1.江西省自然资源事业发展中心,江西 南昌 330025
2.南昌大学 先进制造学院,江西 南昌 330031
徐世亮(1981—),男,硕士,正高级工程师,从事计算机软件技术、网络与信息安全的研究,E-mail: vigor2005@163.com.
刘继忠(1974—),男,博士,教授,博士生导师,主要从事智能机电系统与机器人、机器视觉与图像处理的研究,E-mail: liujizhong@ncu.edu.cn.
收稿:2025-07-07,
修回:2026-01-09,
录用:2026-01-14,
纸质出版:2026-03-25
移动端阅览
徐世亮,赖民权,刘继忠.基于改进BIT的耕地变化检测算法[J].新疆大学学报(自然科学版中英文),2026,43(2):144-155.
Xu Shiliang,Lai Minquan,Liu Jizhong.Farmland change detection algorithm based on improved BIT[J].Journal of Xinjiang University(Natural Science Edition in Chinese and English),2026,43(2):144-155.
徐世亮,赖民权,刘继忠.基于改进BIT的耕地变化检测算法[J].新疆大学学报(自然科学版中英文),2026,43(2):144-155. DOI: 10.13568/j.cnki.651094.651316.2025.07.07.0004.
Xu Shiliang,Lai Minquan,Liu Jizhong.Farmland change detection algorithm based on improved BIT[J].Journal of Xinjiang University(Natural Science Edition in Chinese and English),2026,43(2):144-155. DOI: 10.13568/j.cnki.651094.651316.2025.07.07.0004.
耕地“非农化”严重威胁全球粮食安全与生态稳定.遥感变化检测技术因具有大范围动态监测优势,已成为识别耕地“非农化”过程的核心手段.然而,现有方法在处理复杂耕地场景时,受限于多尺度特征表征能力,难以在提取破碎耕地边缘细节的同时兼顾大范围地块的全局语义一致性,从而导致边缘模糊与局部特征丢失.针对上述问题,本文提出一种基于改进双时相图像Transformer(Bitemporal Image Transformer,BIT)的耕地变化检测算法Far-CDNet.首先,引入并联普通卷积及多种差分卷积的细节增强卷积模块,并通过动态加权和残差连接强化特征提取网络的边缘细节表征能力.其次,将BIT模块中语义标记器的普通卷积替换为深度可分离卷积,以增强局部特征捕获能力并生成具有更高层语义的输出特征.最后,增加一条残差分支,进一步融合Transformer前后的局部及全局信息.实验结果表明,改进后的模型
F
1分数为79.18%,
IoU
为69.32%,相较于BIT模型,
F
1分数提升4.17%,
IoU
提升4.24%.
Farmland non-agriculturalization is a serious threat to global food security and ecological stability. Remote sensing change detection technology has become a core tool for identifying the process of farmland non-agriculturalization by virtue of its advantage of
large-scale dynamic monitoring. However
existing methods face challenges in balancing the extraction of fine edge details in fragmented farmland with the maintenance of global semantic consistency in large-scale fields
often resulting in blurred edges and lost local features. To address these issues
a farmland change detection algorithm based on improved BIT
named Far-CDNet
is proposed. Firstly
a detail enhancement convolution module that connects ordinary convolution and multiple differential convolutions in parallel is introduced
and the edge detail representation capability of the feature extraction network is enhanced through dynamic weighting and residual connection. Secondly
the ordinary convolution of the semantic tokenizer in the BIT module is replaced by a deep separable convolution to enhance the local feature capture ability and generate output features with higher-level semantics
so as to improve the overall feature expression ability of the model. Finally
a residual branch is added to further integrate the local and global information before and after the Transformer. The experimental results show that the improved model
F
1 score is 79.18%
and
IoU
is 69.32%. Compared with the BIT model
the
F
1 score is increased by 4.17%
and
IoU
is increased by 4.24%.
关洁琳 . 国内外耕地非农化研究进展及展望 [J]. 南方农机 , 2023 , 54 ( 22 ): 42 - 45 .
Guan J L . Research progress and prospect of non-agriculturalization of arable land at home and abroad [J]. China Southern Agricultural Machinery , 2023 , 54 ( 22 ): 42 - 45 . (in Chinese)
汪杰 , 孙孝林 , 伍丹华 , 等 . 高密度植被覆盖区基于无人机高光谱数据的农田土壤有机质反演 [J]. 光谱学与光谱分析 , 2025 , 45 ( 10 ): 2885 - 2896 .
