DDAM-Net: A Difference-Directed Multi-Scale Attention Mechanism Network for Cultivated Land Change Detection

Declining cultivated land poses a serious threat to food security. However, existing Change Detection (CD) methods are insufficient for overcoming intra-class differences in cropland, and the accumulation of irrelevant features and loss of key features leads to poor detection results. To effectively...

Full description

Saved in:
Bibliographic Details
Main Authors: Junbiao Feng, Haikun Yu, Xiaoping Lu, Xiaoran Lv, Junli Zhou
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/21/7040
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850193450680451072
author Junbiao Feng
Haikun Yu
Xiaoping Lu
Xiaoran Lv
Junli Zhou
author_facet Junbiao Feng
Haikun Yu
Xiaoping Lu
Xiaoran Lv
Junli Zhou
author_sort Junbiao Feng
collection DOAJ
description Declining cultivated land poses a serious threat to food security. However, existing Change Detection (CD) methods are insufficient for overcoming intra-class differences in cropland, and the accumulation of irrelevant features and loss of key features leads to poor detection results. To effectively identify changes in agricultural land, we propose a Difference-Directed Multi-scale Attention Mechanism Network (DDAM-Net). Specifically, we use a feature extraction module to effectively extract the cropland’s multi-scale features from dual-temporal images, and we introduce a Difference Enhancement Fusion Module (DEFM) and a Cross-scale Aggregation Module (CAM) to pass and fuse the multi-scale and difference features layer by layer. In addition, we introduce the Attention Refinement Module (ARM) to optimize the edge and detail features of changing objects. In the experiments, we evaluated the applicability of DDAM-Net on the HN-CLCD dataset for cropland CD and non-agricultural identification, with F1 and precision of 79.27% and 80.70%, respectively. In addition, generalization experiments using the publicly accessible PX-CLCD and SET-CLCD datasets revealed F1 and precision values of 95.12% and 95.47%, and 72.40% and 77.59%, respectively. The relevant comparative and ablation experiments suggested that DDAM-Net has greater performance and reliability in detecting cropland changes.
format Article
id doaj-art-61bb11203afb40efb46fb2baac81e1c5
institution OA Journals
issn 1424-8220
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-61bb11203afb40efb46fb2baac81e1c52025-08-20T02:14:16ZengMDPI AGSensors1424-82202024-10-012421704010.3390/s24217040DDAM-Net: A Difference-Directed Multi-Scale Attention Mechanism Network for Cultivated Land Change DetectionJunbiao Feng0Haikun Yu1Xiaoping Lu2Xiaoran Lv3Junli Zhou4Key Laboratory of Spatio-Temporal Information and Ecological Restoration of Mines of Natural Resources of the People’s Republic of China, Henan Polytechnic University, Jiaozuo 454003, ChinaHenan Remote Sensing and Mapping Institute, Zhengzhou 450003, ChinaKey Laboratory of Spatio-Temporal Information and Ecological Restoration of Mines of Natural Resources of the People’s Republic of China, Henan Polytechnic University, Jiaozuo 454003, ChinaKey Laboratory of Spatio-Temporal Information and Ecological Restoration of Mines of Natural Resources of the People’s Republic of China, Henan Polytechnic University, Jiaozuo 454003, ChinaHenan Remote Sensing and Mapping Institute, Zhengzhou 450003, ChinaDeclining cultivated land poses a serious threat to food security. However, existing Change Detection (CD) methods are insufficient for overcoming intra-class differences in cropland, and the accumulation of irrelevant features and loss of key features leads to poor detection results. To effectively identify changes in agricultural land, we propose a Difference-Directed Multi-scale Attention Mechanism Network (DDAM-Net). Specifically, we use a feature extraction module to effectively extract the cropland’s multi-scale features from dual-temporal images, and we introduce a Difference Enhancement Fusion Module (DEFM) and a Cross-scale Aggregation Module (CAM) to pass and fuse the multi-scale and difference features layer by layer. In addition, we introduce the Attention Refinement Module (ARM) to optimize the edge and detail features of changing objects. In the experiments, we evaluated the applicability of DDAM-Net on the HN-CLCD dataset for cropland CD and non-agricultural identification, with F1 and precision of 79.27% and 80.70%, respectively. In addition, generalization experiments using the publicly accessible PX-CLCD and SET-CLCD datasets revealed F1 and precision values of 95.12% and 95.47%, and 72.40% and 77.59%, respectively. The relevant comparative and ablation experiments suggested that DDAM-Net has greater performance and reliability in detecting cropland changes.https://www.mdpi.com/1424-8220/24/21/7040non-agricultural changehigh-resolution remote-sensing imagesattention mechanismchange detectionself-built dataset
spellingShingle Junbiao Feng
Haikun Yu
Xiaoping Lu
Xiaoran Lv
Junli Zhou
DDAM-Net: A Difference-Directed Multi-Scale Attention Mechanism Network for Cultivated Land Change Detection
Sensors
non-agricultural change
high-resolution remote-sensing images
attention mechanism
change detection
self-built dataset
title DDAM-Net: A Difference-Directed Multi-Scale Attention Mechanism Network for Cultivated Land Change Detection
title_full DDAM-Net: A Difference-Directed Multi-Scale Attention Mechanism Network for Cultivated Land Change Detection
title_fullStr DDAM-Net: A Difference-Directed Multi-Scale Attention Mechanism Network for Cultivated Land Change Detection
title_full_unstemmed DDAM-Net: A Difference-Directed Multi-Scale Attention Mechanism Network for Cultivated Land Change Detection
title_short DDAM-Net: A Difference-Directed Multi-Scale Attention Mechanism Network for Cultivated Land Change Detection
title_sort ddam net a difference directed multi scale attention mechanism network for cultivated land change detection
topic non-agricultural change
high-resolution remote-sensing images
attention mechanism
change detection
self-built dataset
url https://www.mdpi.com/1424-8220/24/21/7040
work_keys_str_mv AT junbiaofeng ddamnetadifferencedirectedmultiscaleattentionmechanismnetworkforcultivatedlandchangedetection
AT haikunyu ddamnetadifferencedirectedmultiscaleattentionmechanismnetworkforcultivatedlandchangedetection
AT xiaopinglu ddamnetadifferencedirectedmultiscaleattentionmechanismnetworkforcultivatedlandchangedetection
AT xiaoranlv ddamnetadifferencedirectedmultiscaleattentionmechanismnetworkforcultivatedlandchangedetection
AT junlizhou ddamnetadifferencedirectedmultiscaleattentionmechanismnetworkforcultivatedlandchangedetection