基于Relief F与卷积神经网络的湿地植物群落精细分类

doi:10.13474/j.cnki.11-2246.2023.0041

测绘通报 ›› 2023, Vol. 0 ›› Issue (2): 58-64.doi: 10.13474/j.cnki.11-2246.2023.0041

基于Relief F与卷积神经网络的湿地植物群落精细分类

张永彬¹, 刘雅辉¹, 刘明月^1,2,3,4, 满卫东^1,2,3,4, 宋唐雷¹, 李春雨¹

1. 华北理工大学矿业工程学院, 河北唐山 063210;
2. 唐山市资源与环境遥感重点实验室, 河北唐山 063210;
3. 河北省矿区生态修复产业技术研究院, 河北唐山 063210;
4. 河北省矿业开发与安全技术重点实验室, 河北唐山 063210

收稿日期:2022-04-19 发布日期:2023-03-01
通讯作者: 满卫东。E-mail:manwd@ncst.edu.cn
作者简介:张永彬(1969-),男,博士,教授,研究方向为3S技术在资源与环境中的应用及地理国情监测。E-mail:zyb063009@yeah.net
基金资助:
国家自然科学基金(41901375;42101393);河北省自然科学基金(D2019209322;D2022209005);河北省高等学校科学技术研究项目青年拔尖人才项目(BJ2020058);河北省引进留学人员资助项目(C20200103);唐山市科技计划重点研发项目(19150231E)

Wetland plant community classification based on Relief F and convolutional neural network

ZHANG Yongbin¹, LIU Yahui¹, LIU Mingyue^1,2,3,4, MAN Weidong^1,2,3,4, SONG Tanglei¹, LI Chunyu¹

1. College of Mining Engineering, North China University of Science and Technology, Tangshan 063210, China;
2. Tangshan Key Laboratory of Resources and Environmental Remote Sensing, Tangshan 063210, China;
3. Hebei Industrial Technology Institute of Mine Ecological Remediation, Tangshan 063210, China;
4. Hebei Key Laboratory of Mining Development and Security Technology, Tangshan 063210, China

Received:2022-04-19 Published:2023-03-01

摘要/Abstract

摘要： 湿地是陆地生态系统和水生生态系统之间的重要过渡带,准确高效地获取湿地植物群落分布信息对于保护湿地具有深远的意义。本文以无人机多光谱影像为数据源,首先构建包含光谱特征、植被指数和纹理特征的多维特征数据集,并采用Relief F算法进行特征优选,确定最优特征数据集;然后构建基于特征优选的卷积神经网络 (CNN)分类模型,对最优特征数据集进行分类,并与基于原始多光谱影像的CNN和随机森林(RF)分类方法进行对比。结果表明:①随着特征个数的增加,分类精度先增加后下降,当特征数为32时分类精度最高;②窗口为13×13的GLCM提取的信息熵和同质性等纹理特征及GNDVI、MSAVI2、RVI等多光谱植被指数重要性较高;③基于最优特征数据集的CNN分类模型,能够有效提取空间光谱信息,抑制“椒盐现象”的产生,分类效果最佳,总体精度达93.40%,与未进行特征优选的RF和CNN分类模型相比分别提高了9.80%和7.40%。

关键词: 无人机多光谱, 卷积神经网络, 特征优选, 湿地精细分类

Abstract: Wetland is an important transition zone between terrestrial and aquatic ecosystems. Accurate and efficient acquisition of wetland plant community distribution information is of profound significance for wetland conservation. We use the UAV multispectral images as the data source, construct a multidimensional feature dataset containing spectral features, vegetation indices, and texture features, and determine the optimal feature dataset by the Relief F algorithm. Then, we construct a convolutional neural networks (CNN) classification model based on the feature selection and classify the optimal feature dataset with the CNN based on the original multispectral images. The results show that:① The classification accuracy increases and then decreases as the number of features increases, and the classification accuracy is highest when the number of features is 32. ② Texture features such as information entropy, homogeneity, and multispectral vegetation indices such as GNDVI, MSAVI2, and RVI extracted by GLCM with a window of 13×13 have higher importance. ③ The CNN classification model based on the optimal feature dataset can effectively extract the spatial-spectral information and suppress the “salt-and-pepper noise”, with the best classification effect and the overall accuracy of 93.40%, which is 9.80% and 7.40% higher than the RF and CNN classification models without feature optimization, respectively.

