Marjan Teheri; MahmodReza Sahebi; Mehrnoosh Omati
Abstract
Synthetic aperture radar (SAR) sensors with various properties offer potential in various remote sensing applications, such as land cover and land use segmentation. Despite the two independent approaches of region-based segmentation and boundary-based segmentation, it isn't easy to obtain satisfactory ...
Read More
Synthetic aperture radar (SAR) sensors with various properties offer potential in various remote sensing applications, such as land cover and land use segmentation. Despite the two independent approaches of region-based segmentation and boundary-based segmentation, it isn't easy to obtain satisfactory results if either process is used in SAR images. In contrast, complementary information can be obtained using both region-based and boundary-based segmentation methods, removing existing limitations and improving results.In this research, with the help of polarimetric SAR images, a new segmentation method is presented, aiming to improve segmentation results by combining the two region-based and boundary-based approaches. From the set of superpixel methods, the Felzenszwalb method as a proposed region-based algorithm is compared with Quickshift and SLIC methods. The proposed method was able to prevent over-segmentation of the image and significantly increased the efficiency of segmentation analysis. Also, as the proposed method of boundary-based segmentation, Shannon entropy has considerably preserved the boundaries of the image segmentation compared to the two gradient-based methods, Canny and Laplacian. Comparison of the results of this method with reference data shows the total error of 10.39% and 11.25% for the first and second-time images, respectively. Compared to the performance of the other two methods, the absolute error has been decreased to 5.81% and 9.73% in the first image, and 11.16% and 13.86% in the second image, respectively. Finally, as a significant achievement of this research, integrating the two proposed segmentation algorithms improves the accuracy of polarimetric image segmentation.
Mohsen Esmail nezhad soltanloo; Mahmod Reze Sahebi
Volume 10, Issue 4 , February 2019, , Pages 121-144
Abstract
Polarimetric Interferometric SAR (POLINSAR) data by providing wealth of information containing intensity, polarimetric and interferometric measurements, have shown many capability of mentioned data in the land cover classification. These three componentes of POLINSAR data could be found independently ...
Read More
Polarimetric Interferometric SAR (POLINSAR) data by providing wealth of information containing intensity, polarimetric and interferometric measurements, have shown many capability of mentioned data in the land cover classification. These three componentes of POLINSAR data could be found independently in the Shannon entropy of POLINSAR data. These components play a complementary role in the classification where the presence of interferometric information improves the classification results. As well as the data acquired form the real world has spatial connectivity so considering the neighboring and spatial connectivity in the classification process is essential and useful. So in this paper Markov Random Field segmentation algorithm has been used for classification of Shannon Entropies of POLINSAR data. In order to provide a Markovian field for the MRF classification, an initialization method has been proposed where classifies the image into 16 classes according to the polarimetric and interferometric entropy and anisotropy and merges the clusters obtained to 8 clusters using equality test of coherency matrices. The purity indices (PI) of the clusters obtained over the POLINSAR data acquired by DLR (German Aerospace center) E-SAR have been used to evaluate the effectiveness of the Entropy based MRF classification. The proposed method has been compared with the –Wishart (), -Wishart (, -FCM ( and FCM clustering using Shannon Entropy parameters where this comparisons show approximately 28%, 11%, 17% and 20% increasing in the Purity Indices respectively.
S Salehi; M.J Valadan Zoej; M. Sahebi
Volume 9, Issue 2 , December 2017, , Pages 21-40
Abstract
In applications related to environmental monitoring and disaster management, multichannel synthetic aperture radar (SAR) data present a great potential, owing both to their insensitivity to atmospheric and Sun-illumination conditions and to the improved discrimination capability they may provide as compared ...
