Please wait a minute...
 
Remote Sensing for Natural Resources    2024, Vol. 36 Issue (3) : 128-136     DOI: 10.6046/zrzyyg.2023079
|
NSCT-based change detection for high-resolution remote sensing images under the framework of change vector analysis in posterior probability space
SONG Jiaxin1(), LI Yikun1,2,3(), YANG Shuwen1,2,3, LI Xiaojun1,2,3
1. Faculty of Geomatics,Lanzhou Jiaotong University, Lanzhou 730070, China
2. National-Local Joint Engineering Research Center of Technologies and Applications for National Geographic State Monitoring, Lanzhou 730070, China
3. Gansu Provincial Engineering Laboratory for National Geographic State Monitoring, Lanzhou 730070, China
Download: PDF(12723 KB)   HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks    
Abstract  

In the change detection for high-resolution remote sensing images, non-subsampled contourlet transform (NSCT) and change vector analysis (CVA) cannot ensure high detection accuracies under single thresholds due to significantly different changes in surface features. Hence, under the framework of change vector analysis in posterior probability space (CVAPS), this study proposed a NSCT-based change detection method combining fuzzy C-means (FCM) clustering and a simple Bayesian network (SBN): the FCM-SBN-CVAPS-NSCT method. First, the proposed method coupled FCM with an SBN to generate a change intensity map in posterior probability space. Then, the change intensity map was decomposed into submaps of different scales and directions through NSCT. The reconstructed change intensity map was optimized by preserving the details and eliminating noise in the high-frequency submaps. Finally, the multi-scale and multi-directional change detection in posterior probability space was achieved, enhancing the change detection accuracy. As indicated by the experimental results, the Kappa values obtained by the proposed method for three study areas were 0.100 9, 0.056 6, and 0.067 4 higher than those derived from the FCM-SBN-CVAPS method, demonstrating certain superiority.
Keywords simple Bayesian network      fuzzy C-means clustering      change vector analysis in posterior probability space      non-subsampled contourlet transform     
ZTFLH:  TP79  
Issue Date: 03 September 2024
Service
E-mail this article
E-mail Alert
RSS
Articles by authors
Jiaxin SONG
Yikun LI
Shuwen YANG
Xiaojun LI
Cite this article:   
Jiaxin SONG,Yikun LI,Shuwen YANG, et al. NSCT-based change detection for high-resolution remote sensing images under the framework of change vector analysis in posterior probability space[J]. Remote Sensing for Natural Resources, 2024, 36(3): 128-136.
URL:  
https://www.gtzyyg.com/EN/10.6046/zrzyyg.2023079     OR     https://www.gtzyyg.com/EN/Y2024/V36/I3/128
Fig.1  Change detection flow chart of FCM-SBN-CVAPS-NSCT
Fig.2  Simple Bayesian network
Fig.3  NSCT three-stage decomposition structure
Fig.4  Comparison of change detection algorithms of study area 1
Fig.5  Comparison of change detection algorithms of study area 2
Fig.6  Comparison of change detection algorithms of study area 3
Fig.7  Effect of different number of training pixels on the Kappa coefficient of the algorithm
Fig.8  Effect of different number of clusters and fuzzy parameter q on Kappa coefficient
Fig.9  Effect of NSCT denoising threshold parameters on Kappa coefficients
研究区 分解层数
1 2 3 4 5
研究区1 0.758 6 0.827 1 0.845 4 0.857 1 0.823 1
研究区2 0.708 2 0.714 2 0.762 2 0.711 8 0.737 6
研究区3 0.562 4 0.706 9 0.889 5 0.845 7 0.839 3
Tab.1  The influence of the number of NSCT decomposition layers on the Kappa coefficients
算法 参数 错检率/% 漏检率/% 总体精度/% Kappa系数
FCM-SBN-CVAPS-NSCT 30聚类 q=3.5