Key words: UAV multispectral, convolutional neural network, feature preference, wetland fine classification

中图分类号:

张永彬, 刘雅辉, 刘明月, 满卫东, 宋唐雷, 李春雨. 基于Relief F与卷积神经网络的湿地植物群落精细分类[J]. 测绘通报, 2023, 0(2): 58-64.

ZHANG Yongbin, LIU Yahui, LIU Mingyue, MAN Weidong, SONG Tanglei, LI Chunyu. Wetland plant community classification based on Relief F and convolutional neural network[J]. Bulletin of Surveying and Mapping, 2023, 0(2): 58-64.

参考文献

[1] 刘瑞清,李加林,孙超,等. 基于Sentinel-2遥感时间序列植被物候特征的盐城滨海湿地植被分类[J]. 地理学报,2021,76(7): 1680-1692.
[2] 徐逸,甄佳宁,蒋侠朋,等. 无人机遥感与XGBoost的红树林物种分类[J]. 遥感学报,2021,25(3): 737-752.
[3] 耿仁方,付波霖,蔡江涛,等. 基于无人机影像和面向对象随机森林算法的岩溶湿地植被识别方法研究[J]. 地球信息科学学报,2019,21(8): 1295-1306.
[4] WU Ke,CHEN Tao,XU Ying,et al. A novel change detection approach based on spectral unmixing from stacked multitemporal remote sensing images with a variability of endmembers[J]. Remote Sensing,2021,13(13): 2550.
[5] 杨倩,李宁云,陈丽,等. 大山包湿地植被群落数量分类及主要种生态位特征研究[J]. 西部林业科学,2020,49(2): 36-42.
[6] JAMALI A,MAHDIANPARI M,BRISCO B,et al. Wetland mapping using multi-spectral satellite imagery and deep convolutional neural networks: a case study in Newfoundland and Labrador,Canada[J]. Canadian Journal of Remote Sensing,2021,47(2): 243-260.
[7] 左萍萍,付波霖,蓝斐芜,等. 基于无人机多光谱的沼泽植被识别方法[J]. 中国环境科学,2021,41(5): 2399-2410.
[8] 肖武,任河,吕雪娇,等. 基于无人机遥感的高潜水位采煤沉陷湿地植被分类[J]. 农业机械学报,2019,50(2): 177-186.
[9] GENG Renfang,JIN Shuanggen,FU Bolin,et al. Object-based wetland classification using multi-feature combination of ultra-high spatial resolution multispectral images[J]. Canadian Journal of Remote Sensing,2020,46(6): 784-802.
[10] 汪传建,赵庆展,马永建,等. 基于卷积神经网络的无人机遥感农作物分类[J]. 农业机械学报,2019,50(11): 161-168.
[11] ZHANG Meimei,CHEN Fang,TIAN Bangsen,et al. Multi-temporal SAR image classification of coastal plain wetlands using a new feature selection method and random forests[J]. Remote Sensing Letters,2019,10(3): 312-321.
[12] LIU Tao. Deep convolutional neural network training enrichment using multi-view object-based analysis of unmanned aerial systems imagery for wetlands classification[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2018,139: 154-170.
[13] DOS SANTOS FERREIRA A. Weed detection in soybean crops using ConvNets[J]. Computers and Electronics in Agriculture,2017,143: 314-324.
[14] 郑卓,方芳,刘袁缘,等. 高分辨率遥感影像场景的多尺度神经网络分类法[J]. 测绘学报,2018,47(5): 620-630.
[15] HU Fan,XIA Guisong,HU Jingwen,et al. Transferring deep convolutional neural networks for the scene classification of high-resolution remote sensing imagery[J]. Remote Sensing,2015,7(11): 14680-14707.
[16] 黄昕. 高分辨率遥感影像多尺度纹理、形状特征提取与面向对象分类研究[D]. 武汉: 武汉大学,2009.
[17] 刘戈,姜小光,唐伯惠. 特征优选与卷积神经网络在农作物精细分类中的应用研究[J]. 地球信息科学学报,2021,23(6): 1071-1081.
[18] ROBNIK-ŠIKONJA M,KONONENKO I. Theoretical and empirical analysis of Relief F and RRelief F[J]. Machine Learning,2003,53(1/2): 23-69.
[19] ZHONG Yanfei,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.
[20] 周飞燕,金林鹏,董军. 卷积神经网络研究综述[J]. 计算机学报,2017,40(6): 1229-1251.

