基于面向对象CNN和RF的不同空间分辨率遥感影像农业大棚提取研究  

Different Spatial Resolutions based on Object-oriented CNN and RF Research on Agricultural Greenhouse Extraction from Remote Sensing Images

作　　者：林欣怡 汪小钦[1,2] 汤紫霞 李蒙蒙 吴瑞姣 黄德华 LIN Xinyi;WANG Xiaoqin;TANG Zixia;LI Mengmeng;WU Ruijiao;HUANG Dehua(Key Laboratory of Spatial Data Mining and Information Sharing of Ministry of Education,Fuzhou University,Fuzhou 350108,China;The Academy of Digital China(Fujian),Fuzhou University,Fuzhou 350108,China;Fujian Geologic Surveying and Mapping Institute,Fuzhou 350011,China)

机构地区：[1]福州大学空间数据挖掘与信息共享教育部重点实验室,福建福州350108 [2]福州大学数字中国研究院(福建),福建福州350108 [3]福建省地质测绘院,福建福州350011

出　　处：《遥感技术与应用》2024年第2期315-327,共13页Remote Sensing Technology and Application

基　　金：福建省科技创新基金项目(2022C0024);中央引导地方科技发展专项(2017L3012)。

摘　　要：遥感技术已成为快速有效获取农业大棚覆盖信息的重要途径,但遥感影像空间分辨率大小对提取精度的影响具有双重性,选择适宜分辨率影像具有重要意义。以南方农业塑料大棚为研究对象,利用GF-1、GF-2和Sentinel-2形成1~16 m间6个不同空间分辨率影像数据集,基于面向对象影像分析方法(Object-Based Image Analysis,OBIA),分别利用面向对象卷积神经网络(Convolutional Neural Network,CNN)方法和随机森林(Random forest,RF)方法开展大棚提取,分析提取精度和不同方法下的差异性。结果表明:①CNN和RF方法下,农业大棚的提取精度随着影像分辨率降低总体呈下降趋势,在1~16 m的影像上均能检测到农业大棚;②相对于RF方法,CNN方法对影像空间分辨率要求更高,在1~2 m分辨率下,CNN方法有更少的漏提和误提,但在4m及更低分辨率下,RF方法的适用性更高;③2 m分辨率影像是大棚信息提取的最佳空间分辨率,可经济有效地实现大棚监测。Remote sensing technology has become an important way to obtain agricultural greenhouse coverage information quickly and effectively.But the spatial resolution size of remote sensing images has a dual influence on the extraction accuracy,and it is important to select suitable resolution images.Taking the southern agricul⁃tural plastic greenhouses as the research object,GF-1,GF-2 and Sentinel-2 are used to form six different spa⁃tial resolution image datasets between 1 and 16 m.Based on Object-Based Image Analysis(OBIA),we use the Convolutional Neural Network(CNN)and Random Forest(RF)methods to extract the canopy and ana⁃lyze the extraction accuracy and the difference between the methods.The results show that:(1)the extraction accuracy of agricultural greenhouses under CNN and RF methods generally decreases as the image resolution de⁃creases,and agricultural sheds can be detected on images from 1m to 16 m;(2)the CNN method requires high⁃er spatial resolution than the RF method,and the CNN method has fewer missed and false extractions at 1~2 m resolution,but at 4 m and lower resolutions,the RF method is more applicable;(3)the 2 m resolution im⁃age is the best spatial resolution for shed information extraction,which can realize shed monitoring economically and effectively.

关 键 词：农业大棚提取 面向对象CNN方法 随机森林 空间分辨率 高分辨率遥感数据 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置] TP79[自动化与计算机技术—控制科学与工程]