{\Omega}SFormer: Dual-Modal {\Omega}-like Super-Resolution Transformer Network for Cross-scale and High-accuracy Terraced Field Vectorization Extraction

TL;DR

This paper introduces { Omega}SFormer, a novel dual-modal super-resolution Transformer network that enhances terraced field vectorization accuracy from remotely sensed imagery by fusing spectral and terrain data, reducing segmentation errors, and optimizing feature extraction.

Contribution

The paper presents the first dual-modal { Omega}-like super-resolution Transformer network for terraced field vectorization, integrating multi-scale, multi-modal features and a new segmentation strategy.

Findings

Improved mIOU by up to 0.297 over baseline methods.

Validated effectiveness across nine study areas in China.

Achieved high-accuracy terraced field extraction with a new deep-learning framework.

Abstract

Terraced field is a significant engineering practice for soil and water conservation (SWC). Terraced field extraction from remotely sensed imagery is the foundation for monitoring and evaluating SWC. This study is the first to propose a novel dual-modal {\Omega}-like super-resolution Transformer network for intelligent TFVE, offering the following advantages: (1) reducing edge segmentation error from conventional multi-scale downsampling encoder, through fusing original high-resolution features with downsampling features at each step of encoder and leveraging a multi-head attention mechanism; (2) improving the accuracy of TFVE by proposing a {\Omega}-like network structure, which fully integrates rich high-level features from both spectral and terrain data to form cross-scale super-resolution features; (3) validating an optimal fusion scheme for cross-modal and cross-scale (i.e., inconsistent spatial resolution between remotely sensed imagery and DEM) super-resolution feature extraction; (4) mitigating uncertainty between segmentation edge pixels by a coarse-to-fine and spatial topological semantic relationship optimization (STSRO) segmentation strategy; (5) leveraging contour vibration neural network to continuously optimize parameters and iteratively vectorize terraced fields from semantic segmentation results. Moreover, a DMRVD for deep-learning-based TFVE was created for the first time, which covers nine study areas in four provinces of China, with a total coverage area of 22441 square kilometers. To assess the performance of {\Omega}SFormer, classic and SOTA networks were compared. The mIOU of {\Omega}SFormer has improved by 0.165, 0.297 and 0.128 respectively, when compared with best accuracy single-modal remotely sensed imagery, single-modal DEM and dual-modal result.