南方农业学报2025，Vol.56Issue(1)：18-28,11.DOI:10.3969/j.issn.2095-1191.2025.01.002
基于SAM2多任务学习的山区地块模糊边界提取
SAM2-based multi-task learning for fuzzy land parcel boundary extraction in mountainous areas
摘要
Abstract
[Objective]The multi-task deep learning model of fuzzy boundary extraction was constructed to solve the problems of difficult extraction of fuzzy boundary and difficult elimination of pseudo-boundary,which could provide re-ference for the extraction of land parcel block boundary in areas with the broken land parcels.[Method]Taking Yizhou District,Hechi City,Guangxi as the research area,by interpreting the broken remote sensing image of a typical mountain area,the fuzzy boundary extraction data set was established,the SAM2 visual large model was introduced and the en-coder was fine-optimized by using the Adapter,the auxiliary task of land attribute extraction was designed,and the multi-task fuzzy boundary extraction deep learning model SAM2Xi was constructed.The results showed that the model was ef-fective in extracting fuzzy boundary in mountainous area with broken land parcels.[Result]The SAM2Xi model per-formed the best on the global best threshold(ODS)and single graph best threshold(OIS),which were 0.663 and 0.672 respectively,showing the highest edge detection accuracy and adaptability,but 50% accuracy recall(R50)were slightly lower than the DexiNed model.The SAM2Xi model combined semantic information and edge features to enhance the fuzzy boundary recognition ability,especially in complex scenes.SAM2Xi model still maintained high precision under low contrast and complex background,and the detail retention,coherence and noise suppression of fuzzy boundary re-gion were better than other models.In addition,the SAM2Xi model performed the best in the pseudo-boundary clearing task,and its advanced feature extraction and optimization mechanism almost completely eliminated pseudo-boundary in-terference,maintaining high-precision edge detection in various scenarios,with higher robustness and accuracy.The SAM2Xi model could successfully extract the land parcel information of the study area(the total number of land parcel spots was 1587597,and the total area was 145696.646 ha),and the extracted land parcel distribution was highly consis-tent with the actual situation,which was shown as follows:(1)it could accurately divide various land parcels within a large area of cultivated land;(2)a few pieces of cultivated land or garden could be extracted from the building;(3)it could extract the land parcels of forest land that could be divided separately(artificial forests),but natural forests would not be misidentified.[Conclusion]The SAM2Xi model based on SAM2 multi-task learning realizes the double break-through of fuzzy boundary recognition and pseudo-boundary elimination,and has obvious advantages in complex terrain adaptability,boundary continuity maintenance and noise suppression,providing technical support for land parcel bounda-ry extraction and precise management of agricultural resources in mountainous areas of southwestern China under com-plex terrain.关键词
地块边界提取/SAM2/多任务学习/遥感影像/SAM2Xi模型Key words
land parcel boundary extraction/SAM2/multi-task learning/remote sensing images/SAM2Xi model分类
农业科技引用本文复制引用
黄启厅,凌玉荣,谢国雪,杨绍锷,杨颖频,李海亮,梁存穗,何新洁,谢意..基于SAM2多任务学习的山区地块模糊边界提取[J].南方农业学报,2025,56(1):18-28,11.基金项目
国家自然科学基金项目(42201413) （42201413）
广西重点研发计划项目(桂科AB24153001) （桂科AB24153001）
海南省热带作物信息技术应用研究重点实验室开放基金项目(ZDSYS-KFJJ-202308) （ZDSYS-KFJJ-202308）
广西农业科学院科技发展基金项目(桂农科2017ZX04) National Natural Science Foundation of China(42201413) （桂农科2017ZX04）
Guangxi Key Research and Develop-ment Plan Project(Guike AB24153001) （Guike AB24153001）
Open Project of Key Laboratory of Applied Research on Tropical Crop Informa-tion Technology of Hainan(ZDSYS-KFJJ-202308) （ZDSYS-KFJJ-202308）
Science and Technology Development Project of Guangxi Academy of Agricultural Sciences(Guinongke 2017ZX04) （Guinongke 2017ZX04）
