• ISSN 1004-0323     CN 62-1099/TP
• 联合主办：中国科学院遥感联合中心
• 中国科学院兰州文献情报中心
• 中国科学院国家空间科学中心

,, ,,

## An Improved CVA Change Detection Method Combining Spatial and Spectral Information

,, ,,

School of Electronic and Information Engineering, Nanjing University of Information Science and Technology, Nanjing 210044, China

 基金资助: 国家自然科学基金项目.  61601229江苏省自然科学基金项目.  BK20160966江苏省高校自然科学基金项目.  16KJB510022信国家重点实验室开放研究基金项目.  2012D20江苏省高等学校优势学科项目.  1081080015001

Received: 2018-04-25   Revised: 2019-04-27   Online: 2019-09-19

Abstract

Change detection based on change vector analysis can quickly extract change information between multi-temporal images by directly comparing pixel differences. However, because the spatial context information in the pixel field and the difference and complementarity between bands are ignored, it is difficult to eliminate the "pseudo-changes" caused by noise and other factors in the detection results. In view of this, this paper proposes a method for detecting changes in spatial and spectral information. Firstly, the image is enhanced by the principal component analysis method, and then spatial context information of pixels is extracted by constructing a new multi-directional differential descriptor; On this basis, a spectrally weighted fusion strategy based on inter-band correlation is proposed to obtain a uniform variation intensity difference image Finally, the EM algorithm is adopted to confirm the final change pixels. The experimental results show that the proposed algorithm can effectively deal with the "pseudo-change" interference and significantly improve the accuracy and reliability of the change detection.

Keywords： CVA ; Change detection ; Multidirectional ; Spectral weighting ; EM algorithm

Shen Yi, Wang Chao, Hu Jiale. An Improved CVA Change Detection Method Combining Spatial and Spectral Information. Remote Sensing Technology and Application[J], 2019, 34(4): 799-806 doi:10.11873/j.issn.1004-0323.2019.4.0799

## 1 引 言

### 图1

Fig.1   Change detection process of remote sensing image

### 2.1　主成分分析法

#### 2.2.2　多方向差分描述子模型

$FT,n(u,v)$表示影像第$T(T=1,2)$时相$n(n=1,2,3)$主分量中$(u,v)$点的灰度值，$FT,n(u+Δφ,v)$$FT,n(u,v+Δφ)$分别代表$T(T=1,2)$时相$n$主分量中与$(u,v)$点水平和竖直方向上相差$Δφ$像素的灰度值。求取第2时相变化灰度值的3阶多方向差分描述子如图2所示。

### 图2

Fig.2   Multi-directional difference descriptor

$x2,nu,v=x1+x8+x7-(x3+x4+x5)$
$y2,nu,v=x1+x2+x3-(x7+x6+x5)$

$D2,n(u,v)=x2,n(u,v)2+y2,n(u,v)2$

#### 2.3　融合策略

$λn=1pn⋅1S$

$D̂2(u,v)=∑n=1,2,3D2,n(u,v)·λn$

#### 2.4　EM算法

$p(hkφ)=12πδφexp[-(hk-μφ)2δφ2]$

$p(hk)=p(wc)×p(hkwc)+p(wn)×p(hkwn)$

$pt+1(φ)=∑k=1npt(φ|hk)n$
$μφt+1=∑k=1npt(φ|hk)⋅hk∑k=1npt(φ|hk)$
$(δφt+1)2=∑k=1npt(φ|hk)(hk-μφt)2∑k=1npt(φ|hk)$

$p(φ|hk)=p(hk|φ)p(φ)p(hk)$

### 图3

Fig.3   The first experimental data

### 图4

Fig.4   Detection results of the first experimental data

Table 1  The Accuracy and error of change detection of the first experimental data

/个

/个

/个

Kappa

/%

CVA-EM3 7122 1141 5980.623 1

### 图6

Fig.6   Results of the second experimental data

### 图5

Fig.5   The second experimental data

Table 2  The Accuracy and error of change detection of the second experimental data

CVA-EM4 2782 1562 1220.603 9

### 图7

Fig.7   The effect of threshold on wrong pixels

## 参考文献 原文顺序 文献年度倒序 文中引用次数倒序 被引期刊影响因子

RoganJ, ChenD M.

Remote Sensing Technology for Mapping and Monitoring Land-Cover and Land-Use Change

[J]. Progress in Planning, 2004, 61(4):301-325.

