Toward Sustainable Agriculture: DPA-UNet for Semantic Segmentation of Landscapes Using Remote Sensing Imagery

Particularly in agricultural contexts where exact delineation of land cover types is vital for resource management and planning, semantic segmentation is a key technique for high-resolution image interpretation. Although U-Net-based designs have shown significant success in Land Use and Land Cover (...

Full description

Saved in:
Bibliographic Details
Main Authors: J. Kavipriya, G. Vadivu
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11113314/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849770772940193792
author J. Kavipriya
G. Vadivu
author_facet J. Kavipriya
G. Vadivu
author_sort J. Kavipriya
collection DOAJ
description Particularly in agricultural contexts where exact delineation of land cover types is vital for resource management and planning, semantic segmentation is a key technique for high-resolution image interpretation. Although U-Net-based designs have shown significant success in Land Use and Land Cover (LULC) identification, they sometimes struggle when segmenting classes with comparable spectral, textural, and intensity traits. Moreover, generating large-scale ground truth across wide agricultural areas is still time consuming and labor intensive, which greatly limits the creation of scalable segmentation solutions. This work presents a new architecture called Deep Pro Agri-UNet (DPA-UNet) meant specifically for agricultural field segmentation with high-resolution images sourced from Google Earth Pro in order to solve these problems. DPA-UNet improves the model’s ability to extract discriminative features and properly separate spectrally similar land classes by means of a multi-branch spatial and channel attention mechanism at the model’s bottleneck layer. A Dice loss function is included into the training goal to offset the consequences of class imbalance common in agricultural datasets. Attention gates are also included into the decoder path to selectively hone feature maps from the encoder to emphasize spatially relevant areas during the upsampling process. Experimental results show that DPA-UNet significantly outperforms traditional U-Net models, with an 81.8% total accuracy and an 82.8% Intersection over Union (IoU). While keeping a lower computational load, the proposed model efficiently lowers segmentation mistakes in heterogeneous agricultural areas. The findings confirm that DPA-UNet provides a scalable, precise, and computationally efficient solution for large scale agricultural monitoring, therefore supporting applications in sustainable land management, informed policy decision making, and precision farming.
format Article
id doaj-art-d84e7fcab3c34addb9f1621c2055eda1
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-d84e7fcab3c34addb9f1621c2055eda12025-08-20T03:02:53ZengIEEEIEEE Access2169-35362025-01-011313840013841410.1109/ACCESS.2025.359583611113314Toward Sustainable Agriculture: DPA-UNet for Semantic Segmentation of Landscapes Using Remote Sensing ImageryJ. Kavipriya0https://orcid.org/0009-0000-0612-1362G. Vadivu1https://orcid.org/0000-0003-2982-4145Department of Data Science and Business Systems, School of Computing, SRM Institute of Science and Technology, Chengalpattu, Kattankulathur, IndiaDepartment of Data Science and Business Systems, School of Computing, SRM Institute of Science and Technology, Chengalpattu, Kattankulathur, IndiaParticularly in agricultural contexts where exact delineation of land cover types is vital for resource management and planning, semantic segmentation is a key technique for high-resolution image interpretation. Although U-Net-based designs have shown significant success in Land Use and Land Cover (LULC) identification, they sometimes struggle when segmenting classes with comparable spectral, textural, and intensity traits. Moreover, generating large-scale ground truth across wide agricultural areas is still time consuming and labor intensive, which greatly limits the creation of scalable segmentation solutions. This work presents a new architecture called Deep Pro Agri-UNet (DPA-UNet) meant specifically for agricultural field segmentation with high-resolution images sourced from Google Earth Pro in order to solve these problems. DPA-UNet improves the model’s ability to extract discriminative features and properly separate spectrally similar land classes by means of a multi-branch spatial and channel attention mechanism at the model’s bottleneck layer. A Dice loss function is included into the training goal to offset the consequences of class imbalance common in agricultural datasets. Attention gates are also included into the decoder path to selectively hone feature maps from the encoder to emphasize spatially relevant areas during the upsampling process. Experimental results show that DPA-UNet significantly outperforms traditional U-Net models, with an 81.8% total accuracy and an 82.8% Intersection over Union (IoU). While keeping a lower computational load, the proposed model efficiently lowers segmentation mistakes in heterogeneous agricultural areas. The findings confirm that DPA-UNet provides a scalable, precise, and computationally efficient solution for large scale agricultural monitoring, therefore supporting applications in sustainable land management, informed policy decision making, and precision farming.https://ieeexplore.ieee.org/document/11113314/U-Netremote sensingsemantic segmentationhigh resolution satellite imageryagriculture land
spellingShingle J. Kavipriya
G. Vadivu
Toward Sustainable Agriculture: DPA-UNet for Semantic Segmentation of Landscapes Using Remote Sensing Imagery
IEEE Access
U-Net
remote sensing
semantic segmentation
high resolution satellite imagery
agriculture land
title Toward Sustainable Agriculture: DPA-UNet for Semantic Segmentation of Landscapes Using Remote Sensing Imagery
title_full Toward Sustainable Agriculture: DPA-UNet for Semantic Segmentation of Landscapes Using Remote Sensing Imagery
title_fullStr Toward Sustainable Agriculture: DPA-UNet for Semantic Segmentation of Landscapes Using Remote Sensing Imagery
title_full_unstemmed Toward Sustainable Agriculture: DPA-UNet for Semantic Segmentation of Landscapes Using Remote Sensing Imagery
title_short Toward Sustainable Agriculture: DPA-UNet for Semantic Segmentation of Landscapes Using Remote Sensing Imagery
title_sort toward sustainable agriculture dpa unet for semantic segmentation of landscapes using remote sensing imagery
topic U-Net
remote sensing
semantic segmentation
high resolution satellite imagery
agriculture land
url https://ieeexplore.ieee.org/document/11113314/
work_keys_str_mv AT jkavipriya towardsustainableagriculturedpaunetforsemanticsegmentationoflandscapesusingremotesensingimagery
AT gvadivu towardsustainableagriculturedpaunetforsemanticsegmentationoflandscapesusingremotesensingimagery