CLASSIFICATION OF FULLY POLARIMETRIC SAR SATELLITE DATA USING GENETIC ALGORITHM AND NEURAL NETWORKS

Size: px
Start display at page:

Download "CLASSIFICATION OF FULLY POLARIMETRIC SAR SATELLITE DATA USING GENETIC ALGORITHM AND NEURAL NETWORKS"

Transcription

1 CLASSIFICATION OF FULLY POLARIMETRIC SAR SATELLITE DATA USING GENETIC ALGORITHM AND NEURAL NETWORKS Iman Entezari 1, Babak Mansouri 2, and Mahdi Motagh 1 1 Department of Geomatics Engineering, College of Engineering, University of Tehran, Tehran, Iran {entezari, motagh}@ut.ac.ir 2 International Institute of Earthquake Engineering and Seismology, Tehran, Iran #26 Arghavan St., N. Dibaji, Farmanieh, Tehran, Iran, Code: Tel: , Fax: mansouri@iiees.ac.ir ABSTRACT A novel method for supervised classification using fully polarimetric SAR data is proposed in this research. First a set of polarimetric parameters are extracted from SAR complex analysis and target decomposition theorems. Due to a large number of polarimetric parameters, the heuristic search method of Genetic Algorithm (GA) is used to select an optimum set of parameters as the feature vector. A multilayer feedforward neural network, which is a non-parametric classifier, is used to classify the features and to produce land cover maps. This procedure is implemented to fully polarimetric ALOS-PALSAR datasets of Tehran in order to assess the accuracy of the method. The final results show that the proposed algorithm provides high accuracy land cover identification/classification with an overall accuracy of 98.68% (Kappa coefficient of 97.86%). Keywords: SAR Polarimetry, Polarimetric Parameters, Genetic Algorithm, Neural Networks, Classification. INTRODUCTION Land cover identification and classification studies are important in delineating features associated with the built environment. The ability to differ between land cover types is necessary for urban planning and also in producing urban database. Fully polarimetric SAR image analysis shows unprecedented advantages in the identification and classification of different land types as compared with the single-channel SAR results. One of the most important aspects of using fully polarimetric data is the feasibility of selecting meaningful indices from numerous polarimetric parameters. These parameters can assist in the interpretation of the scene under study. Many studies have proposed different methods for classification of fully polarimetric SAR images [1-5]. These methods are usually based on employing polarimetric parameters in parametric and nonparametric classifiers. For example, parametric classifiers such as Maximum Likelihood and Minimum Distance have been used for classification purpose [1]. Also, non-parametric classifiers such as those based on Neural Networks and SVMs (Support Vector Machines) have been employed in supervised classification of fully polarimetric SAR data [2-4]. A novel method for supervised classification of the fully polarimetric SAR data is presented in this research. Different sets of polarimetric parameters are first extracted from SAR complex analysis and target decomposition theorems. From SAR complex analysis, parameters are calculated in both linear and circular polarization bases. Also, both coherent and incoherent decomposition theorems are considered for computing the parameters from target decomposition techniques. Secondly, due to a large number of polarimetric parameters, the feature selection method of Genetic Algorithm (GA) is used to select an optimum set of parameters as the feature vector. Finally, since the probability distribution function of some of the parameters is unidentified, a multilayer feedforward neural network which is a non-parametric classifier is used for classification stage. To assess the accuracy of the proposed method, fully polarimetric ALOS-PALSAR data of Tehran is processed. The results show that our classification algorithm provides a very high level of accuracy for land cover identification and classification. 1

