Comparison of Segmentation Methods in Remote Sensing for Land Use Land Cover

2025-07-24

AI Summary

Rapid urbanization has led to complex land use and land cover (LULC) dynamics—including urban expansion, green space reduction, and industrial sprawl—posing significant challenges for timely and accurate LULC monitoring. To address this, we propose a remote sensing image classification framework integrating atmospheric correction with semi-supervised learning. Our method innovatively introduces a dynamic weighted cross-pseudo supervision mechanism to enhance pseudo-label quality and training stability. It synergistically combines look-up-table (LUT)-based atmospheric correction, the DeepLabV3+ semantic segmentation network, and the Cross-Pseudo Supervision framework to improve generalization in heterogeneous urban scenes. Evaluated over Hyderabad, India, the approach achieves substantially improved LULC mapping accuracy, enabling fine-grained urban expansion monitoring and supporting sustainable land resource management. The framework provides a scalable, cost-effective, and operationally viable paradigm for high-temporal-resolution LULC change assessment.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Semi-Supervised Learning
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Land Use Land Cover (LULC) mapping is essential for urban and resource planning, and is one of the key elements in developing smart and sustainable cities.This study evaluates advanced LULC mapping techniques, focusing on Look-Up Table (LUT)-based Atmospheric Correction applied to Cartosat Multispectral (MX) sensor images, followed by supervised and semi-supervised learning models for LULC prediction. We explore DeeplabV3+ and Cross-Pseudo Supervision (CPS). The CPS model is further refined with dynamic weighting, enhancing pseudo-label reliability during training. This comprehensive approach analyses the accuracy and utility of LULC mapping techniques for various urban planning applications. A case study of Hyderabad, India, illustrates significant land use changes due to rapid urbanization. By analyzing Cartosat MX images over time, we highlight shifts such as urban sprawl, shrinking green spaces, and expanding industrial areas. This demonstrates the practical utility of these techniques for urban planners and policymakers.

Problem

• Evaluates LULC mapping techniques for urban planning
• Compares DeeplabV3+ and CPS models with dynamic weighting
• Analyzes Cartosat MX images to track urbanization changes

Innovation

• LUT-based Atmospheric Correction for Cartosat MX
• DeeplabV3+ and CPS for LULC prediction
• Dynamic weighting enhances pseudo-label reliability