[1]董建宾,李卫国,戴佩玉,等.基于残差多尺度提取网络模型（ResMSFCN）和无人机遥感影像的蟹塘水草信息提取[J].江苏农业学报,2026,42(02):349-356.[doi:doi:10.3969/j.issn.1000-4440.2026.02.013]
　DONG Jianbin,LI Weiguo,DAI Peiyu,et al.Extraction of aquatic plant information in crab ponds using a residual multiscale fully connected neural network (ResMSFCN) and unmanned aerial vehicle remote sensing images[J].,2026,42(02):349-356.[doi:doi:10.3969/j.issn.1000-4440.2026.02.013]
点击复制

基于残差多尺度提取网络模型（ResMSFCN）和无人机遥感影像的蟹塘水草信息提取()

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
42
期数:
2026年02期
页码:
349-356
栏目:
农业信息工程
出版日期:
2026-02-28

文章信息/Info

Title:
Extraction of aquatic plant information in crab ponds using a residual multiscale fully connected neural network (ResMSFCN) and unmanned aerial vehicle remote sensing images
作者:
董建宾1; 2; 李卫国1; 2; 戴佩玉2; 毛星2; 金晶2
(1.南京信息工程大学生态与应用气象学院,江苏南京210044；2.江苏省农业科学院农业信息研究所,江苏南京210014)
Author(s):
DONG Jianbin1; 2; LI Weiguo1; 2; DAI Peiyu2; MAO Xing2; JIN Jing2
(1.School of Ecology and Applied Meteorology, Nanjing University of Information Science & Technology, Nanjing 210044, China;2.Institute of Agricultural Information, Jiangsu Academy of Agricultural Sciences, Nanjing 210014, China)
关键词:
蟹塘; 水草; 卷积神经网络; 无人机遥感; 多光谱影像
Keywords:
crab pond; aquatic plants; convolutional neural network; unmanned aerial vehicle remote sensing; multispectral images
分类号:
S127
DOI:
doi:10.3969/j.issn.1000-4440.2026.02.013
文献标志码:
A
摘要:
蟹塘中的水草不仅能够净化水质、增加溶氧量、提供饵料,夏季高温期还可为螃蟹提供遮阳和栖息的场所。目前,水产养殖过程中水草种植信息的获取主要依靠人工判断,存在劳动力成本高、时效性差以及效率低等问题。为了有效解决以上问题,本研究选取南京市高淳区和无锡市宜兴市大闸蟹养殖塘作为研究区,将卷积神经网络与无人机高空间分辨率多光谱影像相结合,构建基于无人机多光谱影像的多时相蟹塘水草分布数据集,提出基于残差多尺度提取网络的水草信息精细提取模型(ResMSFCN),并与U-Net模型和DeepLabv3+模型进行精度比较。结果表明,ResMSFCN模型具有较好的水草影像提取能力,准确率达0.963,交并比达0.804。此外,该模型能精准识别6月份至10月份5个时相的水草分布区域均匀度。本研究提出的基于无人机多光谱影像和ResMSFCN结合的蟹塘水草信息提取模型能高精度、高效率获取蟹塘多时相水草覆盖信息,为蟹塘水草资源快速评估提供科学依据。
Abstract:
Aquatic plants in crab ponds not only purify water quality, increase dissolved oxygen, and provide food, but also offer shading and habitats for crabs during the high-temperature period in summer. Currently, the acquisition of aquatic plant planting information in aquaculture mainly relies on manual judgment, which has problems such as high labor costs, poor timeliness, and low production efficiency. To effectively solve these issues, this study selected crab ponds for Chinese mitten crabs in Gaochun District of Nanjing and Yixing City of Wuxi as the research areas. Combining convolutional neural networks with high-spatial-resolution multispectral images acquired by unmanned aerial vehicles (UAVs), a multi-temporal dataset of aquatic plant distribution in crab ponds based on UAV multispectral images was constructed. A fine extraction model for aquatic plants based on the residual multiscale fully connected neural network (ResMSFCN) was proposed, and its accuracy was compared with U-Net and DeepLabv3+models. The results showed that the ResMSFCN model had better ability to extract aquatic plant images, with an accuracy of 0.963 and an intersection over union (IoU) of 0.804. In addition, this model could accurately identify the uniformity of aquatic plant distribution areas across five temporal phases from June to October. The model proposed in this study, which combines UAV multispectral images with ResMSFCN for aquatic plant extraction in crab ponds, can acquire multi-temporal aquatic plant coverage information with high precision and efficiency, and also offer a scientific basis for the rapid evaluation of aquatic plant resources in crab ponds.

