# A Multi-Scale Global Fusion-Based Method for Surface Fissure Extraction from UAV Imagery

## TL;DR

This paper introduces MGF-UNet, a new method for accurately extracting surface fissures from high-resolution UAV imagery to aid in geohazard monitoring.

## Contribution

The novel MGF-UNet integrates multi-scale feature sensing and a transformer-based module for improved fissure detection in complex terrains.

## Key findings

- MGF-UNet achieves 78.2% accuracy, 81.4% Dice score, and 68.6% IoU on fissure detection benchmarks.
- The method outperforms existing networks in capturing elongated fissures and preserving structural details.
- It demonstrates effectiveness in deformation-prone environments for geohazard monitoring and ecological restoration.

## Abstract

The prevalence of ground fissures in deformation-affected areas has intensified, presenting serious risks to both operational safety and the local natural environment. Fissures in these disturbed terrains are typically characterized by elongated morphologies and large-scale variations, which pose substantial challenges to accurate feature extraction. To address these complexities, this paper proposes a semantic segmentation network termed MGF-UNet. In the shallow layers, we integrate multi-scale feature sensing (MFS) and grouped efficient multi-scale attention (EMA) to sharpen anisotropic textures and boundary details under high-resolution representations. For the deeper layers, a Token-Selective Context Transformer (TSCT) is designed to perform selective global modeling on high-level semantic features, effectively capturing long-range dependencies while preserving the structural integrity of elongated fissures. Meanwhile, we employ feature-wise linear modulation (FiLM) to derive pixel-wise affine parameters from shallow structures, which pre-modulate deep features and strengthen cross-level interactions. In the decoder, a Fourier transform-based adaptive feature fusion (AFF) module suppresses background noise and enhances boundary contrast, followed by cross-scale aggregation for final prediction.Benchmark tests conducted on the mining-area fissure dataset (MFD) and road-based datasets demonstrate that MGF-UNet achieves an accuracy of 78.2%, a Dice score of 81.4%, and an IoU of 68.6%, outperforming existing mainstream networks. The results confirm that MGF-UNet provides an effective solution for automatic fissure extraction in deformation-prone environments, offering significant potential for geohazard monitoring and ecological restoration.