Greenery Segmentation In Urban Images By Deep Learning

TL;DR

This paper introduces a deep learning approach for urban greenery segmentation that improves the accuracy of Green View Index estimation by leveraging advanced architectures and a novel loss function weighting strategy.

Contribution

The paper presents a new deep learning method with a specialized loss function to enhance greenery segmentation accuracy in urban images.

Findings

Improved Green View Index estimation accuracy

Effective deep learning architecture for greenery segmentation

Enhanced loss function strategy for better results

Abstract

Vegetation is a relevant feature in the urban scenery and its awareness can be measured in an image by the Green View Index (GVI). Previous approaches to estimate the GVI were based upon heuristics image processing approaches and recently by deep learning networks (DLN). By leveraging some recent DLN architectures tuned to the image segmentation problem and exploiting a weighting strategy in the loss function (LF) we improved previously reported results in similar datasets.