基于面向?qū)ο笈c深度學(xué)習(xí)方法的遙感影像自動(dòng)提取技術(shù)研究

打開文本圖片集

摘要：文章在對(duì)面向?qū)ο蠖喑叨确指罴夹g(shù)和深度學(xué)習(xí)技術(shù)分別進(jìn)行理論、方法闡述后，開展目標(biāo)區(qū)建設(shè)用地和非建設(shè)用地自動(dòng)提取實(shí)例研究。通過建立少量地類樣本庫完成遙感影像自動(dòng)分類提取，并對(duì)提取結(jié)果進(jìn)行分析，得出目標(biāo)區(qū)總體分類精度達(dá)到94.40%，建設(shè)用地的制圖精度和用戶精度能夠滿足實(shí)際生產(chǎn)需求。

關(guān)鍵詞：遙感影像；自動(dòng)提??；面向?qū)ο?；深度學(xué)習(xí)

doi：10.3969/J.ISSN.1672-7274.2023.07.009

中圖分類號(hào)：P 237，TP 3             文獻(xiàn)標(biāo)志碼：A               文章編碼：1672-7274（2023）07-00-03

Research on Remote Sensing Image Automatic Extraction Technology Based on Object Oriented and Deep Learning Methods

DOU Yajuan

（Zhongse Blueprint Technology Co.， Ltd.， Beijing 101312， China）

Abstract： This article conducts a case study on automatic extraction of construction and non construction land in the target area. By establishing a small number of land class sample libraries to complete automatic classification and extraction of remote sensing images， and analyzing the extraction results， it was found that the overall classification accuracy of the target area reached 94.40%， and the mapping accuracy and user accuracy of construction land can meet actual production needs.

Key words： remote sensing images; automatic extraction; object-oriented; deep learning

目前，遙感圖像解譯存在兩大難點(diǎn)：一是不同地物難以分割開，二是地物分類不準(zhǔn)確。（剩余4348字）