Yousef Ebadi; Akram Eftekhary; Hekmatollah Mohammad Khanlu; Majid Fakhri
Abstract
Introduction As an important type of precipitation, snow is especially important in the hydrological cycle. This importance can be examined and analyzed from several aspects such as water supply in other seasons. The most important aspect is the possibility of creating hazards for human beings and human ...
Read More
Introduction As an important type of precipitation, snow is especially important in the hydrological cycle. This importance can be examined and analyzed from several aspects such as water supply in other seasons. The most important aspect is the possibility of creating hazards for human beings and human infrastructure (snow avalanches, floods during seasonsof snowmelt). Therefore, it is necessary to study the snow phenomenon and its covered surfaces in winter. Monitoring the changes in this important climatic phenomenon has always been considered important by researchers and planners. Remote sensing methods have revolutionized the field of natural environment monitoring since their inception. Snow depth is an example of what can be monitored and evaluated by remotely sensed data and techniques. Materials & Methods The present study seeks to evaluate the efficiency of several important remote sensing indices in monitoring snow depth, andalso to introduce and evaluate a proposed spectral index. To reach this aim, satellite images of Landsat 8 and Sentinel 2 have been used. These images were received from the relevant portal and used to calculate snow indicesafterinitial corrections. Four spectral indices were usedto extract snow covered surfaces. These indices include: NDSI - S3 - NDSII - SWI. These indices are based on reflection from snow covered surfaces in light reflection and absorption spectra of snow covered surfaces.Light reflection from snow covered surfaces in the visible spectra and absorption in the short infrared spectrum allow automatic detection and extraction of snow covered surfacesin remote sensing multispectral images. The above mentioned indices have the ability to extract snow, but they fail to differentiatebetween snow and other related phenomena such as water (in the absorption band) and light-color salt marshes (in the reflection band) and thus, similarity of the spectra occurs. This spectral mixing which occurs due to the similarity of the reflections, cannot be eliminated even when threshold limits are defined. Thus, the extracted snow cover includes not only snow, but also other similar zones. To solve this problem and extract snow covered surfaces correctly,a new index is presented in this paper based on principal component analysis (PCA) and the first component of the set, and short wave infrared (SWIR) spectrum reflection.Using the first component of the set with the highest variance makes the difference between reflectance of snow and similar phenomena visible and thus, solves the issue of spectral mixing to a very large extent. The proposed new index called PCSWIRI is also evaluated and validated along with 4 other indices in the present paper. Results & Discussion Spectral indices introduced in the previous section were examined and evaluatedusing 7 sets of images (4 Landsat images and 3 sentinel 2images) captured in different days of winter from the main study area (Lake Urmia in the northwest) and two other study areas. The results indicate efficiency of the proposed index in the extractionof snow covered surfaces. The proposed index has improved the accuracy of snow cover extractionin the whole collection of images. This increased accuracy has been confirmed withstatistical evaluation criteria, such as kappa coefficient, overall accuracy and in the visual review of indices(comparing to the composition of the original image). The main study area includes Lake Urmia, an important geographic feature containing water and salt and a mixture of the two, which makes its spectrum similar to snow. This lake is incorrectly identified by other indices as a snow covered surface. Like the main study area, the first study and assessment area contains salt covered zones (salt lake). Despite the spectral similarity between snow and salt,the proposed index has been able to distinguish between this phenomena (in both regions) and snow and to extract only realsnow covered surfaces. In addition, visual review of existing water bodies (Dam Lake) and 5 evaluated indicesindicates higher accuracy of the proposed index. In order to automate the process of calculation in the proposed spectral indices, a software was also providedbased on MatLAB. Conclusion The findings of the present study indicates higher accuracy and efficiency of the proposed index (PCSWIRI) for snow cover extraction. Snow cover maps are very useful in various hydrological, climatic, precipitation-runoff modeling studies, and etc. Therefore, increasing the accuracy of snow cover maps is of great importance and results inimprovedaccuracy and reliability of modeling processes.