1 000训练样本C=10		 14.50 13.63 97.48 0.845 5
FCM-SBN-CVAPS 30聚类 q=3.5
1 000训练样本		 32.13 10.92 95.27 0.744 6
SVM-CVAPS cp=13 gamma=3
1 000训练样本		 47.67 8.98 91.81 0.621 7
CVA-NSCT-FCM 30聚类 q=3.5 22.40 27.25 95.70 0.727 5
CVA-NSCT C=10 6.48 40.43 96.01 0.706 3
Tab.2  Performance evaluation of change detection algorithms of study area 1
算法 参数 错检率/% 漏检率/% 总体精度/% Kappa系数
FCM-SBN-
CVAPS-NSCT		 30聚类 q=3.5
1 000训练样本C=10		 10.11 8.05 88.76 0.762 2
FCM-SBN-CVAPS 30聚类 q=3.5
1 000训练样本		 13.98 3.73 86.31 0.705 6
SVM-CVAPS cp=15 gamma=3
1 000训练样本		 11.96 23.41 79.35 0.581 3
CVA-NSCT-FCM 30聚类 q=3.5 13.02 68.10 55.50 0.206 8
CVA-NSCT C=10 5.47 68.59 56.95 0.238 9
Tab.3  Performance evaluation of change detection algorithms of study area 2
算法 参数 错检率/% 漏检率/% 总体精度/% Kappa系数
FCM-SBN-CVAPS-NSCT 30聚类 q=3.5
1 000训练样本C=10		 5.51 14.13 98.15 0.889 6
FCM-SBN-CVAPS 30聚类 q=3.5
1 000训练样本		 0.87 27.66 97.27 0.822 2
SVM-CVAPS cp=13 gamma=3
1 000训练样本		 19.46 20.10 96.17 0.780 0
CVA-NSCT-FCM 30聚类 q=3.5 24.95 15.12 95.81 0.773 4
CVA-NSCT C=10 13.31 15.85 97.22 0.838 6
Tab.4  Performance evaluation of change detection algorithms of study area 3
[1] 李德仁. 利用遥感影像进行变化检测[J]. 武汉大学学报(信息科学版), 2003, 28(s1):7-12.
[1] Li D R. Change detection from remote sensing images[J]. Geomatics and Information Science of Wuhan University, 2003, 28(s1):7-12.
[2] 杨存建, 欧晓昆, 党承林, 等. 森林植被动态变化信息的遥感检测[J]. 地球信息科学, 2000, 2(4):71-74,2.
[2] Yang C J, Ou X K, Dang C L, et al. Detecting the change information of forest vegetation in Lushui County of Yunnan Province[J]. Geo-information Science, 2000, 2(4):71-74,2.
[3] Bruzzone L, Prieto D F. Automatic analysis of the difference image for unsupervised change detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2000, 38(3):1171-1182.
[4] 李天宏, 韩鹏. 厦门市土地利用/覆盖动态变化的遥感检测与分析[J]. 地理科学, 2001, 21(6):537-543.
[4] Li T H, Han P. Land use/cover change detection and analysis with remote sensing in Xiamen city[J]. Scientia Geographica Sinica, 2001, 21(6):537-543.
doi: 10.13249/j.cnki.sgs.2001.06.537
[5] 严宇, 刘耀林. 基于融合和IFLICM算法的非监督遥感影像变化检测[J]. 测绘通报, 2018(3):25-31.
doi: 10.13474/j.cnki.11-2246.2018.0070
[5] Yan Y, Liu Y L. Unsupervised remote sensing image change detection based on fusion and IFLICM algorithm[J]. Bulletin of Surveying and Mapping, 2018(3):25-31.
doi: 10.13474/j.cnki.11-2246.2018.0070
[6] 盛光伟. 基于角度优先变化向量分析的林地变化检测[D]. 南京: 南京大学, 2020.
[6] Sheng G W. Forest change detection based on direction-first change vector analysis[D]. Nanjing: Nanjing University, 2020.
[7] Li L, Li X, Zhang Y, et al. Change detection for high-resolution remote sensing imagery using object-oriented change vector analysis method[C]// 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).Beijing,China.IEEE, 2016:2873-2876.
[8] Liu S, Bruzzone L, Bovolo F, et al. Sequential spectral change vector analysis for iteratively discovering and detecting multiple changes in hyperspectral images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(8):4363-4378.
[9] Li S T, Fang L Y, Yin H T. Multitemporal image change detection using a detail-enhancing approach with nonsubsampled contourlet transform[J]. IEEE Geoscience and Remote Sensing Letters, 2012, 9(5):836-840.
[10] Guo Q, Zhang J. Change detection for mutil-temporal remote sensing images based on NSCT and hierarchical clustering[C]// 2019 IEEE International Conference on Signal Processing,Communications and Computing (ICSPCC).Dalian,China.IEEE, 2019:1-4.
[11] Sun Q, Gao Y. Unsupervised change detection in multitemporal SAR images via NSCT-domain feature clustering[C]// 2013 IEEE International Conference on Signal Processing,Communication and Computing (ICSPCC 2013).Kunming,China.IEEE, 2013:1-4.
