fabSAM: A Farmland Boundary Delineation Method Based on the Segment Anything Model
This work addresses agricultural management needs by providing a more accurate method for mapping farmland boundaries from satellite data, though it is incremental as it adapts existing models.
The paper tackles farmland boundary delineation from remote sensing imagery by proposing fabSAM, a method combining Deeplabv3+ and the Segment Anything Model with fine-tuning, resulting in mIOU improvements of up to 23.5% over zero-shot SAM and 12.5% over Deeplabv3+ on benchmark datasets.
Delineating farmland boundaries is essential for agricultural management such as crop monitoring and agricultural census. Traditional methods using remote sensing imagery have been efficient but limited in generalisation. The Segment Anything Model (SAM), known for its impressive zero shot performance, has been adapted for remote sensing tasks through prompt learning and fine tuning. Here, we propose a SAM based farmland boundary delineation framework 'fabSAM' that combines a Deeplabv3+ based Prompter and SAM. Also, a fine tuning strategy was introduced to enable SAMs decoder to improve the use of prompt information. Experimental results on the AI4Boundaries and AI4SmallFarms datasets have shown that fabSAM has a significant improvement in farmland region identification and boundary delineation. Compared to zero shot SAM, fabSAM surpassed it by 23.5% and 15.1% in mIOU on the AI4Boundaries and AI4SmallFarms datasets, respectively. For Deeplabv3+, fabSAM outperformed it by 4.9% and 12.5% in mIOU, respectively. These results highlight the effectiveness of fabSAM, which also means that we can more easily obtain the global farmland region and boundary maps from open source satellite image datasets like Sentinel2.