2 METHODOLOGY Polarimetric SAR parameters computation Different sets of polarimetric parameters can be derived from SAR complex data analysis and polarimetric decomposition techniques. The scattering matrix can be computed in any orthogonal polarization basis considering SAR complex analysis. In this research, we consider the conventional linear and circular polarization bases. It should be mentioned that the scattering matrix in circular basis is computed using the change-of-basis theory [6]. The backscattering cross sections in linear and circular basis, ratios between the scattering matrix elements in linear and circular basis, ratios of the scattering matrix elements to the Span (sum of the intensities of four polarimetric channels) in linear and circular basis, and the polarimetric coherency in linear and circular basis and computed. Furthermore, many parameters can be obtained from different types of target decomposition techniques which provide information about scattering mechanisms in the scene. Here, the parameters including Pauli, Krogager, Freeman, Yamaguchi, H/A/ coefficients, and eigenvalues of the coherency matrix are also calculated from polarimetric decomposition techniques. Therefore, the extracted parameters in this research are listed as follows: Backscattering cross sections in linear and circular basis (6 features) Ratios between scattering matrix elements in linear basis and circular basis (6 features) Ratios of the scattering matrix elements to the Span in linear and circular basis (6 features) Polarimetric coherence in linear and circular basis (6 features) Pauli decomposition coefficients (3 features) Krogager decomposition coefficients (3 features) Freeman decomposition coefficients (3 features) Four component Yamaguchi decomposition coefficients (4 features) H/A/alpha parameters and combinations of H and A: HA, H(1-A), (1-H)A, and (1-H)(1-A) (the total of 7 features) Eigenvalues of the coherency matrix (3 features) Pedestal Height (1 features) Feature Selection The aim of feature selection is to find a set of features that yield the best classification result compromising computational efforts [7]. Because of three main reasons, feature selection is necessary for target identification and classification [7]. Firstly, the computational time is decreased by using fewer input features. Secondly, since some of the features may have considerable correlation, the complexity of the classification problem can be high and thus, employing many features does not necessarily increase the performance and the accuracy of the classification. Thirdly, in many cases the number of training data is limited. Therefore, in both parametric and standard non-parametric classifiers, the performance of the classification is decreased when the number of features in the input space is increased. In this research, the Genetic Algorithm is used for feature selection [8]. Fig. 1 shows the steps of implementing GA in optimization problems. The procedure of implementing Genetic Algorithm has three major steps as shown in Fig. 1. Firstly, the initial population which is a set of chromosomes should be created. Chromosomes are vectors of binary values. A vector value is associated with each classification feature. The length of the vector is the number of the extracted polarimetric SAR parameters. Secondly, the fitness function, which evaluates the ability of each chromosome to be selected as a parent, must be computed. The fitness function, in this research, is the Overall Accuracy of classification computed by the well-known Minimum Distance Classifier (MDC). The MDC is used mainly because this classifier can linearly separate different classes. Therefore, it is expected that the selected features yield the faster convergence of the neural network in the learning phase. Finally, the reproduction phase must be completed. In this phase, the process of parent selection is performed and then using the genetic operators such as crossover and mutation, the next generation is produced. The Tournament method is selected as the parent selection technique. According to the diagram, the procedure of reproduction and fitness computation are repeated till the stop criterion is met. 2

3 Table 1. Main specifications of the ALOS-PALSAR data Image Mode Full Polarimetric Center Frequency 1270 MHz Wavelength 23.6 cm (L-band) Band width 14 MHz Transmission Power 2 kw (peak power) Look Direction Right Look Angle 21.5 degree Swath Width 30 Km Range Resolution 30 m Azimuth Resolution 5 m Figure 1. Steps in implementing the Genetic Algorithm Neural Network Classifier Artificial Neural Networks are widely used in remote sensing applications such as pattern recognition and classification. Neural Networks have two important advantages in classification problems [9]: 1) no necessity to have a prior knowledge about the statistical distribution of the input data, and 2) capability to implement nonlinear discrimination functions. The multilayer feed-forward neural network is used in this research. The input layer of the network has a number of neurons that are equivalent to the number of input features. The number of neurons in the output layer is corresponding to the number of classes which have to be categorized. Also, a decision should be made on the number of hidden layers and their neurons. Kolmogorov stated that any discriminant function can be derived by a three-layer feedforward neural network [10]. Based on this rule, in this research, one hidden layer is considered for the neural network to identify the classes. Furthermore, a convenient rule of thumb is used to determine the number of neurons in the hidden layer of a threelayer feedforward neural network [9]. This rule confirms that the number of neurons in the hidden layer of a three-layer feedforward neural network (N H ) with N I input neurons and N O output neurons should be an integer close to: (1) After determining the structure of the network, the training phase must be completed using the selected training data for each class. The network is trained by Back-Propagation algorithm. The strategy in back-propagation learning algorithm is to update the weights in each layer in a way that minimize the total error. RESULTS AND DISCUSSION Study Area and Polarimetric Data The ALOS-PALSAR data (SLC - single look complex) as acquired on April 2009, over Tehran, is used. The specification of the used data is listed in Tab. 1. To make the ground resolution in both range and azimuth directions identical, a multi-looking with a 6x1 window size (i.e. 6 pixels in azimuth direction and 1 pixel in range direction) is applied on the original data. Also, for computing the polarimetric parameters, a 3x3 window size is adopted. Implementation The methodology of supervised classification of fully polarimetric SAR images is according to the flowchart shown in Fig 2. The objective is to identify different types of spectral classes to produce land cover map with four main classes of interest, namely built environments, forest areas, 3

