Convolutional Neural Network Segmentation for Satellite Imagery Data to Identify Landforms Using U-Net Architecture

2025-02-08

AI Summary

This paper addresses the challenge of pixel-level semantic segmentation of topographic landforms in high-resolution remote sensing imagery. Methodologically, it proposes a U-Net variant specifically tailored for landform classification—marking the first application of deep U-Net architecture to this task—integrated with a high-fidelity satellite image preprocessing pipeline and enhanced by Dropout regularization and the Adam optimizer to improve generalization and training stability. Experimental results demonstrate state-of-the-art performance, achieving an mIoU of 86.3% on landform classes, significantly outperforming conventional CNN-based segmentation baselines. The model exhibits strong practical utility and cross-domain transferability across diverse applications, including autonomous vehicle path perception, dynamic flood disaster monitoring, and territorial spatial planning. By establishing a reusable technical paradigm, this work advances intelligent interpretation of remote sensing data.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

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

Abstract

This study demonstrates a novel use of the U-Net architecture in the field of semantic segmentation to detect landforms using preprocessed satellite imagery. The study applies the U-Net model for effective feature extraction by using Convolutional Neural Network (CNN) segmentation techniques. Dropout is strategically used for regularization to improve the model's perseverance, and the Adam optimizer is used for effective training. The study thoroughly assesses the performance of the U-Net architecture utilizing a large sample of preprocessed satellite topographical images. The model excels in semantic segmentation tasks, displaying high-resolution outputs, quick feature extraction, and flexibility to a wide range of applications. The findings highlight the U-Net architecture's substantial contribution to the advancement of machine learning and image processing technologies. The U-Net approach, which emphasizes pixel-wise categorization and comprehensive segmentation map production, is helpful in practical applications such as autonomous driving, disaster management, and land use planning. This study not only investigates the complexities of U-Net architecture for semantic segmentation, but also highlights its real-world applications in image classification, analysis, and landform identification. The study demonstrates the U-Net model's key significance in influencing the environment of modern technology.

Problem

• U-Net for landform identification
• CNN segmentation in satellite imagery
• Semantic segmentation using U-Net architecture

Innovation

• U-Net architecture
• CNN segmentation
• Adam optimizer