基于Relief F与卷积神经网络的湿地植物群落精细分类

Wetland plant community classification based on Relief F and convolutional neural network

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	李子彧, 周维勋, 耿万轩. 联合类别筛选与重排序的交叉视角图像地理定位[J]. 测绘通报, 2023, 0(2): 40-45.
[2]	施仲添, 沈正伟, 杨四海. 基于前景感知的遥感影像建筑物提取方法[J]. 测绘通报, 2023, 0(2): 134-138.
[3]	向煜, 黄志, 华媛媛, 邓剑峰. 深度学习支持下的宅基地复垦项目真实性智能审查技术研究与应用[J]. 测绘通报, 2023, 0(1): 163-167.
[4]	黄宇鸿, 周维勋. 高分辨率遥感影像场景变化检测的相似度方法[J]. 测绘通报, 2022, 0(8): 48-53.
[5]	柳林, 孙毅, 李万武. 基于CNN海上钻井平台检测模型的构建及训练算法分析[J]. 测绘通报, 2022, 0(7): 26-32,99.
[6]	蔡柔丹. 一种基于用户异步轨迹的身份识别智能方法[J]. 测绘通报, 2022, 0(7): 158-162,167.
[7]	滕文鑫, 张建辰, 邵杰. 集成时空邻近与卷积网络车道级高精度定位算法[J]. 测绘通报, 2022, 0(6): 1-5,61.
[8]	文奴, 郭仁忠, 贺彪, 万远. YOLO v4框架下Multi-Patch多帧增量式交通视频目标检测[J]. 测绘通报, 2022, 0(5): 38-44.
[9]	王胜利, 朱寿红, 蒋毅. 基于CNN模型迁移的OLI影像光伏电池板场景识别[J]. 测绘通报, 2022, 0(2): 5-9.
[10]	王铮, 符校, 杜凯旋, 刘纪平, 车向红. 深度学习支持下的地图图片典型地理目标检测[J]. 测绘通报, 2022, 0(11): 74-78.
[11]	闵星, 黄品文, 谭金祥. 基于卷积神经网络的地铁保护区风险源识别[J]. 测绘通报, 2022, 0(10): 162-165,170.
[12]	耿万轩, 周维勋, 金双根. 基于LDCNN特征提取的多核SVM高分辨率遥感影像场景分类[J]. 测绘通报, 2021, 0(8): 14-21.
[13]	赵恒谦, 杨屹峰, 刘泽龙, 宋瑞. 农作物叶片病害迁移学习分步识别方法[J]. 测绘通报, 2021, 0(7): 34-38.
[14]	贾文翰, 刘越岩. 基于卷积神经网络的高分遥感影像内陆盐沼湿地信息提取[J]. 测绘通报, 2021, 0(6): 89-92.
[15]	段雅鸣, 张锦水, 朱爽. 基于深度卷积神经网络的云检测方法[J]. 测绘通报, 2021, 0(4): 33-39.