Fuzzy clustering algorithms for unsupervised change detection in remote sensing images

Ghosh, Ashish; Mishra, Niladri Shekhar; Ghosh, Susmita

doi:10.1016/j.ins.2010.10.016

Cited by 289 publications

(152 citation statements)

References 64 publications

Supporting

Mentioning

129

Contrasting

Unclassified

Order By: Relevance

“…The change magnitude image between bi-temporal images can be obtained mainly by image differencing [14], image ratio [15,16], change vector analysis (CVA) [17][18][19][20], and spectral gradient difference [21]. Then, a binary threshold is needed to divide the change magnitude image into a binary change detection map; the popular threshold determining methods for change detection are mainly expectation maximization (EM) [22,23], fuzzy c-means [24][25][26], and Otsu's method [27][28][29]. In general, these methods measure the distance between the bi-temporal images and use a threshold to determine whether each pixel in the change magnitude image is changed or unchanged.…”

Section: Introductionmentioning

confidence: 99%

Post-Processing Approach for Refining Raw Land Cover Change Detection of Very High-Resolution Remote Sensing Images

Lv¹,

Liu²,

Wan

et al. 2018

Remote Sensing

View full text Add to dashboard Cite

Abstract:In recent decades, land cover change detection (LCCD) using very high-spatial resolution (VHR) remote sensing images has been a major research topic. However, VHR remote sensing images usually lead to a large amount of noises in spectra, thereby reducing the reliability of the detected results. To solve this problem, this study proposes an object-based expectation maximization (OBEM) post-processing approach for enhancing raw LCCD results. OBEM defines a refinement of the labeling in a detected map to enhance its raw detection accuracies. Current mainstream change detection (preprocessing) techniques concentrate on proposing a change magnitude measurement or considering image spatial features to obtain a change detection map. The proposed OBEM approach is a new solution to enhance change detection accuracy by refining the raw result. Post-processing approaches can achieve competitive accuracies to the preprocessing methods, but in a direct and succinct manner. The proposed OBEM post-processing method synthetically considers multi-scale segmentation and expectation maximum algorithms to refine the raw change detection result. Then, the influence of the scale of segmentation on the LCCD accuracy of the proposed OBEM is investigated. Four pairs of remote sensing images, one of two pairs (aerial image with 0.5 m/pixel resolution) which depict two landslide sites on Landtau Island, Hong Kong, China, are used in the experiments to evaluate the effectiveness of the proposed approach. In addition, the proposed approach is applied, and validated by two case studies, LCCD in Tianjin City China (SPOT-5 satellite image with 2.5 m/pixel resolution) and Mexico forest fire case (Landsat TM images with 30 m/pixel resolution), respectively. Quantitative evaluations show that the proposed OBEM post-processing approach can achieve better performance and higher accuracies than several commonly used preprocessing methods. To the best of the authors' knowledge, this type of post-processing framework is first proposed here for the field of LCCD using VHR remote sensing images.

show abstract

Section: Introductionmentioning

confidence: 99%

Post-Processing Approach for Refining Raw Land Cover Change Detection of Very High-Resolution Remote Sensing Images

Lv¹,

Liu²,

Wan

et al. 2018

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Ghosh ve ark. 2011 yılında yaptıkları çalışmalarda geliştirdikleri kontrolsüz değişim yaklaşımı ile hem yangın hem de su taşkını neticesinde ortaya çıkan tahribatın otomatik olarak belirlenebileceğini göstermişlerdir [16].…”

Section: Introductionunclassified

Afet Yöneti̇mi̇nde Opti̇k Görüntüler İçi̇n Dalgacik Dönüşümü Ve Gaussian Karişim Modelleri̇ Tabanli Yeni̇ Bi̇r Deği̇şi̇m Saptama Yaklaşimi

