IGraSS: Learning to Identify Infrastructure Networks from Satellite Imagery by Iterative Graph-constrained Semantic Segmentation

TL;DR

IGraSS is an iterative framework that combines semantic segmentation and graph-based refinement to improve infrastructure network mapping from satellite imagery, significantly reducing unreachable segments and enhancing accuracy.

Contribution

The paper introduces IGraSS, a novel iterative approach that integrates semantic segmentation with graph-based ground-truth refinement for infrastructure mapping.

Findings

Reduces unreachable canal segments from 18% to 3%.

Improves canal identification accuracy with refined ground truth.

Demonstrates effectiveness on both canal and road networks.

Abstract

Accurate canal network mapping is essential for water management, including irrigation planning and infrastructure maintenance. State-of-the-art semantic segmentation models for infrastructure mapping, such as roads, rely on large, well-annotated remote sensing datasets. However, incomplete or inadequate ground truth can hinder these learning approaches. Many infrastructure networks have graph-level properties such as reachability to a source (like canals) or connectivity (roads) that can be leveraged to improve these existing ground truth. This paper develops a novel iterative framework IGraSS, combining a semantic segmentation module-incorporating RGB and additional modalities (NDWI, DEM)-with a graph-based ground-truth refinement module. The segmentation module processes satellite imagery patches, while the refinement module operates on the entire data viewing the infrastructure network as a graph. Experiments show that IGraSS reduces unreachable canal segments from around 18% to 3%, and training with refined ground truth significantly improves canal identification. IGraSS serves as a robust framework for both refining noisy ground truth and mapping canal networks from remote sensing imagery. We also demonstrate the effectiveness and generalizability of IGraSS using road networks as an example, applying a different graph-theoretic constraint to complete road networks.