数字农科院2.0

Achieving precise cropland parcel extraction from remote sensing images through integration of segment anything model and adaptive mask refinement

文献类型： 外文期刊

作者： Li, Huibin;Zhu, Jianyu;Mao, Xing;Hao, Xueli;Li, Shiyao;Yu, Qiangyi;Shi, Yun;Qian, Jianping

作者机构：

关键词： Cropland;Segment anything model;Remote sensing;Prompt point;Low-supervision

期刊名称： COMPUTERS AND ELECTRONICS IN AGRICULTURE

ISSN： 0168-1699

年卷期： 2025 年 243 卷

页码：

收录情况： SCIE（2025版） ; ; EI（2025版）

摘要： The efficient extraction of cropland parcels from satellite imagery is of crucial importance for modern agricultural management. The advent of the Segment Anything Model (SAM) presents the potential to reduce the need for annotations and complex training in the context of cropland extraction. However, SAM faces challenges in handling diverse and heterogeneous cropland types. To address these issues, this study proposes a novel, unsupervised methodology that integrates SAM with an adaptive mask refinement strategy, enabling accurate cropland extraction under minimal supervision. The refinement strategy comprises three key components: (1) an adaptive prompt point module that leverages superpixels to dynamically generate optimised prompt points, (2) an overlap filtering module to eliminate redundant cropland parcels and (3) a boundary-matching stitching module to maintain spatial continuity across image tiles. The efficacy of the method was evaluated using diverse satellite images (similar to 160 km(2)) from seven representative regions in China, the United States, and South Africa. Ablation experiment results showed that the proposed approach achieved notable improvements over the baseline SAM, with increases in recall (R), Intersection over Union (IoU) and global total classification errors (GTC) of 0.971, 0.908 and 0.124, respectively. Furthermore, it outperformed five contemporary state-of-the-art methods, achieving a precision (P) of 0.960. The method also generalised well across different cropland configurations, ranging from large, regular parcels (e.g. Xinjiang, Illinois) to fragmented landscapes (e.g. Guangdong, Western Cape). Seasonal analysis confirmed that images captured during the sowing period yielded the highest extraction accuracy. These findings highlight the potential of SAM-based approaches for scalable and accurate cropland parcel mapping in complex agricultural landscapes under low-supervision settings.

分类号：

  • 相关文献

[1]Evaluation of Ecosystem Water Use Efficiency Based on Coupled and Uncoupled Remote Sensing Products for Maize and Soybean. Lingxiao Huang,Meng Liu,Na Yao. 2023

[2]EMSAM: enhanced multi-scale segment anything model for leaf disease segmentation. Junlong Li,Quan Feng,Jianhua Zhang,Sen Yang. 2025

[3]Transfer Learning in Junction With a Light Use Efficiency Model for Estimating Grassland Gross Primary Production. Yu, Ruiyang,Yao, Yunjun,Tang, Qingxin,Zhang, Xueyi,Shao, Changliang,Fisher, Joshua B.,Chen, Jiquan,Zhang, Xiaotong,Li, Yufu,Xu, Jia,Liu, Lu,Xie, Zijing,Ning, Jing,Fan, Jiahui,Zhang, Luna. 2025

[4]Modeling Soil Organic Carbon Storage and Its Dynamics in Croplands of China. Tang Hua-jun,Qiu Jian-jun,Wang Li-gang,Li Hu,Li Chang-sheng,van Ranst, Eric. 2010

[5]Study on the Lambertian property of cropland in thermal infrared region through field experiments. Tu, Lili,Geng, Jun,Yang, Lechan,Qin, Zhihao,Li, Wenjuan. 2016

[6]Relationship between soil inorganic carbon and organic carbon in the wheat-maize cropland of the North China Plain. Shi, H. J.,Wang, X. J.,Li, D. W.,Guo, Y.,Zhao, Y. J.,Xu, M. G..

[7]Factors controlling regional grain yield in China over the last 20 years. Wang, Xiaobin,Cai, Dianxiong,Grant, Cynthia,Hoogmoed, Willem B.,Oenema, Oene.

[8]Management opportunities to mitigate greenhouse gas emissions from Chinese agriculture. Nayak, Dali,Smith, Pete,Saetnan, Eli,Newbold, Jamie,Cheng, Kun,Cheng, Yan-Fen,Zhu, Wei Yun,Pan, Genxing,Wang, Wen,Wang, Wen,Koslowski, Frank,Moran, Dominic,Wang, Jia-Kun,Liu, Jian-Xin,Yan, Xiaoyuan,Cardenas, Laura,Lui, Yuelai.