参考文献/References:

[1]赵德安,罗吉,孙月平,等. 河蟹养殖自动作业船导航控制系统设计与测试[J]. 农业工程学报,2016,32(11):181-188.
[2]沈启扬,朱虹,孙龙霞,等. 虾蟹池塘养殖水草收割机应用现状及发展前景[J]. 江苏农机化,2020(1):13-15.
[3]马荣华,孔繁翔,段洪涛,等. 基于卫星遥感的太湖蓝藻水华时空分布规律认识[J]. 湖泊科学,2008,20(6):687-694.
[4]DAI Y H, FENG L, HOU X J, et al. An automatic classification algorithm for submerged aquatic vegetation in shallow lakes using Landsat imagery[J]. Remote Sensing of Environment,2021,260:112459.
[5]ALBRIGHT T P, ODE D J. Monitoring the dynamics of an invasive emergent macrophyte community using operational remote sensing data[J]. Hydrobiologia,2011,661(1):469-474.
[6]李俊生,吴迪,吴远峰,等. 基于实测光谱数据的太湖水华和水生高等植物识别[J]. 湖泊科学,2009,21(2):215-222.
[7]ZHAO D H, LV M T, JIANG H, et al. Spatio-temporal variability of aquatic vegetation in Taihu Lake over the past 30 years[J]. PLoS One,2013,8(6):66365.
[8]闫大鹏,周兴东,刘伟,等. 一种基于高斯拟合的水生植被遥感分类阈值确定方法[J]. 西安科技大学学报,2018,38(5):776-782.
[9]侍昊,李旭文,牛志春,等. 基于随机森林模型的太湖水生植被遥感信息提取[J]. 湖泊科学,2016,28(3):635-644.
[10]GAO H Y, LI R R, SHEN Q, et al. Deep-learning-based automatic extraction of aquatic vegetation from Sentinel-2 images:a case study of lake Honghu[J]. Remote Sensing,2024,16(5):867.
[11]PANDE-CHHETRI R, ABD-ELRAHMAN A, JACOBY C. Classification of submerged aquatic vegetation in Black River using hyperspectral image analysis[J]. Geomatica,2014,68(3):169-182.
[12]于堃,单捷,王志明,等. 无人机遥感技术在小尺度土地利用现状动态监测中的应用[J]. 江苏农业学报,2019,35(4):853-859.
[13]宋恩泽,张颖,邵光成,等. 基于无人机多光谱遥感的农业园区地物分类研究[J]. 江苏农业学报,2023,39(9):1862-1871.
[14]孙月平,刘勇,郭佩璇,等. 基于改进YOLO v8n-seg的蟹塘水草区域分割与定位方法[J]. 农业工程学报,2024,40(17):224-233.
[15]YU Z J, XIE T Y, ZHU Q B, et al. Aquatic plants detection in crab ponds using UAV hyperspectral imagery combined with transformer-based semantic segmentation model[J]. Computers and Electronics in Agriculture,2024,227:109656.
[16]曹梦娇,白石,唐攀攀,等. 基于无人机多光谱遥感的水稻二化螟冬前虫量测算[J]. 江苏农业学报,2025,41(2):305-312.
[17]洪国军,张灵,徐恒,等. 多高度无人机多光谱成像在枣树不同生育期LAI监测中的应用[J]. 江苏农业学报,2024,40(11):2093-2101.
[18]王德兴,何勇,袁红春. 基于YOLO v8-BAN模型的水下生物目标检测方法[J]. 江苏农业学报,2025,41(1):101-111.
[19]李鑫. 基于无人机遥感数据的蓝藻识别应用研究[D]. 郑州:解放军信息工程大学,2017.
[20]高敏,谢娅,李潇屹,等. 基于大面阵无人机多光谱遥感的水生植被精细分类研究[J]. 南京信息工程大学学报,2025,17(3):414-422.
[21]戴佩玉,张欣,毛星,等. 利用空间-光谱双分支特征和动态选择的高光谱影像农作物分类[J]. 农业工程学报,2023,39(16):160-170.
[22]ZHONG Y, HU X, LUO C, et al. WHU-Hi:UAV-borne hyperspectral with high spatial resolution (H2) benchmark datasets and classifier for precise crop identification based on deep convolutional neural network with CRF[J]. Remote Sensing of Environment,2020,250:112012.
[23]朱庆,李俊生,张方方,等. 基于海岸带高光谱成像仪影像的太湖蓝藻水华和水草识别[J]. 遥感技术与应用,2016,31(5):879-885.
[24]丁铭,李旭文,姜晟,等. 基于无人机高光谱遥感在太湖蓝藻水华监测中的一次应用[J]. 环境监测管理与技术,2022,34(1):49-51,71.
[25]谢雨涵,史建康,孙晓慧,等. 基于大疆精灵4无人机多光谱影像的西沙植被监测[J]. 遥感技术与应用,2022,37(5):1170-1178.
[26]BASTIDAS A A, TANG H L. Channel attention networks[C]//IEEE/CVF. 2019 IEEE/CVF conference on computer vision and pattern recognition workshops (CVPRW). Long Beach,CA,USA:IEEE,2019.

备注/Memo

备注/Memo:
收稿日期：2025-05-07基金项目：江苏省重点研发计划项目(BE2022366)；江苏现代农业产业单项技术研发项目[CX(23)3131]作者简介：董建宾(1999-),男,山东聊城人,硕士研究生,研究方向为农业遥感信息技术及应用。(E-mail)kovacs991@163.com通讯作者：戴佩玉,(E-mail)pydai@whu.edu.cn
更新日期/Last Update: 2026-03-16