Project: Identifying illegal dumping from satellite imagery

Description: Illegal dumping is a frequent phenomenon in south European countries, including Cyprus. Dumping involves organic material, construction waste, old electronichs and machinery, abandoned cars etc. The goal of this project is to identify where dumping occurs from satellite imagery and then check whether this dumping is illegal. Spots of dumping will be indicated by citizens through their mobile phones, via a crowdsourcing-based approach. The identification system will then be automatically connected to the respective municipality services, depending on the exact location where dumping has occurred, in order to take measures. The case study takes place in Cyprus, with a strong focus in the sub-urban areas of Nicosia.

Collaboration with: CLEANathon team (Cyprus), Friends of the Earth (Cyprus)

Techniques used: Satellite imagery, deep learning, mobile phone computing (citizens’ crowdsourcing), geospatial analysis, GIS.

Started: July, 2020

Status: Finished

Chirag Padubidri, Andreas Kamilaris and Savvas Karatsiolis, Accurate Detection of Illegal Dumping Sites Using High Resolution Aerial Photography and Deep Learning, Workshop on Pervasive Smart Sustainable Cities (PerAwareCity), Proc. of the 20th IEEE PerCom, Pisa, Italy, March 2022.