Saeed Ojaghi; safa khazai
Abstract
Extended Abstract
Land use/cover (LULC) change detection is one of the most important applications in the remote sensing field, providing insights that inform management, policy, and science. In the recent decade, development of remote sensing systems and accessibility to high spatial resolution images ...
Read More
Extended Abstract
Land use/cover (LULC) change detection is one of the most important applications in the remote sensing field, providing insights that inform management, policy, and science. In the recent decade, development of remote sensing systems and accessibility to high spatial resolution images has associated with the improvement of digital image processing. The advantage of high spatial resolution remote sensing imagery further supports opportunities to apply change detection with object-based image analysis, i.e. object-based change detection – OBCD.
OBCD analysis in comparison with pixel-based techniques provides a more effective way, especially in high spatial resolution imagery to incorporate spatial, spectral, textural and geometry feature that can identify the LULC change in comparison with pixel-based technique. OBCD approach is classified into for categories: (i) image-object, (ii) class-object, (iii) multi- temporal object, and (iv) hybrid change detection. Different algorithms and features can be employed in the process of image classification for OBCD. Therefore, the choice of algorithm and optimization features are major challenges in OBCD. This paper has introduced an object- based change detection method based on the machine learning algorithm, which can overcome the traditional change detection method limitation and find the interested changed objects. In this paper, multi-temporal object approach is utilized and high spatial resolution imagery, GeoEye-1 and Quick Bird-1 satellite images were acquired during 2002 and 2015, covering a region of the Geshm Island which were used to detect the meaningful detailed change in the study area. As an essential preprocessing for change detection, multi-temporal image registration with the accuracy of less than one second of a pixel is applied. Also, radiometric correction is performed using histogram matching algorithm in ENVI Software. In the Next step, a number of texture features of images such as mean, variance, entropy, homogeneity, momentum and such are extracted from two images. To reduce the input features space, PCA algorithm is employed and the result of this process is used in the segmentation process. The two images are incorporated with PCA output and are used as inputs feature to segmentation. Segmentation is the first step in OBCD. It divides the image into larger numbers of small image objects by grouping pixels. The segmentation algorithm is a region-merging technique. It begins by considering each pixel as a separate object. Subsequently, adjacent pairs of image objects are merged to form bigger segments. The merging decision is based on local homogeneity criterion, describing the similarity between adjacent image objects. Correct image segmentation is a prerequisite to successful image classification. At the same time, this task requires explicit knowledge representation. Furthermore, optimal segmentation results are depended on not only the choice of segmentation algorithm or procedure, but are also often influenced by the choice of user-defined parameter combinations which are required inputs for many segmentation programs. The segmentation has been done using multi resolution segmentation algorithm which involves knowledge-free extraction of image objects. Multi-resolution segmentation begins with single pixel objects and employs a region-growing algorithm to merge pixels into larger objects; pixels are merged based on whether they meet user-defined homogeneity criteria. Each multi-resolution segmentation task must be parameterized by the user and involves settings of three parameters: Scale, Color-versus-Shape, and Compactness-versus-Smoothness. In this paper the process of segmentation is performed in four different levels using Ecognition software and finally, the level with better output with scale of 100 is selected to provide the change map. The scale values were determined through an iterative method. The color/shape was set to 0.6/0.4 and compactness/sharpness was set to 0.5/0.5 for the selected level. Color and shape weightage are inter-connected to each other. If color has a high value, which means it has a high influence on segmentation; Shape must have a low value with less influence. If both parameters are equal, then each will have roughly equal amount of influence on segmentation outcome. In addition, texture, spatial and geometrical features from the segmented image are extracted. Feature space Optimization (FSO) tool available in Ecognition software have been used to calculate optimum feature combination based on class samples in four classes including: ”barren to road”, ”barren to building”, barren to vegetation” and “barren with no change. It evaluates the Euclidean distance in feature space between the samples of all classes and selects a feature combination resulting in best class separation distance. In this study, the performance of the proposed RF-based OBCD method is compared with the conventional methods such as support vector machine (SVM) and KNN. The commonly used accuracy assessment elements include overall accuracy, producer’s accuracy, user’s accuracy and the Kappa coefficient. The overall accuracy of the change map produced by the RF method was 86.57%, with Kappa statistic of 0.79, whereas the overall accuracy and Kappa coefficient of that by the SVM and NN methods were 83.76%, 0.75 and 75%, 0.63, respectively. Experimental results show that overall accuracy and kappa coefficient obtained from the proposed RF-based OBCD method improve 3% and 18%, 2% and 10% respectively compared with SVM and KNN improved. The results indicated that object base change detection method can be performed more accurately and reliably in the high-density region if it uses image with high spatial resolution. Also, selection of classification algorithm has very impressive effect on the providing change map.