Read More
In applications related to environmental monitoring and disaster management, multichannel synthetic aperture radar (SAR) data present a great potential, owing both to their insensitivity to atmospheric and Sun-illumination conditions and to the improved discrimination capability they may provide as compared with single-channel SAR. However, exploiting this potential requires accurate and automatic techniques to generate change maps from images acquired over the same geographic region in different polarizations or at different frequencies at different times. Furthermore, sensitivity to contextual information of each pixel reduces the error rates in labeling process, thus generates accurate change maps. The smoothing effect of despeckling and the isotropic formulation of the Markov Random Field model cause over-smoothing of the spatial boundaries between changed and unchanged areas in the final change maps. In order to reduce this drawback, edge-preserving MRF models could be integrated in the labeling process. This method improves the precision of edges at spatial boundaries and increases the change detection accuracy. In this paper, a contextual unsupervised change-detection technique (based on a data-fusion approach) is proposed for two-date multichannel SAR images. A Markov Random Field model is formulated by using “energy functions” that combines the information conveyed by each SAR channel, the spatial contextual information concerning the correlation among neighboring pixels and the edge information. In order to estimate the model parameters, the expectation–maximization algorithm is combined with the recently proposed “method of log-cumulants.” The proposed technique was experimentally validated with semisimulated data produced by ASAR-ENVISAT images. Experiments illustrate a significant improvement (average 12%) with the proposed technique over the other change detection approaches. Integrating edge information yielded accurate results in exploiting various levels of changes (low-medium-high) whereas contextual information and information conveyed by channels were unable to detect low and medium level changes. Considering the small number of iterations, computation time is reduced considerably. Generally the highest accuracy achieved by the proposed algorithm is 99/67%.
, Y Rezaei; , M.J. Valadan Zouj; , M.R Sahebi
Volume 9, Issue 1 , October 2017, , Pages 1-16
Abstract
Mountain Glaciers are pertinent indicators of climate change and their surface velocity changes, are an essential climate variable. In order to retrieve the climatic signature from surface velocity, large scale study of glacier changes is required. Satellite remote sensing is an effective way to derive ...
Read More
Mountain Glaciers are pertinent indicators of climate change and their surface velocity changes, are an essential climate variable. In order to retrieve the climatic signature from surface velocity, large scale study of glacier changes is required. Satellite remote sensing is an effective way to derive mountain glacier surface velocities. In this research, we have conducted a comprehensive assessment of Alam-Chal glacier surface changes (include displacement and velocity), all based on remotely-sensed data. All datasets include aerial photos and satellite images were ortho rectified, normalized and co-registered. By using an aerial photograph collected in 1955 as a baseline and comparing it against a 2003 image collected by the SPOT satellite, the glacier retreat, in direct response to changes in local climate conditions were extracted. Furthermore, we have assessed short-term changes over two-time scales (1988-2003, 2003-2005),using an aerial photo acquired in 1988, a 2003 SPOT image, and a high-resolution Quick Bird image collected over the study area in 2005. We have derived accurate glacier surface velocity vectors (RMSE~2m), based on an FFT-based image cross-correlation technique. Our results point to the capability of the proposed method in accurately retrieving glacier surface changes at a high level of spatial detail, which is important for studies of regional climate change.
Jadidi Milad Niroumand; Mehdi Mokhtarzade; Mahmood Reza Sahebi
Volume 7, Issue 3 , November 2015, , Pages 1-16
Abstract
The mixed pixels are considered as a major challenge in land cover mapping procedure from satellite imagery. Developments of the spectral unmixing and soft classification methods have provided the possibility for estimation of class proportions within the pixels. However, sub-pixel land cover mapping ...
Read More
The mixed pixels are considered as a major challenge in land cover mapping procedure from satellite imagery. Developments of the spectral unmixing and soft classification methods have provided the possibility for estimation of class proportions within the pixels. However, sub-pixel land cover mapping requires the spatial allocation of the sub-pixels. Recently, the Super Resolution Mapping (SRM) techniques have been developed for optimization of the sub-pixels spatial arrangement using the outputs of soft classifiers and based on the concepts of spatial dependency. In this research, the overall capability of the simulated annealing algorithm was evaluated through sub-pixel land cover mapping of the study area. To do so, a novel method was proposed for generating new solutions in each step of the algorithm and then the results were compared to the traditional method. On the other hand, the effective parameters on the performance of the algorithm (e.g. zoom factor, cooling function type, static and dynamic iterations) were investigated. According to the obtained results, higher values of zoom factor yields more promising overall accuracy . Also, the geometric function was found as the optimal cooling function with respect to the overall accuracy and processing speed. Meanwhile, dynamic iterations demonstrated more accuracy than the static case. As another key result of the paper, the proposed method for generating the new solutions in simulated annealing algorithm is led to increasing of the overall accuracy and also reducing the processing time of algorithm up to 50 percent. The most accurate result of the proposed algorithm, which was obtained for the that case of being independent from soft classifier, is determined 94.97 percent
Volume 6, Issue 3 , October 2014
Abstract
Remote sensing can be used as a powerful tool by using data from different sources and combine them for vegetation and land cover classification. Pasture type classification provides key information for analysis of agricultural productivity, carbon accounting and biodiversity.The firstdata set thatused ...