4 agricultural regions, and bare fields. The training and test data are selected by visual interpretation using a co-registered optical VHR image of the scene. The location of the training data, the test samples and the optical image of the scene are shown in Figs. 3, 4, and 5 respectively. Also, the number of training and test samples is listed in Tab. 2. Figure 2. Flowchart of the proposed supervised classification using polarimetric images Figure 3. Pauli image - Training samples Figure 4. Pauli image - Test samples Table 2. Number of training and test samples Class type Training samples Test samples Built environments Forest areas Agricultural areas Bare fields Figure 5. VHR image of Tehran (Google Earth) The Genetic Algorithm was applied to select the optimum feature set. Selecting 7 up to 10 features was considered as a constraint for GA. This constraint was because of the fact that due to the limitation of the training samples size, selecting more than 10 features can cause a complexity in classification problem. Also, the stop criterion of GA process was considered the identicality of the 70% of population. Finally, GA stopped after 11 iteration and nine polarimetric parameters were selected as the feature vector for classification. They are namely: ratio between HH and VV channels, ratio between RR and LL channels, ratio of RR and Span, polarimetric coherence between HH and HV, polarimetric coherence between HV and VV, diplane and helix components of the Krogager decomposition, combination term of HA, and the pedestal height. Thus, these nine parameters are employed in the neural network classifier as the input feature vector. 4

5 Since the Genetic Algorithm selected nine parameters as the input feature set, the number of neurons in the input layer is nine. Also, four spectral classes should be classified. Therefore, based on the formula introduced in Eq. 1, the number of neurons in the hidden layer is six. The structure of the neural network is (See Fig. 6). Besides, the values of the parameters needed in the training phase were set by trial and error. Figure 6. Structure of the Neural Network Classification Results In order to evaluate the accuracy and the performance of the proposed method, three steps must be performed. Firstly, the training samples are presented to the neural network repeatedly until the network learns them. Secondly, the test samples are classified and finally, the confusion matrix is formed and the statistical indicators are computed to assess the performance of the classification. Tab. 3 presents the confusion matrix derived from the proposed method. Reference Data Table 3. Confusion matrix derived from the proposed method Classified Data Land Cover Built Env. Forest Area Agricultural Regions Bare Fields Total Built Env Forest Area Agricultural Regions Bare Fields Total Σ=3256 In this research, we computed the statistical indicators including: Overall Accuracy (OA), Kappa Coefficient (K), Producer s Accuracy (PA), and User s Accuracy (UA). This method has reached the Overall Accuracy of 98.68% and Kappa value of 97.86%. These values represent the high efficiency of the proposed method in supervised classification of fully polarimetric SAR data. Also, the values of PA and UA for different types of land covers and the final classified map produced by the proposed method are shown in Figs. 7 and 8 respectively. As can be seen in Fig. 7, the proposed method has identified all classes with a very high level of accuracy. Specially, the values of PA and UA for built environments are considerable. The method has been completely successful in identification of built environments. Identification and classification of built environments has always been an important field of study because it represents the building inventory as a major urban element-at-risk in man-made and natural disasters. Delineating the buildings from the entire urban scene is the basic step in applying change detection algorithms for revealing physical damages. Finally, it seems the high performance of the proposed classification method arises from the fact that the four considered classes are extremely different, spectrally. Also, it should be mentioned that since the proposed methodology was just implemented using a single dataset, the results have not absolute validity but may indicate a general trend for similar data and classes of interest. CONCLUSIONS A novel method for supervised classification of fully polarimetric SAR images was proposed. The proposed methodology is based on the Genetic Algorithm feature section and multilayer neural network classifier. The methodology was implemented on the fully polarimetric ALOS-PALSAR data as acquired in April 2009, over Tehran, Iran. The results of classification show that a high degree of accuracy for land cover classification and land cover mapping can be obtained. Also, it is worth 5

