结合特征选择的CVA多尺度遥感影像变化检测

doi:10.13474/j.cnki.11-2246.2020.0257

测绘通报 ›› 2020, Vol. 0 ›› Issue (8): 101-104,130.doi: 10.13474/j.cnki.11-2246.2020.0257

结合特征选择的CVA多尺度遥感影像变化检测

蔡怤晟^1,2,3, 向泽君^1,2,3,4, 蔡衡^1,2,3, 单德明^1,2,3

1. 重庆邮电大学通信与信息工程学院, 重庆 400065;
2. 重庆邮电大学重庆高校市级光通信与网络重点实验室, 重庆 400065;
3. 重庆邮电大学泛在感知与互联重庆市重点实验室, 重庆 400065;
4. 重庆市勘测院, 重庆 400020

收稿日期:2019-10-28 修回日期:2019-12-25 出版日期:2020-08-25 发布日期:2020-09-01
作者简介:蔡怤晟(1995-),男,硕士生,研究方向为遥感影像处理。E-mail:553200971@qq.com
基金资助:
重庆高校创新团队建设计划（CXTDX201601020）

CVA multi-scale remote sensing image change detection combined with feature selection

CAI Fusheng^1,2,3, XIANG Zejun^1,2,3,4, CAI Heng^1,2,3, SHAN Deming^1,2,3

1. School of Telecommunication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China;
2. Chongqing University of Posts and Telecommunications, Key Laboratory of Optical Communication and Network in Chongqing, Chongqing 400065, China;
3. Chongqing University of Posts and Telecommunications, Key Laboratory of Ubiquitous Sensing and Networking in Chongqing, Chongqing 400065, China;
4. Chongqing Survey Institute, Chongqing 400020, China

Received:2019-10-28 Revised:2019-12-25 Online:2020-08-25 Published:2020-09-01

摘要/Abstract

摘要： 针对在多时相变化检测中，面向对象方法无法较好地检测影像中的细微变化，受分割效果以及面向像素方法的影响出现较高虚警率等问题，本文提出了一种结合基于像素的多特征变化向量分析法（CVA）与基于对象的多层次分割的联合判别方法。首先提取不同时相的光谱与纹理特征，利用最大相关最小冗余（mRMR）算法进行特征选择并通过CVA得到像素级变化检测结果；然后对两幅影像进行叠合分割，利用区域合并策略进行不同尺度检测并获取各尺度检测结果；最后结合多种检测结果进行融合，获得最终变化检测结果。检测结果表明本文所提方法能有效降低漏检率，同时提高了检测的准确性。

关键词: 特征融合, 特征选择, 多尺度分割, 变化向量法, 决策级融合

Abstract: Aiming at the problems of the object-oriented method can not detect the subtle changes in the image, the segmentation effect, and the high false alarm rate in the pixel-oriented method in the multi-temporal change detection. In this paper, a combined with multiple characteristics change vector analysis (CVA) method based on pixel and multi-level segmentation joint discriminant method based on the object. Firstly, the spectral and texture features of different time phases are extracted, and the maximum correlation minimum redundancy (mRMR) algorithm is used to select the features and the pixel-level change detection results are obtained by CVA. Then the two images are superimposed and split, and the regional merge strategy is used to make different scale detection, obtain the test results of each scale. And finally combine the multiple test results to determine the final change test results. The experimental results show that the proposed method can effectively reduce the missed detection rate and improve the accuracy of detection.

Key words: feature fusion, feature selection, multi-scale segmentation, change vector analysis, decision-level fusion

中图分类号:

P237

蔡怤晟, 向泽君, 蔡衡, 单德明. 结合特征选择的CVA多尺度遥感影像变化检测[J]. 测绘通报, 2020, 0(8): 101-104,130.

CAI Fusheng, XIANG Zejun, CAI Heng, SHAN Deming. CVA multi-scale remote sensing image change detection combined with feature selection[J]. Bulletin of Surveying and Mapping, 2020, 0(8): 101-104,130.