Atasever

2018

Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi

View full text Add to dashboard Cite

ÖZOrman yangını, taşkın gibi felaketler hem ülkemizin hem de dünyanın en önemli problemleri arasındadır Afet sonrası alansal rehabilitasyon işlemlerinin hızla yapılabilmesi için zarar gören alanların hızlı ve yüksek doğrulukla belirlenebilmesi gerekmektedir. Bu çalışmada, optik görüntüler için tasarlanmış, yangın ve sel gibi afetler sonrasında hasar gören alanların tespit edilmesine yönelik dalgacık dönüşümü ve Gaussian karışım modelleri temelli yeni bir yaklaşım önerilmiştir. Sunulan yaklaşımın ilk aşamasında, afet öncesi ve sonrasına ait görüntülerin standart ve logaritmik fark görüntüleri hesaplanır. İkinci aşamada standart fark görüntüsüne medyan filtre, logaritmik fark görüntüsüne wiener filtre uygulanır. Ardından bu görüntüler dalgacık dönüşümü ile birleştirilir. Son aşamada ise birleştirilmiş görüntü Gaussian karışım modelleri ile kümelenir ve böylelikle afet nedeniyle zarar gören alanlar tespit edilmiş olur. Yaklaşımın etkinliği gerçek afetler neticesinde ortaya çıkan Sardinia ve Mexico veri setleri kullanılarak irdelenmiştir. Önerilen yaklaşımın performansı toplam hata ve toplam hata oranı kriterlerine ek olarak ortalama karesel hata, tepe gürültü sinyal oranı, yapısal benzerlik indeksi ve evrensel kalite indeksi metrikleri ile incelenmiş ve başarısı ortaya koyulmuştur.Anahtar Kelimeler: Afet, Değişim Saptama, Dalgacık Dönüşümü, Gaussian Karışım Modelleri A NEW CHANGE DETECTION APPROACH BASED ON WAVELET TRANSFORMATION AND GAUSSIAN MIXTURE MODELS FOR OPTICAL IMAGERY IN DISASTER MANAGEMENT ABSTRACTDisasters such as forest fires and floods are among most important problems of both our country and the world. In order to be able to perform rapid rehabilitation processes after disaster, damaged areas should be determined with high accuracy quickly. In this study, a new approach, designed for optical images, based on wavelet transform and Gaussian mixture models is proposed for detection of damaged areas after disasters such as fire and flood. In the first step of the presented approach, standard and logarithmic difference images from images belonging before and after disaster are calculated. Second, median filter to standard difference image and wiener filter to logarithmic difference image are applied, respectively. After that, these images are fused with wavelet transformation. Lastly, fused image is clustered with Gaussian mixture models and thus the areas damaged by the disasters are identified. The effectiveness of the approach was explored using Sardinia and Mexico data sets resulting from real disasters. The performance of the proposed approach has been investigated and its success has been shown with the mean squared error, peak signal to noise ratio, structural similarity index and universal quality index metrics, in addition to the total error and total error rate criteria.

show abstract

“…In recent years, various methods based on remote sensing images, such as image difference [14,15], image ratio [11], change vector analysis (CVA) [16,17], and principal component analysis-based change detection methods (CD_PCA_Kmeans) [1], have been developed. In addition, pixel-based post-classification change detection can provide the "from to" change information compared with the binary change detection technique [18][19][20][21][22].…”

Section: Introductionmentioning

confidence: 99%

Semi-Automatic System for Land Cover Change Detection Using Bi-Temporal Remote Sensing Images

Shi

Zhou

et al. 2017

Remote Sensing

View full text Add to dashboard Cite

Abstract:Change detection is an increasingly important research topic in remote sensing application. Previous studies achieved land cover change detection (LCCD) using bi-temporal remote sensing images. However, many widely used methods detected change depending on a series of parameters, and determining parameters is time-consuming. Furthermore, numerous methods are data-dependent. Therefore, their degree of automation should be improved significantly. Three techniques, which consist of a semi-automatic change detection system, are proposed for LCCD to overcome the abovementioned drawbacks. The three techniques are as follows: (1) change magnitude image (CMI) noise reduction is based on Gaussian filter (GF), which is coupled with OTSU for reducing CMI noise automatically using an iterative optimization strategy; (2) a method based on histogram curve fitting is suggested to predict the threshold range for parameter determination; and (3) a modified region growing algorithm is built for iteratively constructing the final change detection map. The detection accuracies of the proposed system are investigated through four experiments with different bi-temporal image scenes. Compared with several widely used change detection methods, the proposed system can be applied to detect land cover change with high accuracy and flexibility. This work is an attempt to provide a change detection system that is compatible with remote sensing images with high and median-low spatial resolution.

show abstract

Fuzzy clustering algorithms for unsupervised change detection in remote sensing images

Cited by 289 publications

References 64 publications

Post-Processing Approach for Refining Raw Land Cover Change Detection of Very High-Resolution Remote Sensing Images

Post-Processing Approach for Refining Raw Land Cover Change Detection of Very High-Resolution Remote Sensing Images

Afet Yöneti̇mi̇nde Opti̇k Görüntüler İçi̇n Dalgacik Dönüşümü Ve Gaussian Karişim Modelleri̇ Tabanli Yeni̇ Bi̇r Deği̇şi̇m Saptama Yaklaşimi

Semi-Automatic System for Land Cover Change Detection Using Bi-Temporal Remote Sensing Images

Contact Info

Product

Resources

About