6 mentioning that this methodology should be implemented on the different polarimetric datasets with more spectral classes to asses the reliability of the method accordingly. Figure 7. User s and Producer s accuracies Figure 8. Classification map ACKNOWLEDGMENT The authors would like to thank the Japan Aerospace Exploration Agency (JAXA) for acquiring fully polarimetric ALOS-PALSAR data over Tehran and the European Space Agency for providing the data using the ALOS proposal No. AOALO3740. REFERENCES [1] Alberga, V. (2005) Comparison of Polarimetric Methods in Image Classification and SAR Interferometry Applications. Ph.D. dissertation, Tech. Univ. Chemnitz, Chemnitz, Germany. [2] Shah Hosseini, R., Entezari, I., Homayouni, S., and Mansouri, B. (2009) Classification of Polarimetric SAR Images Using Support Vector Machines. In Proceedings of the 30th Canadian Symposium on Remote Sensing, Lethbridge, Alberta, Canada. [3] Fukuda, S. and Hirosawa, H. (2001) Polarimetric SAR image classification using support vector machines. IEICE Trans. Electronics, vol.e84-c, no.12, pp [4] Song, C.J., Yun, S., and Hui, L. (2004) Classification of Polarimetric SAR imagerary based on Target Decomposition and neural network classifier. In Proc. of ACRS 04, November, [5] Lee, J.S., Grues, M.R., and Kwok, R. (1994) Classification of Multi-look Polarimetric SAR Imagery Based on Complex Wishart Distribution. International Journal of Remote Sensing, vol. 15, pp [6] Lüneburg, E. (1996) Radar polarimetry: A revision of basic concepts, in Direct and Inverse Electromagnetic Scattering. (H. Serbest and S. Cloude, Eds.), Pittman Research Notes in Mathematics Series 361, Addison Wesley Longman, Harlow, U.K. [7] Bhanu, B. and Lin, Y. (2003) Genetic Algorithm Based Feature Selection for Target Detection in SAR Images. Image and Vision Computing, vol. 21(7), pp [8] Holland, J. (1975) Adaptation in Natural and Artificial Systems. University of Michigan Press, Ann Arbor. [9] Duda, R.O., Hart, P.E., and Stork, D.G. (2001) Pattern Classification (2nd edition). John Wiley and Sons, New York. [10] Miller, D.M., Kaminsky, E.J., and Rana, S. (1995) Neural Network Classification of Remote Sensing Data. Computers and Geosciences, vol. 21, pp

Synthetic Aperture Radar (SAR) Polarimetry for Wetland Mapping & Change Detection

Synthetic Aperture Radar (SAR) Polarimetry for Wetland Mapping & Change Detection Synthetic Aperture Radar (SAR) Polarimetry for Wetland Mapping & Change Detection Jennifer M. Corcoran, M.S. Remote Sensing & Geospatial Analysis Laboratory Natural Resource Science & Management PhD Program

More information

CLASSIFICATION STRATEGIES FOR POLARIMETRIC SAR SEA ICE DATA

CLASSIFICATION STRATEGIES FOR POLARIMETRIC SAR SEA ICE DATA CLASSIFICATION STRATEGIES FOR POLARIMETRIC SAR SEA ICE DATA Bernd Scheuchl (), Irena Hajnsek (), Ian Cumming () () Department of Electrical and Computer Engineering, University of British Columbia 56 Main

More information

CLASSIFICATION OF EARTH TERRAIN COVERS USING THE MODIFIED FOUR- COMPONENT SCATTERING POWER DECOMPOSITION,

CLASSIFICATION OF EARTH TERRAIN COVERS USING THE MODIFIED FOUR- COMPONENT SCATTERING POWER DECOMPOSITION, CLASSIFICATION OF EARTH TERRAIN COVERS USING THE MODIFIED FOUR- COMPONENT SCATTERING POWER DECOMPOSITION, Boularbah Souissi (1), Mounira Ouarzeddine (1),, Aichouche Belhadj-Aissa (1) USTHB, F.E.I, BP N

More information

Four-component Scattering Power Decomposition with Rotation of Coherency Matrix

Four-component Scattering Power Decomposition with Rotation of Coherency Matrix 1 Four-component Scattering Power Decomposition with Rotation of Coherency Matrix Yoshio Yamaguchi, Fellow, IEEE, Akinobu Sato, Wolfgang Martin Boerner, Life Fellow, IEEE, Ryoichi Sato, Member, IEEE, and

More information

Polarimetric Radar Remote Sensing

Polarimetric Radar Remote Sensing Proceedings of ISAP2007, Niigata, Japan 1A2 Polarimetric Radar Remote Sensing Yoshio Yamaguchi Department of Information Engineering, Niigata University Ikarashi 2-8050, Niigata, 950-2181, Japan yamaguch@ie.niigata-u.ac.jp

