一种用于遥感图像自动变化检测的特征描述符外文翻译资料

The Egyptian Journal of Remote Sensing and Space Sciences xxx (xxxx) xxx

Contents lists available at ScienceDirect

The Egyptian Journal of Remote Sensing and Space Sciences

journal homepage: www.sciencedirect.com

Research Paper

A novel feature descriptor for automatic change detection in remote

sensing images ^q

C.P. Dalmiya ^a,1,uArr;, N. Santhi ^a,2, B. Sathyabama

b,3

^a Department of ECE, Noorul Islam Centre for Higher Education, Kumaracoil, Thuckalay, Kanyakumari, Tamil Nadu 629180, India

^b Department of ECE, Thiagarajar College of Engineering, Madurai, Tamil Nadu 625015, India

a r t i c l e i n f o

a b s t r a c t

Article history:

Automatic change detection has expected increasing interest for researchers in recent years on high-

spatial resolution remote sensing system where multispectral, multi-resolution and multimodal images

can be acquired. The commonly used techniques for high-resolution change detection rely on feature

extraction. Due to its high dimensional feature space, the conventional feature extraction techniques rep-

resent a progress of issues when handling huge size information e.g., computational cost, processing

capacity and storage load. In order to overcome the existing drawback, we propose a novel Structural

Phase Congruency Histogram (SPCH) descriptor for automatic change detection without reducing the sig-

nificant loss of information. The proposed feature extractor depends upon the structural properties of the

image which is invariant to contrast deviations and illumination. The structural phase congruency with

the histograms is combined to build the edge and corner features. The dimensionality of the feature vec-

tor is reduced using Linear Discriminant Analysis (LDA) to form SPCH-LDA descriptor which leads to be

more robust for image scale variations. Finally, the accuracy of the change detection is estimated with

Artificial Neural Network (ANN) as compared with the existing algorithms. The experimental results pro-

vided 98.4375% accuracy which confirms the effectiveness and superiority of the proposed technique for

automatic change detection.

Received 12 August 2017

Revised 1 March 2018

Accepted 19 March 2018

Available online xxxx

Keywords:

Change detection

Feature extraction

Classifier

Dimension reduction

Oacute; 2018 National Authority for Remote Sensing and Space Sciences. Production and hosting by Elsevier B.

V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-

nc-nd/4.0/).

1. Introduction

application involved in multi-temporal datasets. Automatic change

detection expects to identify land cover variations between two

Remote Sensing images are generally utilized for viewing the

urban extension and land cover changes at a medium to enable

the advancement of urbanization and propel the practical

improvement process. In remote sensing applications, changes

are considered as surface component alterations with varying

rates. Change detection is one of the main applications of remote

sensing that quantitatively examines the temporal impacts of

registered remote sensing images obtained over the same topo-

graphical location at two diverse time moments (Neagoe et al.,

2014). The general objectives of change detection in remote sens-

ing include identifying the geographical location and type of

changes, quantifying the changes, and assessing the accuracy of

change detection results (Hussain et al., 2013). Change detection

from multi-temporal remotely sensed images is widely used in

many fields, such as land use/land cover change (Amini and

Hesami, 2017), irrigated land change (Hesami and Amini, 2016)

urban growth, forest and vegetation dynamics, and disaster moni-

toring, since many types of changes can be extracted at local, regio-

nal, and global scale (Du et al., 2013; Chen et al., 2012a,b). In

change detection of remote sensing images, the researchers mainly

focussed on change measure, and then they created methods for

classifying changed features (Liu et al., 2012).

Peer review under responsibility of National Authority for Remote Sensing and

Space Sciences.

uArr;

Corresponding author.

E-mail address: dalmiya2017@gmail.com (C.P. Dalmiya).

1

Current designation details with college name: Research Scholar, ECE Depart-

ment, Noorul Islam Centre for Higher Education, Kumaracoil, Thuckalay, Kanyaku-

mari, Tamil Nadu 629180, India.

2

Current designation details with college name: Associate Professor, ECE Depart-

Generally, change detection methods can be partitioned into

two classes: supervised and unsupervised. The supervised classifi-

cation needs learning knowledge about the study territory for

training the detection module, for example, Artificial Neural

ment, Noorul Islam Centre for Higher Education, Kumaracoil, Thuckalay, Kanyaku-

mari, Tamil Nadu 629180, India.

3

Current designation details with college name: Associate Professor, ECE Depart-

ment, Thiagarajar College of Engineering, Madurai, Tamil Nadu 625015, India.

https://doi.org/10.1016/j.ejrs.2018.03.005

1110-9823/Oacute; 2018 National Authority for Remote Sensing and Space Sciences. Production and hosting by Elsevier B.V.

This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Please cite this article as: C. P. Dalmiya, N. Santhi and B. Sathyabama, , The Egyptian Journal of Remote Sensing and Space Sciences, https://doi.org/10.1016/lt;

剩余内容已隐藏，支付完成后下载完整资料

英语译文共 16 页，剩余内容已隐藏，支付完成后下载完整资料

资料编号：[609471]，资料为PDF文档或Word文档，PDF文档可免费转换为Word