC-V chip with built-in neural networks acceleration together with the LoRa radio module, enables massive deployment of edge intelligence in LPWAN applications where complex data processing is required, such as videos. 

Using edge computing, the gigabytes of sensory and special data are analyzed, filtered and compressed before being transmitted. Overall, edge processing saves network expenses, storage and operating costs for management IoT traffic.

For the object-detection, we use the widely known Neural Networks: Yolo

Get in touch about your project needs, we are excited to help you build an intelligent solution. Contact us: awesome@matchx.io

One Response

Leave a Reply

Your email address will not be published. Required fields are marked *

Thank You

You subscribed to the MatchX Newsletter. You will soon receive an email asking you to confirm your subscription.