Wang J , Sun X L , Wu D H , et al . Prediction of soil organic matter for farmlands covered with high density of vegetation based on UAV hyperspectral data [J]. Spectroscopy and Spectral Analysis , 2025 , 45 ( 10 ): 2885 - 2896 . (in Chinese)
李林源 , 黄华国 , 穆西晗 , 等 . 低空无人机植被定量遥感:进展、挑战与展望 [J]. 遥感学报 , 2025 , 29 ( 6 ): 2083 - 2113 .
Li L Y , Huang H G , Mu X H , et al . Low-altitude UAV-based quantitative remote sensing of vegetation:Advances,challenges,and prospects [J]. National Remote Sensing Bulletin , 2025 , 29 ( 6 ): 2083 - 2113 . (in Chinese)
习文强 , 杜世宏 , 杜守基 . 多时相耕地覆盖提取和变化分析:一种结合遥感和空间统计的时空上下文方法 [J]. 地球信息科学学报 , 2022 , 24 ( 2 ): 310 - 325 .
Xi W Q , Du S H , Du S J . Multi-temporal cropland cover extraction and change analysis:A spatio-temporal contextual approach combining remote sensing and spatial statistics [J]. Journal of Geo-information Science , 2022 , 24 ( 2 ): 310 - 325 . (in Chinese)
Marpu P , Gamba P , Benediktsson J A . Hyperspectral change detection using IR-MAD and feature reduction [C]// 2011 IEEE International Geoscience and Remote Sensing Symposium , July 24-29,2011 , Vancouver,BC,Canada.New York : IEEE , 2011 : 98 - 101 .
Singh S , Talwar R . Review on different change vector analysis algorithms based change detection techniques [C]// 2013 IEEE Second International Conference on Image Information Processing (ICIIP-2013) , December 9-11,2013 , Shimla,India.New York : IEEE , 2013 : 136 - 141 .
Li P J , Cheng T , Moser G , et al . Multitemporal change detection by spectral and multivariate texture information [C]// 2007 IEEE International Geoscience and Remote Sensing Symposium , July 23-28,2007 , Barcelona,Spain.New York : IEEE , 2007 : 1922 - 1925 .
Bai T , Sun K M , Deng S Q , et al . Comparison of four machine learning methods for object-oriented change detection in high-resolution satellite imagery [C]// MIPPR 2017:Remote Sensing Image Processing,Geographic Information Systems,and Other Applications , October 28-29,2017 , Xiangyang, Hubei, China.New York : SPIE , 2018 : 99 - 106 .
Devries B , Decuyper M , Verbesselt J , et al . Tracking disturbance-regrowth dynamics in tropical forests using structural change detection and Landsat time series [J]. Remote Sensing of Environment , 2015 , 169 : 320 - 334 .
Lyu H B , Lu H , Mou L C . Learning a transferable change rule from a recurrent neural network for land cover change detection [J]. Remote Sensing , 2016 , 8 ( 6 ): 506 - 528 .
Wang Q , Zhang X D , Chen G Z , et al . Change detection based on Faster R-CNN for high-resolution remote sensing images [J]. Remote Sensing Letters , 2018 , 9 ( 10 ): 923 - 932 .
詹必伟 , 唐小丽 , 何奕萱 , 等 . 基于改进U-Net网络的耕地变化检测方法研究 [J]. 测绘 , 2023 , 46 ( 2 ): 76 - 79 .
Zhan B W , Tang X L , He Y X , et al . Research of farmland change detection technology based on improvement U-Net [J]. Surveying and Mapping , 2023 , 46 ( 2 ): 76 - 79 . (in Chinese)
Chen H , Qi Z P , Shi Z W . Remote sensing image change detection with transformers [J]. IEEE Transactions on Geoscience and Remote Sensing , 2021 , 60 : 1 - 14 .
Daudt R C , LE Saus B , Boulch A . Fully convolutional Siamese networks for change detection [C]// 2018 25th International Conference on Image Processing , October 7-10,2018 , Athens, Greece.New York : IEEE , 2018 : 4063 - 4067 .
Fang S , Li K Y , Shao J Y , et al . SNUNet-CD:A densely connected Siamese network for change detection of VHR images [J]. Geoscience and Remote Sensing Letters , 2021 , 19 : 1 - 5 .
Zhang C , Wang L J , Cheng S L , et al . SwinSUNet:Pure transformer network for remote sensing image change detection [J]. IEEE Transactions on Geoscience and Remote Sensing , 2022 , 60 : 1 - 13 .
Bandara W G C , Patel V M . A transformer-based Siamese network for change detection [C]// IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium , July 17-22,2022 , Kuala Lumpur,Malaysia . New York : IEEE , 2022 : 207 - 210 .
Han C X , Wu C , Guo H N , et al . Change guiding network:Incorporating change prior to guide change detection in remote sen‑sing imagery [J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 2023 , 16 : 8395 - 8407 .
0
浏览量
3
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621
