Monitoring Urban Forests from Auto-Generated Segmentation Maps
This work addresses the need for efficient urban forest monitoring for environmental management, but it is incremental as it builds on existing weakly-supervised segmentation methods.
The authors tackled the problem of quantifying urban forests with minimal human supervision by using LiDAR data as noisy labels to train segmentation models, achieving a proof-of-concept application to monitor Hurricane Sandy's impact on trees in NYC.
We present and evaluate a weakly-supervised methodology to quantify the spatio-temporal distribution of urban forests based on remotely sensed data with close-to-zero human interaction. Successfully training machine learning models for semantic segmentation typically depends on the availability of high-quality labels. We evaluate the benefit of high-resolution, three-dimensional point cloud data (LiDAR) as source of noisy labels in order to train models for the localization of trees in orthophotos. As proof of concept we sense Hurricane Sandy's impact on urban forests in Coney Island, New York City (NYC) and reference it to less impacted urban space in Brooklyn, NYC.