吉林大学学报(信息科学版) ›› 2023, Vol. 41 ›› Issue (4): 739-745.

• • 上一篇    下一篇

基于 CNN 的零样本城市遥感影像场景分割算法

陈 静, 王晓轩, 吴宇静, 王蓉蓉   

  1. 广州华立学院 城建学院, 广州 511325
  • 收稿日期:2022-08-23 出版日期:2023-08-16 发布日期:2023-08-17
  • 作者简介:陈静(1981— ), 女, 山东滕州人, 广州华立学院副教授, 主要从事 3S 空间信息技术应用研究, (Tel)86-13533828816 (E-mail)ccjj22@ yeah. net。
  • 基金资助:
    2020 年度广东省普通高校特色人才创新基金资助项目(2020KTSCX194); 2020 年广东省普通高校青年创新人才基金资助 项目(2020KQNCX121) 

Zero-Sample Urban Remote Sensing Image Scene Segmentation Algorithm Based on Convolutional Neural Network

CHEN Jing, WANG Xiaoxuan, WU Yujing, WANG Rongrong   

  1. School of Urban Construction, Gangzhou Huali College, Gangzhou 511325, China
  • Received:2022-08-23 Online:2023-08-16 Published:2023-08-17

摘要: 针对观测数据的零样本遥感影像场景分割时, 因不存在相应的参照物, 造成分割耗时长, 精确率较低等 问题, 提出了基于卷积神经网络的零样本城市遥感影像场景分割算法。 采用主成分分析方法与 K-奇异值分解 方法对遥感影像去噪处理, 抑制斑块效应; 将去噪后影像输入 Retinex 增强算法中, 进一步提升零样本城市遥 感影像增强效果; 采用均值漂移算法分割遥感影像场景获取其像素点之间关系, 通过卷积神经网络完成零样本 城市遥感影像场景精准分割。 实验结果表明, 该算法精确率高, 召回率高, F-score 率高, 消耗时间短。 

关键词:  主成分分析方法, Retinex 增强算法, 遥感影像场景, 均值漂移分割计算, K-奇异值分解方法, 卷积 神经网络

Abstract: In the case of zero sample remote sensing image scene segmentation without any observation data, there is no response reference, which results in long segmentation time and low accuracy. Therefore, a zero sample urban remote sensing image scene segmentation algorithm based on convolutional neural network is proposed. PCA ( Principal Component Analysis) and K-SVD ( K-Singular Value Decomposition) are used to denoise remote sensing images to suppress the patch effect. The denoised image is input into the Retinex enhancement algorithm to further improve the enhancement effect of zero sample urban remote sensing image. The mean shift algorithm is used to segment the remote sensing image scene to obtain the relationship between its pixels, and the convolution neural network is used to complete the accurate segmentation image scene. The experimental results show that the algorithm has high accuracy, high recall, high F-score rate and short consumption time.

Key words: principal component analysis ( PCA) method, Retinex enhancement algorithm, remote sensing image scene, mean shift segmentation calculation, K-singular value decomposition method (K-SVD), convolutional neural network

中图分类号: 

  •