[12] 热比古丽·艾散, 贾振红, 覃锡忠, 等. 基于NSCT与FCM的多时相遥感图像的变化检测[J]. 激光杂志, 2014, 35(2):42-44.
[12] Rabigul H, Jia Z H, Qin X Z, et al. Based on NSCT combination with FCM multitemporal remote sensing image change detection[J]. Laser Journal, 2014, 35(2):42-44.
[13] Chen J, Chen X, Cui X, et al. Change vector analysis in posterior probability space:A new method for land cover change detection[J]. IEEE Geoscience and Remote Sensing Letters, 2011, 8(2):317-321.
[14] Malila W A. Change vector analysis:An approach for detecting forest changes with landsat[J]. Proceedings of the Society of Photo-Optical Instrumentation Engineers, 1980:326-336.
[15] 蔡怤晟, 向泽君, 蔡衡, 等. 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(8):101-104,130.
doi: 10.13474/j.cnki.11-2246.2020.0257
[15] Cai F S, Xiang Z J, Cai H, et al. CVA multi-scale remote sensing image change detection combined with feature selection[J]. Bulletin of Surveying and Mapping, 2020(8):101-104,130.
doi: 10.13474/j.cnki.11-2246.2020.0257
[16] 龙亦凡, 乔雯钰, 孙静. 基于SVM的大屯矿区遥感影像变化检测[J]. 测绘与空间地理信息, 2020, 43(12):107-110,115.
[16] Long Y F, Qiao W Y, Sun J. Change detection of remote sensing images in datun mining area based on support vector machine[J]. Geomatics & Spatial Information Technology, 2020, 43(12):107-110,115.
[17] 李轶鲲, 杨洋, 杨树文, 等. 耦合模糊C均值聚类和贝叶斯网络的遥感影像后验概率空间变化向量分析[J]. 自然资源遥感, 2021, 33(4):82-88.doi:10.6046/zrzyyg.2021032.
[17] Li Y K, Yang Y, Yang S W, et al. A change vector analysis in posterior probability space combined with fuzzy C-means clustering and a Bayesian network[J]. Remote Sensing for Natural Resources, 2021, 33(4):82-88.doi:10.6046/zrzyyg.2021032.
[18] 林明泽, 李轶鲲, 安新磊, 等. 简单贝叶斯网络的遥感图像检索[J]. 云南民族大学学报(自然科学版), 2010, 19(1):67-70.
[18] Lin M Z, Li Y K, An X L, et al. Remote sensing image retrieval based on the simple Bayesian network[J]. Journal of Yunnan University of Nationalities (Natural Sciences Edition), 2010, 19(1):67-70.
[19] Otsu N. A threshold selection method from gray-level histograms[J]. IEEE Transactions on Systems,Man,and Cybernetics, 1979, 9(1):62-66.
[20] DeGroot M H, Schervish M J. Probability and statistics[M]. Beijing: China Machine Press, 2021:495-506.
[1] WANG Zihao, LI Yikun, LI Xiaojun, YANG Shuwen. Noise-resistant change detection for remote sensing images based on spatial fuzzy C-means clustering and a Bayesian network[J]. Remote Sensing for Natural Resources, 2023, 35(4): 96-104.
[2] FU Yukai, YANG Shuwen, YAN Heng, XUE Qing, HONG Weili, SU Hang. An SAR and optical image fusion algorithm coupling non-local self-similarity and divergence[J]. Remote Sensing for Natural Resources, 2023, 35(1): 99-106.
[3] LI Yikun, YANG Yang, YANG Shuwen, WANG Zihao. A change vector analysis in posterior probability space combined with fuzzy C-means clustering and a Bayesian network[J]. Remote Sensing for Natural Resources, 2021, 33(4): 82-88.
[4] Xinran ZHU, Bo WU, Qiang ZHANG. An improved CVAPS method for automatic updating of LUCC classification[J]. Remote Sensing for Land & Resources, 2018, 30(2): 29-37.
[5] DING Haiyong, LUO Haibin, GUO Ruirui. Enhancement of remote sensing images based on NSCT and fuzzy theory[J]. REMOTE SENSING FOR LAND & RESOURCES, 2017, 29(3): 25-31.
[6] CHEN Jian-yu, GUO De-fang, HUANG Peng . THE IMPROVEMENT OF THE FUZZY CLUSTER METHOD FOR NOAA/AVHRR DATA COVERED WITH CLOUD[J]. REMOTE SENSING FOR LAND & RESOURCES, 2004, 16(4): 7-10.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
京ICP备05055290号-2
Copyright © 2017 Remote Sensing for Natural Resources
Support by Beijing Magtech