Improved DeepLabV3+ model for spring crops identification in Sichuan counties

doi:10.13474/j.cnki.11-2246.2025.0323

Abstract

Abstract: Traditional agricultural irrigation water resource allocation models suffer from significant inefficiencies and waste due to uneven distribution. Remote sensing technology can effectively address the issue of missing crop distribution data in irrigation planning by providing accurate spatial distribution information. This paper takes Xinjin district of Chengdu, Sichuan province as the research area. A mechanism which contains contrastive learning and feature enhancement is introduced to improve the DeepLabV3+ model, utilizing GF series satellite imagery to accurately identify both major and minor crops. The results indicate that the improved IM-DeepLabV3+ model can achieve recognition accuracies of 91.73%, 89.93%, 80.18%, and 72.08% for rapeseed, wheat, rice, and corn, respectively, which can provide scientific crop distribution data support for scientific allocation of agricultural irrigation water resources.

Key words: agricultural remote sensing, contrastive learning, deep learning, Sichuan, crop identification

CLC Number:

P237

ZHANG Xuan, YANG Benyong, WEN Wu, DENG Weixi, ZHOU Hefan. Improved DeepLabV3+ model for spring crops identification in Sichuan counties[J]. Bulletin of Surveying and Mapping, 2025, 0(3): 133-137,167.

References

[1] ZHANG D.Study on problems and countermeasures of agricultural water saving irrigation[J].Journal of Water Resources Research, 2017,6(1): 49-54.
[2] 楼豫红,康绍忠,崔宁博,等.基于集对分析的区域节水灌溉发展水平综合评价模型构建与应用: 以四川为例[J].四川大学学报(工程科学版),2014,46(2): 20-28.
[3] 王君勤,高鹏,殴承建.四川省灌溉用水定额标准研究[J].灌溉排水学报,2016,35(S2): 32-35.
[4] 赖积保,康旭东,鲁续坤,等.新一代人工智能驱动的陆地观测卫星遥感应用技术综述[J].遥感学报,2022,26(8): 1530-1546.
[5] 张圣微,杨林,叶德成,等.基于深度学习的内蒙古河套灌区2000—2021年种植结构提取与动态[J].农业工程学报,2023,39(18): 142-150.
[6] YANG Rui,QI Yuan,ZHANG Hui,et al.A study on the object-based high-resolution remote sensing image classification of crop planting structures in the Loess Plateau of eastern Gansu province[J].Remote Sensing,2024,16(13): 2479.
[7] 张悦琦,任鸿瑞.融合特征优选与随机森林算法的GF-6影像东北一季稻遥感提取[J].遥感学报,2023,27(9): 2153-2164.
[8] 张博.基于深度学习的无人机航拍图像小目标检测方法研究[D].海口: 海南大学,2024.
[9] 黄友菊,农志铣,韩广萍,等.一种基于差异注意力的广西耕地“非粮化”提取研究[J].测绘科学,2023,48(8): 193-201.
[10] 蔡玉林,刘照磊,孟祥磊,等.基于HRNet和自注意力机制的多源遥感影像水稻提取[J].农业工程学报,2024,40(4): 186-193.
[11] LE-KHAC P H,HEALY G,SMEATON A F.Contrastive representation learning: a framework and review[J].IEEE Access,2020(8): 193907-193934.
[12] 刘玉洁,葛全胜,戴君虎.全球变化下作物物候研究进展[J].地理学报,2020,75(1): 14-24.
[13] 汤艺成,郑文武,张锦水.中国南方山区油菜识别的遥感影像选择策略研究——以云南罗平县为例[J].中国农业资源与区划,2024,45(7): 170-183.
[14] GITELSON A A,KAUFMAN Y J,MERZLYAK M N.Use of a green channel in remote sensing of global vegetation from EOS-MODIS[J].Remote Sensing of Environment,1996,58(3): 289-298.
[15] GITELSON A A,KAUFMAN Y J,STARK R,et al.Novel algorithms for remote estimation of vegetation fraction[J].Remote Sensing of Environment,2002,80(1): 76-87.
[16] GITELSON A A,VIÑA A,ARKEBAUER T J,et al.Remote estimation of leaf area index and green leaf biomass in maize canopies[J].Geophysical Research Letters,2003,30(5): 335-343.
[17] LIU H Q,HUETE A.A feedback based modification of the NDVI to minimize canopy background and atmospheric noise[J].IEEE Transactions on Geoscience and Remote Sensing,1995,33(2): 457-465.
[18] HU Luojia,LI Wenyu,XU Bing.Monitoring mangrove forest change in China from 1990 to 2015 using Landsat-derived spectral-temporal variability metrics[J].International Journal of Applied Earth Observation and Geoinformation,2018,73: 88-98.