Vahid Sadeghi; Hamid Enayati; Hamid Ebadi
Abstract
Analyzing multi-temporal remotelysensed images is an effective technique for detecting land useand land cover changes in urban areas. Apart from thetechnique used to detect the changes, the features space has an enormous impact on the accuracy of the results. Achieving satisfactory results in detecting ...
Read More
Analyzing multi-temporal remotelysensed images is an effective technique for detecting land useand land cover changes in urban areas. Apart from thetechnique used to detect the changes, the features space has an enormous impact on the accuracy of the results. Achieving satisfactory results in detecting changes inurban areasrequires the use of optimal spectral and spatial features (texture). Although global search is the only guarantees of achieving the optimal set of features, but it is a very timely and impractical process in practice. Data reduction techniquessuch as PCA considers the independence of the data tofind a smaller set of variables with less redundancy withoutintending to improve the CD accuracy. Difficulty in setting thebest threshold for JM distance in Separability Analysis Algorithm (SAA)reduces its efficiency. The main purpose of this paper is to select the optimaltextural and spectral features to enhance the CD accuracy usinggenetic algorithms (GA) and Bayesian classifier. To investigate the effectivenessof the proposed tecknique, a case study using IRS-P6and GeoEye1 satellite imagery taken from Sahand New Town (Northwest ofIran on July 15, 2006, andSeptember 1, 2013) was performed. All of the aforementioned methods of feature selection (PCA, SAA and proposed GA-based method) were implemented in MATLABR2013a. The results show that, textural features provides a complementary sourceof data for CD in urban areas. The results show thatfeature selection is an effective process fordetecting changes basedon textural and spectral features. Each of the techniques for selecting features has its own limitations and advantages, but in general, improve the CD accuracy. The proposed GA-based feature selectionapproach was found to be relatively effective when compared withPCA and SSA approaches. Overall accuracy and Kappa coefficient ofCD were increased from 53.66% to 88.49% and 58.94% to90.39%respectivelyusing proposed methods compared tothe use of spectral information.
Majid Danesh; Hosseinali Bahrami; Seyyed Kazem Alavipanah; Aliakbar Nowruzi
Volume 17, Issue 67 , October 2008, , Pages 26-34
Abstract
Soil texture and lime can be considered as amongst the most important soil characteristics, which are considered in many agricultural and environmental projects. Today, with the scientific progress and the advent of remote sensing technology, the possibility of exploiting this technology in soil science ...
Read More
Soil texture and lime can be considered as amongst the most important soil characteristics, which are considered in many agricultural and environmental projects. Today, with the scientific progress and the advent of remote sensing technology, the possibility of exploiting this technology in soil science has also been provided. In this study, for the analysis of soil texture and lime in the Pol Dokhtar area, the four-spectral data for September 7, 2007 prepared by IRS-P6 satellite with LISS III sensors were used. Geometric corrections and processes including UNC, SLED, NDVI, PCA, were performed on the main image. Finally, using randomized sampling method and based on PMU, FCC image of the region, 95 points were selected and samples were taken from two depths of 0-5 and 20-5 cm. Finally, using multiple regression, it was found that the lime and clay of samples at the first depth had a significant relationship with the near infrared band with modified R2 =0.73, and in the green band it was 0.72, and also at the second depth, with a red band of 0.54 and a green band of 0.48, of which all relationships were statistically significant at 1% statistical level. Consequently it was found that clay and lime have a significant effect on the spectral reflection from the soil surface in the region, and it is possible to study them in the region using satellite data and auxiliary data (incidental information).