Read More
Remote sensing can be used as a powerful tool by using data from different sources and combine them for vegetation and land cover classification. Pasture type classification provides key information for analysis of agricultural productivity, carbon accounting and biodiversity.The firstdata set thatused in thisstudyLandsatTM (Thematic Mapper)optical image and the second ENVISAT ASAR radar image for the study area located within the North-West of Tehran (South Alborz). In this study after applying several methods which all of them are non-lambertian and regarding to evaluate them, topographic correction was performed for optical image. The usefulness and improvement of using texture features extracted from optical and radar images in integration with spectral bands of the optical image has been evaluated on the final classification results and genetic algorithm used to select features that are independent to derive the most accurate results. In another part of the study, the impact of elevation data and optical image vegetation indices evaluated on final classification result and optimal bands selected. The results indicate increase in the overall accuracy and maximum likelihood Kappa coefficientfrom 77.04 and 0.7317 for original optical image to 78.71 and 0.7495 incaseof usinggenetic algorithm and 83.37 and 0.8036 incaseof usingelevation data and vegetation indices. Keywords:Image Fusion, Pasture Classification, Topographic Correction, Image Texture, Remote Sensing.
Volume 6, Issue 2 , August 2014
Abstract
Morphology analysis which concentrates on spatial relations analysis between neighborhood pixels provides a better image processing compared to analyses which are only based on spectral signature of a single pixel. The proposed method in this paper integrates spectral and spatial information produced ...
Read More
Morphology analysis which concentrates on spatial relations analysis between neighborhood pixels provides a better image processing compared to analyses which are only based on spectral signature of a single pixel. The proposed method in this paper integrates spectral and spatial information produced from morphology analysis to improve the final result of hyper spectral image classification. For this reason at first, primary components are extracted using limited training samples. Extended morphological profiles are then produced by applying morphological analysis on each extracted features. Afterwards, Final components are extracted by applying a supervised feature selections on a datasets composed of both the spectral and the extended morphological features. The extracted features are introduced into the Support Vector Machine (SVM) algorithm. The final results are then archived by implementing a majority filter as a post-processing step. The proposed method is implemented on aerial hyper spectral images of Rosis sensor taken from urban and semi-urban areas from. The obtained results proved the efficiency of the proposed method where classification accuracies are improved from 98.86 and 82.70 in conventional method to 99.36 and 95.75 in urban and semi-urban areas respectively. Keywords: Morphological Analysis, Support Vector Machines (SVMS), Feature Extraction (FE), Classification, Majority Vote
Volume 6, Issue 2 , August 2014
Abstract
The increasing concentration of greenhouse gases has been identified as a main cause of increase of global mean temperatures since the mid-20th century. The effect of human-induced climate change could be unprecedented and far-reaching. Carbon sequestration into trees and forests is an effective and ...
Read More
The increasing concentration of greenhouse gases has been identified as a main cause of increase of global mean temperatures since the mid-20th century. The effect of human-induced climate change could be unprecedented and far-reaching. Carbon sequestration into trees and forests is an effective and inexpensive way for mitigating the CO2 level in the atmosphere. Hence, accurate measurement of biomass will be of great importance to global carbon cycle and climate change. This study performed a wavelet-based forest aboveground biomass estimation approach in a temperate deciduous forest, Kheyroud Kenar forest in north part of Iran. Wavelet analysis, specifically two-dimensional discrete wavelet transform (DWT) was applied to ALOS PALSAR images to obtain wavelet coefficients (WCs), which were correlated with forest inventory data using multiple linear regression analysis to investigate the relationship. The results indicate that Db wavelet coefficients correlate better with field biomass data than other parameters. For the first level of the decomposition, the correlation coefficient is 0.5 while for second level, the overall R value increased up to 0.75. This study demonstrates that wavelet-based biomass estimation could be a very promising approach for providing better biomass estimation; however, further research is needed for identifying robust wavelet coefficients and optimizing procedures. Keywords: ALOS PALSAR, Wavelet analysis, Forest biomass, Multiple regression analysis.
