Investigating the Segment Anything Foundation Model for Mapping Smallholder Agriculture Field Boundaries Without Training Labels
This work addresses the challenge of agricultural field mapping for smallholder farms and data-scarce settings, though it is incremental as it adapts an existing foundation model to a specific domain.
This study tackled the problem of mapping agricultural field boundaries from satellite images in data-scarce environments by applying the Segment Anything Model (SAM) without training, achieving about 58% accuracy in identifying boundaries, which is comparable to methods requiring extensive training data.
Accurate mapping of agricultural field boundaries is crucial for enhancing outcomes like precision agriculture, crop monitoring, and yield estimation. However, extracting these boundaries from satellite images is challenging, especially for smallholder farms and data-scarce environments. This study explores the Segment Anything Model (SAM) to delineate agricultural field boundaries in Bihar, India, using 2-meter resolution SkySat imagery without additional training. We evaluate SAM's performance across three model checkpoints, various input sizes, multi-date satellite images, and edge-enhanced imagery. Our results show that SAM correctly identifies about 58% of field boundaries, comparable to other approaches requiring extensive training data. Using different input image sizes improves accuracy, with the most significant improvement observed when using multi-date satellite images. This work establishes proof of concept for using SAM and maximizing its potential in agricultural field boundary mapping. Our work highlights SAM's potential in delineating agriculture field boundary in training-data scarce settings to enable a wide range of agriculture related analysis.