Cycled Technologies is a company that is based in Norway and provides smart waste management and recycling solutions that ensure environmental and financial sustainability. Bluestream was trusted to design and manufacture smart bins for automatic waste identification and segregation for Cycled Technologies. It was a collaboration that incorporated Bluestream’s extensive experience in street furniture and waste management solutions along with Cycled Technologies experience in the tech industry.
Smart litter bins are designed to recognize waste and segregate it accordingly. This is a key element to waste management. The AI is able to recognize the waste as its being deposited and then segregated based on an inbuilt separator. The bin was designed and realized in close association with the Bluestream Design Team, alongside Cycled which handled the technology.
A real-time system that can track vehicles and containers can enhance the collection process of solid trash. An advanced Solid Waste Collection and monitoring system can optimize the concurrent flow of data and information regarding the status of bin levels, the position in relation to their circumstances and state, and the truck data.
Bluestream developed a structure crucial for the instantaneous monitoring of the waste level by analyzing the waste level since improper waste disposal and overflowing waste bins are essential issues in cities that necessitate close observation. There hasn't been much research on bin level recognition, and earlier studies on liquid waste tank levels don't apply to bin level detection. To get the ideal values for their nearby parameters, the image texture is extracted using a Gray Level Aura Matrix. The creation of a reliable database is the initial stage in bin level detection. Then, to classify the new photographs, Gray Level Aura Matrix(GLAM) collects texture information from the pictorial representations and trains and assesses the output by implementing a K-Nearest Neighbor algorithm and the Multilayer Perception artificial neural network. The goal of this research is to optimize the GLAM in order to enhance the performance of this approach. The autonomous and technology-based solid waste bin level detection system is capable of doing a thorough analysis of the solid waste characteristics and estimating the level of waste. Municipalities can use the prototype implementation of this strategy for solid waste identification and classification.
