GTPBD-MM: A Global Terraced Parcel and Boundary Dataset with Multi-Modality

TL;DR

This paper introduces GTPBD-MM, a comprehensive multimodal benchmark dataset for extracting terraced parcels in mountainous regions, integrating optical imagery, text descriptions, and DEM data to improve parcel delineation accuracy.

Contribution

It presents the first unified benchmark for complex terraced parcel extraction using aligned image-text-DEM data and proposes a multimodal baseline network, ETTerra.

Findings

Textual semantics and terrain geometry improve delineation accuracy.

Multimodal cues lead to more coherent parcel boundaries.

Experiments show significant performance gains over visual-only methods.

Abstract

Agricultural parcel extraction plays an important role in remote sensing-based agricultural monitoring, supporting parcel surveying, precision management, and ecological assessment. However, existing public benchmarks mainly focus on regular and relatively flat farmland scenes. In contrast, terraced parcels in mountainous regions exhibit stepped terrain, pronounced elevation variation, irregular boundaries, and strong cross-regional heterogeneity, making parcel extraction a more challenging problem that jointly requires visual recognition, semantic discrimination, and terrain-aware geometric understanding. Although recent studies have advanced visual parcel benchmarks and image-text farmland understanding, a unified benchmark for complex terraced parcel extraction under aligned image-text-DEM settings remains absent. To fill this gap, we present GTPBD-MM, the first multimodal benchmark for global terraced parcel extraction. Built upon GTPBD, GTPBD-MM integrates high-resolution optical imagery, structured text descriptions, and DEM data, and supports systematic evaluation under Image-only, Image+Text, and Image+Text+DEM settings. We further propose Elevation and Text guided Terraced parcel network (ETTerra), a multimodal baseline for terraced parcel delineation. Extensive experiments demonstrate that textual semantics and terrain geometry provide complementary cues beyond visual appearance alone, yielding more accurate, coherent, and structurally consistent delineation results in complex terraced scenes.