[9]Higher nitrates, P and lower pH in soils under medicinal plants versus crop plants. Du, Lianfeng,Zhao, Jiaojiao,Liu, Wenke,Abbas, Farhat.

[10]Global-scale modelling of future changes in sown areas of major crops. Wu, Wenbin,Shibasaki, Ryosuke,Yang, Peng,Tan, Guoxin,Matsumura, Kan-ichiro,Sugimoto, Kenji.

[11]Mapping global cropland and field size. Fritz, Steffen,See, Linda,McCallum, Ian,Bun, Andriy,Moltchanova, Elena,Duerauer, Martina,Perger, Christoph,Havlik, Petr,Mosnier, Aline,Schepaschenko, Dmitry,van der Velde, Marijn,Dunwoody, Antonia,Kraxner, Florian,Obersteiner, Michael,You, Liangzhi,You, Liangzhi,Wood-Sichra, Ulrike,Moltchanova, Elena,Albrecht, Fransizka,Albrecht, Fransizka,Schill, Christian,Thornton, Philip,Herrero, Mario,Becker-Reshef, Inbal,Justice, Chris,Hansen, Matthew,Gong, Peng,Aziz, Sheta Abdel,Cipriani, Anna,Cipriani, Anna,Malanding, Jaiteh,Cumani, Renato,Conchedda, Giulia,Cecchi, Giuliano,Ferreira, Stefanus,Gomez, Adriana,Haffani, Myriam,Kayitakire, Francois,Vancutsem, Christelle,Mueller, Rick,Newby, Terence,Nonguierma, Andre,Olusegun, Adeaga,Ortner, Simone,Rajak, D. Ram,Rocha, Jansle,Schepaschenko, Maria,Terekhov, Alexey,Tiangwa, Alex,Vintrou, Elodie,Wu Wenbin.

[12]Fertilization enhancing carbon sequestration as carbonate in arid cropland: assessments of long-term experiments in northern China. Wang, X. J.,Wang, J. P.,Wang, X. J.,Wang, X. J.,Xu, M. G.,Zhang, W. J.,Wang, J. P.,Yang, X. Y.,Huang, S. M.,Liu, H..

[13]Estimations of soil organic carbon storage in cropland of China based on DNDC model. Tang, Huajun,Qiu, Jianjun,Van Ranst, Eric,Li, Changsheng. 2006

[14]Improved global cropland data as an essential ingredient for food security. See, Linda,Fritz, Steffen,van der Velde, Marijn,McCallum, Ian,Kraxner, Florian,Obersteiner, Michael,You, Liangzhi,Ramankutty, Navin,Herrero, Mario,Justice, Chris,Becker-Reshef, Inbal,Thornton, Philip,Ericksen, Polly,Erb, Karlheinz,Erb, Karlheinz,Gong, Peng,Gong, Peng,You, Liangzhi,Tang, Huajun. 2015

[15]Global Cropping Intensity Gaps: Increasing F.ood Production Without Cropland E xpansion. Wu, WB, Yu, QY, You, LZ, Chen, K, Tang, HJ, Liu, JG. 2018

[16]Shallow groundwater fluctuation: An ignored soil N loss pathway from cropland. Anqiang Chen,Dan Zhang,Hongyuan Wang,Rongyang Cui,Benyamin Khoshnevisan,Shufang Guo,Panlei Wang,Hongbin Liu. 2022

[17]Changes In Regional Grain Yield R.esponses To Chemical Fertilizer U se In China Over The Last 20 Years. Wang, XB, Cai, DX, Grant, C, Hoogmoed, WB, Oenema, O. 2018

[18]Four pathways towards carbon neutrality by controlling net greenhouse gas emissions in Chinese cropland. Bin Wang,Andong Cai,Yu'e Li,Xiaobo Qin,Andreas Wilkes,Panlei Wang,Shuo Liu,Xiaoquan Zhang,Nan Zeng. 2022

[19]Generating Salt-Affected Irrigated Cropland Map in an Arid and Semi-Arid Region Using Multi-Sensor Remote Sensing Data. Deji Wuyun,Junwei Bao,Luís Guilherme Teixeira Crusiol,Tuya Wulan,Liang Sun,Shangrong Wu,Qingqiang Xin,Zheng Sun,Ruiqing Chen,Jingyu Peng,Hongtao Xu,Nitu Wu,Anhong Hou,Lan Wu,Tingting Ren. 2022

[20]Soil organic carbon changes in China's croplands: A newly estimation based on DNDC model. Wuhan Ding,Naijie Chang,Guilong Zhang,Jiahao Kang,Xiaopei Yi,Jing Zhang,Jianfeng Zhang,Ligang Wang,Hu Li. 2023

作者其他论文 更多>>