Volume 6, Issue 1 , April 2014
Abstract
Timely and accurate detection of changes in land use/ cover is important for land planning and management. Remote sensing images have been primary sources for change detection in recent decades. Due to its simplicity, thresholding of difference image is a popular method for change detection. The traditional ...
Read More
Timely and accurate detection of changes in land use/ cover is important for land planning and management. Remote sensing images have been primary sources for change detection in recent decades. Due to its simplicity, thresholding of difference image is a popular method for change detection. The traditional thresholding methods such as Otsu are based on exhaustive search, so that they are time consuming. Since these methods are mainly developed for one-dimensional problems, the computation time grows exponentially with the number of thresholds when these methods are extended to be used for multi-dimensional problems. If thresholding is supposed to be as an optimization problem, optimization methods can potentially decrease the computation time. In this paper, a fast, simple and effective multi-dimensional image thresholding technique based on Particle Swarm Optimization (PSO) method is presented. This technique calculates the optimal threshold values by maximizing the Otsu objective function and minimizing the inter-class variance objective function. The proposed method has been implemented on two multispectral and multi-temporal datasets. The first dataset includes a couple of images acquired by the TM sensor taken form south islands of Aurmia Lake (Iran) in Jun 1984 and July 2010, respectively. The second dataset is obtained from a couple of images acquired by the same sensor on the Khodafarin dam (Iran) in July 2000 and July 2009, respectively. In order to evaluate the proposed method, the computational time and change detection accuracy were computed. In addition, statistical test was carried out in order to evaluate the robustness of the developed method. The experimental results show that the proposed PSO-based multi-dimensional thresholding method could provide optimum thresholds values by decreasing 98% and 15% of the time complexity compared with the most widely used Otsu and inter-class variance-based thresholding methods.
Volume 4, Issue 1 , March 2012
Abstract
Taking the advantages of polarimetric radar data has a decisive role in target detection purposes. In this way, comprehensive geometric and descriptive information could be derived through processing this kind of data. However, the selection of optimal features could be considered as a major challenge ...
Read More
Taking the advantages of polarimetric radar data has a decisive role in target detection purposes. In this way, comprehensive geometric and descriptive information could be derived through processing this kind of data. However, the selection of optimal features could be considered as a major challenge in order to classification of the polarimetric radar imagery. In this paper, a novel approach is proposed for optimal feature selection based on mapping the extracted features to the prototype space. As a key result of the paper, fitness index is introduced to facilitate the optimal feature selection in polarimetric radar images. On the other hand, the mixture of backscattering mechanisms in a pixel level is another limitation to obtain precise spatial information. Thus, utilizing soft classifiers is indispensible to acquire the sub-pixel information. Positivity and sum to unity of the fractions within each pixel are major challenges in results of the soft classifiers. In this paper, integration of the soft classifiers and unsupervised algorithms of end-member extraction is proposed to solve this problem. Likewise, soft classifiers just provide fractional maps and the spatial arrangement of sub-pixels remains unknown. In this regard, Super Resolution Mapping (SRM) techniques are developed to enhance the spatial resolution of the results of soft classifiers. This research attempts to provide a sub-pixel classification of polarimetric radar images using the pixel swapping technique. Towards this end, a non-random procedure is suggested for initial arrangement of the sub-pixels. According to the results, the proposed method for optimal feature selection is demonstrated more accurate results than genetic algorithm. Next, three algorithms including Linear Spectral Unmixing (LSU), Multi-Layer Perceptron (MLP) and Support Vector Machines (SVM) are performed to soft classifying of the polarimetric radar image into three classes (residential, vegetation and bare earth). SVM present accurate results in comparison to others; its resulted fractional maps are used in SRM procedure. Finally, pixel swapping technique is performed based on the results of SVM classification and the land cover map of the study area is produced in a finer spatial resolution.