NIR-RGB-M<sup>2</sup>Net: A Fusion Model for Precise Agricultural Field Segmentation Using Multisource Remote Sensing Data

Precise extraction of agricultural field parcels is critical for resource management and yield prediction. Multisource remote sensing combines near-infrared (NIR) and visible light (RGB) data to leverage complementary features, but fusing these modalities often requires complex networks that risk lo...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhankui Tang, Xin Pan, Xiangfei She, Jian Zhao
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11105414/
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Precise extraction of agricultural field parcels is critical for resource management and yield prediction. Multisource remote sensing combines near-infrared (NIR) and visible light (RGB) data to leverage complementary features, but fusing these modalities often requires complex networks that risk losing vegetation signals and boundary details. To address this issue, this article proposes NIR-RGB-M<sup>2</sup>Net, a novel fusion model for precise agricultural field segmentation using multisource remote sensing data. The primary innovations of NIR-RGB-M<sup>2</sup>Net are as follows: A U&#x2013;Net&#x2013;based fusion model that integrates a convolutional block attention module in the NIR branch to highlight vegetation-related channels and spatial regions, and a dilated convolution module in the RGB branch to expand the receptive field without sacrificing resolution, capturing fine boundary textures. This dual&#x2013;path design enables simultaneous extraction of deep vegetation cues and precise object contours. Evaluated on the high-resolution cropland nonagriculturalization dataset and Belgium dataset, the accuracy rate, pixel precision, IoU, and F1 scores of the proposed model were 94.54%, 93.53%, 89.65%, and 94.54%, as well as 86.35%, 82.46%, 73.58%, and 84.78%, respectively. This method provides a comprehensive and accurate solution for precise farmland extraction, offering significant implications for agricultural resource management, crop yield prediction, and sustainable agricultural practices.
ISSN:1939-1404
2151-1535