LULC-SegNet: Enhancing Land Use and Land Cover Semantic Segmentation with Denoising Diffusion Feature Fusion

Deep convolutional networks often encounter information bottlenecks when extracting land object features, resulting in critical geometric information loss, which impedes semantic segmentation capabilities in complex geospatial backgrounds. We developed LULC-SegNet, a semantic segmentation network fo...

Full description

Saved in:
Bibliographic Details
Main Authors: Zongwen Shi, Junfu Fan, Yujie Du, Yuke Zhou, Yi Zhang
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/16/23/4573
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846123876785848320
author Zongwen Shi
Junfu Fan
Yujie Du
Yuke Zhou
Yi Zhang
author_facet Zongwen Shi
Junfu Fan
Yujie Du
Yuke Zhou
Yi Zhang
author_sort Zongwen Shi
collection DOAJ
description Deep convolutional networks often encounter information bottlenecks when extracting land object features, resulting in critical geometric information loss, which impedes semantic segmentation capabilities in complex geospatial backgrounds. We developed LULC-SegNet, a semantic segmentation network for land use and land cover (LULC), which integrates features from the denoising diffusion probabilistic model (DDPM). This network enhances the clarity of the edge segmentation, detail resolution, and the visualization and accuracy of the contours by delving into the spatial details of the remote sensing images. The LULC-SegNet incorporates DDPM decoder features into the LULC segmentation task, utilizing machine learning clustering algorithms and spatial attention to extract continuous DDPM semantic features. The network addresses the potential loss of spatial details during feature extraction in convolutional neural network (CNN), and the integration of the DDPM features with the CNN feature extraction network improves the accuracy of the segmentation boundaries of the geographical features. Ablation and comparison experiments conducted on the Circum-Tarim Basin Region LULC Dataset demonstrate that the LULC-SegNet improved the LULC semantic segmentation. The LULC-SegNet excels in multiple key performance indicators compared to existing advanced semantic segmentation methods. Specifically, the network achieved remarkable scores of 80.25% in the mean intersection over union (MIOU) and 93.92% in the F1 score, surpassing current technologies. The LULC-SegNet demonstrated an IOU score of 73.67%, particularly in segmenting the small-sample river class. Our method adapts to the complex geophysical characteristics of remote sensing datasets, enhancing the performance of automatic semantic segmentation tasks for land use and land cover changes and making critical advancements.
format Article
id doaj-art-f3b280e66a1b49d49dcbec626e5c2513
institution Kabale University
issn 2072-4292
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-f3b280e66a1b49d49dcbec626e5c25132024-12-13T16:31:18ZengMDPI AGRemote Sensing2072-42922024-12-011623457310.3390/rs16234573LULC-SegNet: Enhancing Land Use and Land Cover Semantic Segmentation with Denoising Diffusion Feature FusionZongwen Shi0Junfu Fan1Yujie Du2Yuke Zhou3Yi Zhang4School of Civil Engineering and Geomatics, Shandong University of Technology, Zibo 255000, ChinaSchool of Civil Engineering and Geomatics, Shandong University of Technology, Zibo 255000, ChinaSchool of Civil Engineering and Geomatics, Shandong University of Technology, Zibo 255000, ChinaState Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, ChinaCollege of Land Resources and Surveying Engineering, Shandong Agriculture and Engineering University, Zibo 255300, ChinaDeep convolutional networks often encounter information bottlenecks when extracting land object features, resulting in critical geometric information loss, which impedes semantic segmentation capabilities in complex geospatial backgrounds. We developed LULC-SegNet, a semantic segmentation network for land use and land cover (LULC), which integrates features from the denoising diffusion probabilistic model (DDPM). This network enhances the clarity of the edge segmentation, detail resolution, and the visualization and accuracy of the contours by delving into the spatial details of the remote sensing images. The LULC-SegNet incorporates DDPM decoder features into the LULC segmentation task, utilizing machine learning clustering algorithms and spatial attention to extract continuous DDPM semantic features. The network addresses the potential loss of spatial details during feature extraction in convolutional neural network (CNN), and the integration of the DDPM features with the CNN feature extraction network improves the accuracy of the segmentation boundaries of the geographical features. Ablation and comparison experiments conducted on the Circum-Tarim Basin Region LULC Dataset demonstrate that the LULC-SegNet improved the LULC semantic segmentation. The LULC-SegNet excels in multiple key performance indicators compared to existing advanced semantic segmentation methods. Specifically, the network achieved remarkable scores of 80.25% in the mean intersection over union (MIOU) and 93.92% in the F1 score, surpassing current technologies. The LULC-SegNet demonstrated an IOU score of 73.67%, particularly in segmenting the small-sample river class. Our method adapts to the complex geophysical characteristics of remote sensing datasets, enhancing the performance of automatic semantic segmentation tasks for land use and land cover changes and making critical advancements.https://www.mdpi.com/2072-4292/16/23/4573land use and land coversemantic segmentationremote sensing imagesdenoising diffusion probabilistic modelfeature fusionK-means clustering algorithms
spellingShingle Zongwen Shi
Junfu Fan
Yujie Du
Yuke Zhou
Yi Zhang
LULC-SegNet: Enhancing Land Use and Land Cover Semantic Segmentation with Denoising Diffusion Feature Fusion
Remote Sensing
land use and land cover
semantic segmentation
remote sensing images
denoising diffusion probabilistic model
feature fusion
K-means clustering algorithms
title LULC-SegNet: Enhancing Land Use and Land Cover Semantic Segmentation with Denoising Diffusion Feature Fusion
title_full LULC-SegNet: Enhancing Land Use and Land Cover Semantic Segmentation with Denoising Diffusion Feature Fusion
title_fullStr LULC-SegNet: Enhancing Land Use and Land Cover Semantic Segmentation with Denoising Diffusion Feature Fusion
title_full_unstemmed LULC-SegNet: Enhancing Land Use and Land Cover Semantic Segmentation with Denoising Diffusion Feature Fusion
title_short LULC-SegNet: Enhancing Land Use and Land Cover Semantic Segmentation with Denoising Diffusion Feature Fusion
title_sort lulc segnet enhancing land use and land cover semantic segmentation with denoising diffusion feature fusion
topic land use and land cover
semantic segmentation
remote sensing images
denoising diffusion probabilistic model
feature fusion
K-means clustering algorithms
url https://www.mdpi.com/2072-4292/16/23/4573
work_keys_str_mv AT zongwenshi lulcsegnetenhancinglanduseandlandcoversemanticsegmentationwithdenoisingdiffusionfeaturefusion
AT junfufan lulcsegnetenhancinglanduseandlandcoversemanticsegmentationwithdenoisingdiffusionfeaturefusion
AT yujiedu lulcsegnetenhancinglanduseandlandcoversemanticsegmentationwithdenoisingdiffusionfeaturefusion
AT yukezhou lulcsegnetenhancinglanduseandlandcoversemanticsegmentationwithdenoisingdiffusionfeaturefusion
AT yizhang lulcsegnetenhancinglanduseandlandcoversemanticsegmentationwithdenoisingdiffusionfeaturefusion