ChenX L, ZhaoH M, LiP X, et al.

Remote Sensing Image-based Analysis of the Relationship between Urban Heat Island and Land Use/Cover Changes

[J]. Remote Sensing of Environment, 2006, 104(2):133-146.

Z Y, ShiW Z, ZhouX C, et al.

Semi-automatic System for Land Cover Change Detection Using Bi-temporal Remote Sensing Images

[J]. Remote Sensing, 2017, 9(11):1112-1124.

Z Y, ShiW, ZhangX, et al.

Landslide Inventory Mapping from Bitemporal High-resolution Remote Sensing Images Using Change Detection and Multiscale Segmentation

[J]. IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing, 2018, 11(5):1520-1532.

FengW, SuiH, TuJ, et al.

A Novel Change Detection Approach based on Visual Saliency and Random Forest from Multi-temporal High-resolution Remote Sensing Images

[J]. International Journal of Remote Sensing, 2018, 39(22):7998-8021.

SabryR, AinsworthT L.

SAR Compact Polarimetry for Change Detection and Characterization

[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2019, 12(3):898-909.

MalilaW A.

Change Vector Analysis: An Approach for Detecting Forest Changes with Landsat

[C]∥LARS Symposia. 1980: 385-397.

BruzzoneL, PrietoD F.

Automatic Analysis of the Difference Image for Unsupervised Change Detection

[J]. IEEE Transactions on Geoscience & Remote Sensing, 2000, 38(3):1171-1182.

ZhuangH, DengK, FanH, et al.

Strategies Combining Spectral Angle Mapper and Change Vector Analysis to Unsupervised Change Detection in Multispectral Images

[J]. IEEE Geoscience & Remote Sensing Letters, 2017, 13(5):681-685.

XiaoMinghong, FengWenqing, HaigangSui .

Remote Sensing Image Change Detection Algorithm based on Super-pixel Segmentation and Multiple Difference Maps

[J]. Bulletin of Surveying and Mapping, 2018(10):101-105,129.

[J]. 测绘通报, 2018(10):101-105,129.

HuangWei, HuangJinliang, WangLihui, et al.

Remote Sensing Image Change Detection based on Change Vector Analysis of PCA Component

[J]. Remote Sensing for Land & Resources, 2016, 28(1):22-27.

[J]. 国土资源遥感, 2016, 28(1):22-27.

ZanettiM, BruzzoneL.

A Theoretical Framework for Change Detection based on a Compound Multiclass Statistical Model of the Difference Image

[J]. IEEE Transactions on Geoscience & Remote Sensing, 2018, 56(2):1129-1143.

ZhuangH, DengK, YangY, et al.

An Approach based on Discrete Wavelet Transform to Unsupervised Change Detection in Multispectral Images

[J]. International Journal of Remote Sensing, 2017, 38(17):4914-4930.

SartajvirS, RajneeshT.

Response of Fuzzy Clustering on Different Threshold Determination Algorithms in Spectral Change Vector Analysis over Western Himalaya, India

[J]. Journal of Mountain Science, 2017, 14(7):1391-1404.

DewiR, BijkerW, SteinA.

Change Vector Analysis to Monitor the Changes in Fuzzy Shorelines

[J]. Remote Sensing, 2017, 9(147):1-28.

PerlibakasV.

Face Recognition Using Principal Component Analysis of the Wavelet Packet Decomposition

[J]. Social Science Electronic Publishing, 2017, 15(15):243-250.

WuZ, HuangY, ZhangK.

Remote Sensing Image Fusion Method based on PCA and Curvelet Transform

[J]. Journal of the Indian Society of Remote Sensing, 2018(3):1-9.

MengJ, LeiW.

Novel Class-relativity Non-local Means with Principal Component Analysis for Multitemporal SAR Image Change Detection

[J]. International Journal of Remote Sensing, 2018, 39(4):1068-1091.

WangY, QiQ, YingL.

Unsupervised Segmentation Evaluation Using Area-weighted Variance and Jeffries-Matusita Distance for Remote Sensing Images

[J]. Remote Sensing, 2018, 10(8):105-117.

BoC, FangQ, WuB, et al.

Image Segmentation based on Constrained Spectral Variance Difference and Edge Penalty

[J]. Remote Sensing, 2015, 7(5):5980-6004.

/

 〈 〉