参考文献

[1] LIU S C, BRUZZONE L, BOVOLO F, et al. Unsupervised multitemporal spectral unmixing for detecting multiple changes in hyperspectral images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(5):2733-2748.
[2] LIU S C, LI Y, TONG X H. Superpixel-based multiple change detection in very-high-resolution remote sensing images[C]//Proceedings of International Workshop on Remote Sensing with Intelligent Processing. Shanghai:IEEE, 2017.
[3] LV P Y, ZHONG Y F, ZHAO J, et al, Unsupervised change detection based on hybrid conditional random field model for high spatial resolution remote sensing imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(7):4002-4015.
[4] 常方正,赵银娣,刘善磊.遥感影像CVA变化检测的CUDA并行算法设计[J].遥感学报,2016,20(1):114-128.
[5] 王守峰,杨学志,董张玉,等.基于Relief-PCA特征选择的遥感图像变化检测[J].图学学报,2019,40(1):117-123.
[6] 程梦真,惠文华,李延金,等.利用影像相关分析的遥感变化检测[J].测绘通报,2019(10):67-71.
[7] LIU S C, DU Q, TONG X H, et al. Multiscale morphological compressed change vector analysis for unsupervised multiple change detection[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017, 10(9):4124-4137.
[8] ZHUANG H F, DENG K Z, FAN H D, et al. Strategies combining spectral angle mapper and change vector analysis to unsupervised change detection in multispectral images[J]. IEEE Geoscience and Remote Sensing Letters, 2016, 13(5):681-685.
[9] 冯文卿,张永军.利用多尺度融合进行面向对象的遥感影像变化检测[J].测绘学报,2015,44(10):1142-1151.
[10] 赵敏,赵银娣.面向对象的多特征分级CVA遥感影像变化检测[J].遥感学报,2018,22(1):119-131.
[11] 张志强,张新长,辛秦川,等.结合像元级和目标级的高分辨率遥感影像建筑物变化检测[J].测绘学报,2018,47(1):102-112.
[12] HUANG X, HAN X P, ZHANG L P, et al. Generalized differential morphological profiles for remote sensing image classification[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016, 9(4):1736-1751.
[13] LEI Y, LIU X D, SHI J, et al. Multiscale superpixel segmentation with deep features for change detection[J]. IEEE Access, 2019, 7:36600-36616.
[14] MAHROOGHY M, AANSTOOS J V, NOBREGA R A A, et al. A machine learning framework for detecting landslides on earthen levees using spaceborne SAR imagery[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015, 8(8):3791-3801.
[15] ZHANG Y, WANG S G, WANG C, et al. SAR image change detection using saliency extraction and shearlet transform[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2018, 11(12):4701-4710.
[16] XU L, JING W P, SONG H B, et al. High-resolution remote sensing image change detection combined with pixel-level and object-level[J]. IEEE Access, 2019, 7:78909-78918.

结合特征选择的CVA多尺度遥感影像变化检测

CVA multi-scale remote sensing image change detection combined with feature selection

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]	窦世卿, 陈治宇, 徐勇, 郑贺刚, 苗林林, 宋莹莹. 基于多特征融合与典型降维方法的高光谱影像分类[J]. 测绘通报, 2022, 0(4): 32-36,50.
[2]	冯志立, 肖锋, 卢小平, 郝波, 王如意, 朱睿. 基于随机森林特征优选的冬小麦分类方法[J]. 测绘通报, 2022, 0(3): 70-75.
[3]	王刚, 丁华祥. Sentinel-2A数据支持下的雷州半岛植被类型识别[J]. 测绘通报, 2022, 0(3): 76-82.
[4]	贾煜, 汪泓, 蔡宏, 张磊. 结合地形因子与分层策略的喀斯特地区无人机影像分类[J]. 测绘通报, 2022, 0(2): 121-127.
[5]	聂倩, 七珂珂, 赵艳福. 融入超像素分割的高分辨率影像面向对象分类[J]. 测绘通报, 2021, 0(6): 44-49.
[6]	侯翘楚, 李必军, 蔡毅. 高分辨率遥感影像的车道级高精地图要素提取[J]. 测绘通报, 2021, 0(3): 38-43.
[7]	任泽茜, 丁丽霞, 刘丽娟, 谢锦莹, 敖伊颍, 张继艳, 何嘉莹. 利用无人机遥感监测农作物种植面积[J]. 测绘通报, 2020, 0(7): 76-81.
[8]	张宏涛, 黄宏胜, 魏康宁, 钟海燕. 基于面向对象与规则的Sentinel-2A影像土地覆被分类——以江西省都昌县为例[J]. 测绘通报, 2020, 0(6): 111-117.
[9]	耿仁方, 付波霖, 金双根, 蔡江涛, 耿万轩, 娄佩卿. 面向对象的无人机遥感影像岩溶湿地植被遥感识别[J]. 测绘通报, 2020, 0(11): 13-18.
[10]	周继苗, 李必军, 陈世增. 一种多层特征融合的道路场景实时分割方法[J]. 测绘通报, 2020, 0(1): 10-15.
[11]	刘金丽, 陈钊. Landsat 8多光谱数据辅助下的高分影像多尺度分割[J]. 测绘通报, 2019, 0(9): 38-43.
[12]	王芳, 杨武年, 王建, 谢兵, 杨鑫, 任金铜. GF-2影像城市地物分类方法探讨[J]. 测绘通报, 2019, 0(7): 12-16.
[13]	沈宇臻, 官云兰, 杨禄, 刘承承, 严小芳. 顾及局部与结构特征的稀疏多项式逻辑回归高光谱图像分类方法[J]. 测绘通报, 2019, 0(6): 24-28.
[14]	滕文秀, 王妮, 施慧慧, 许振宇. 结合面向对象和深度特征的高分影像树种分类[J]. 测绘通报, 2019, 0(4): 38-42.
[15]	刘相云, 龚志辉, 金飞, 杨光, 范炜康. 结合显著图和深度学习的遥感影像飞机目标识别[J]. 测绘通报, 2019, 0(3): 27-31.