Extraction of Cropland Based on Multi-Source Remote Sensing and an Improved Version of the Deep Learning-Based Segment Anything Model (SAM)

Fine extraction of cropland parcels is an essential prerequisite for achieving precision agriculture. Remote sensing technology, due to its large-scale and multi-dimensional characteristics, can effectively enhance the efficiency of collecting information on agricultural land parcels. Currently, sem...

Full description

Saved in:
Bibliographic Details
Main Authors: Kunjian Tao, He Li, Chong Huang, Qingsheng Liu, Junyan Zhang, Ruoqi Du
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Agronomy
Subjects:
Online Access:https://www.mdpi.com/2073-4395/15/5/1139
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Fine extraction of cropland parcels is an essential prerequisite for achieving precision agriculture. Remote sensing technology, due to its large-scale and multi-dimensional characteristics, can effectively enhance the efficiency of collecting information on agricultural land parcels. Currently, semantic segmentation models based on high-resolution remote sensing imagery utilize limited spectral information and rely heavily on a large amount of fine data annotation, while pixel classification models based on medium-to-low-resolution multi-temporal remote sensing imagery are limited by the mixed pixel problem. To address this, the study utilizes GF-2 high-resolution imagery and Sentinel-2 multi-temporal data, in conjunction with the basic image segmentation model SAM, by additionally introducing a prompt generation module (Box module and Auto module) to achieve automatic fine extraction of cropland parcels. The research results indicate the following: (1) The <i>mIoU</i> of SAM with the Box module is 0.711, and the <i>OA</i> is 0.831, showing better performance, while the <i>mIoU</i> of SAM with the Auto module is 0.679, and the <i>OA</i> is 0.81, yielding higher-quality cropland masks; (2) The combination of various prompts (box, point, and mask), along with the hierarchical extraction strategy, can effectively improve the performance of Box module SAM; (3) Employing a more accurate prompt data source can significantly boost model performance. The <i>mIoU</i> of the superior-performing Box module SAM is increased to 0.920, and the <i>OA</i> is raised to 0.958. Overall, the improved SAM, while reducing the demand for mask annotation and model training, can achieve high-precision extraction results for cropland parcels.
ISSN:2073-4395