Self-supervised Approach for Urban Tree Recognition on Aerial Images

Abstract

In the light of Artificial Intelligence aiding modern society in tackling climate change, this research looks at how to detect vegetation from aerial view images using deep learning models. This task is part of a proposed larger framework to build an eco-system to monitor air quality and the related factors like weather, transport, and vegetation, as the number of trees for any urban city in the world. The challenge involves building or adapting the tree recognition models to a new city with minimum or no labeled data. This paper explores self-supervised approaches to this problem and comes up with a system with 0.89 mean average precision on the Google Earth images for Cambridge city.

Data-Driven Framework for Understanding and Predicting Air Quality in Urban Areas

“…Building on our initial studies (Babu Saheer et al, 2020;Babu Saheer and Shahawy, 2021), this research aims to generate a framework for monitoring and modeling the air quality for urban cities by understanding the different factors that influence the concentration of pollutants in the air. Integrating information from various sources including measured pollutant concentration, weather, traffic and other correlated features alongside understanding vegetation distribution around urban cities can help urban planners to build sustainable green spaces.…”