More information

SAR Polarimetry Workstation

SAR Polarimetry Workstation Technical Specifications SAR Polarimetry Workstation The SAR Polarimetry Workstation provides a complete set of tools and applications designed specifically for the processing and analysis of Polarimetric

More information

INVESTIGATING THE PERFORMANCE OF SAR POLARIMETRIC FEATURES IN LAND-COVER CLASSIFICATION

INVESTIGATING THE PERFORMANCE OF SAR POLARIMETRIC FEATURES IN LAND-COVER CLASSIFICATION INVESTIGATING THE PERFORMANCE OF SAR POLARIMETRIC FEATURES IN LAND-COVER CLASSIFICATION Liang Gao & Yifang Ban Division of Geoinformatics, Royal Institute of Technology (KTH) Drottning Kristinas väg 30,

More information

Processing and Analysis of ALOS/Palsar Imagery

Processing and Analysis of ALOS/Palsar Imagery Processing and Analysis of ALOS/Palsar Imagery Yrjö Rauste, Anne Lönnqvist, and Heikki Ahola Kaukokartoituspäivät 6.11.2006 NewSAR Project The newest generation of space borne SAR sensors have polarimetric

More information

PolSARpro v4.03 Forest Applications

PolSARpro v4.03 Forest Applications PolSARpro v4.03 Forest Applications Laurent Ferro-Famil Lecture on polarimetric SAR Theory and applications to agriculture & vegetation Thursday 19 April, morning Pol-InSAR Tutorial Forest Application

More information

SAR Polarimetry Workstation

SAR Polarimetry Workstation SAR Polarimetry Workstation The PCI Geomatics SAR Polarimetry Workstation provides a complete set of tools and applications designed specifically for the processing and analysis of Polarimetric SAR (POLSAR)

More information

RICE FIELD INTERPRETATION WITH TEMPORAL SENTINEL-1 SYNTHETIC APERTURE RADAR IMAGE DATA

RICE FIELD INTERPRETATION WITH TEMPORAL SENTINEL-1 SYNTHETIC APERTURE RADAR IMAGE DATA RICE FIELD INTERPRETATION WITH TEMPORAL SENTINEL-1 SYNTHETIC APERTURE RADAR IMAGE DATA 1 Chia-Hao Chang ( 張家豪 ) 2 Chiou-Shann Fuh ( 傅楸善 ) 2 Shi-Wei Wang ( 王熹偉 ) 1 Dept. of Geography, 2 Dept. of Computer

More information

Assessment of Polarimetric and Spatial Features for Built-up Mapping using ALOS PALSAR Polarimetric SAR Data

Assessment of Polarimetric and Spatial Features for Built-up Mapping using ALOS PALSAR Polarimetric SAR Data Assessment of Polarimetric and patial Features for Built-up Mapping using ALO PALAR Polarimetric AR Data hucheng YOU, China Key words: ALO PALAR, support vector machine, random forest, built-up mapping

More information

A knowledge based classification method for polarimetric SAR data

A knowledge based classification method for polarimetric SAR data A knowledge based classification method for polarimetric AR data M. Dabboor*, V. Karathanassi Laboratory of Remote ensing, chool of Rural and urveying Engineering, National Technical University of Athens,

More information

A Hybrid Entropy Decomposition and Support Vector Machine Method for Agricultural Crop Type Classification

A Hybrid Entropy Decomposition and Support Vector Machine Method for Agricultural Crop Type Classification PIERS ONLINE, VOL. 3, NO. 5, 2007 620 A Hybrid Entropy Decomposition and Support Vector Machine Method for Agricultural Crop Type Classification Chue-Poh Tan 1, Hong-Tat Ewe 2, and Hean-Teik Chuah 1 1

More information

Utilization of four-component scattering power decomposition method for glaciated terrain classification

Utilization of four-component scattering power decomposition method for glaciated terrain classification Utilization of four-component scattering power decomposition method for glaciated terrain classification Gulab Singh, Y. Yamaguchi, and S-E. Park Graduate School of Science and Technology, Niigata University,

More information

CHAPTER 6 HYBRID AI BASED IMAGE CLASSIFICATION TECHNIQUES

CHAPTER 6 HYBRID AI BASED IMAGE CLASSIFICATION TECHNIQUES CHAPTER 6 HYBRID AI BASED IMAGE CLASSIFICATION TECHNIQUES 6.1 INTRODUCTION The exploration of applications of ANN for image classification has yielded satisfactory results. But, the scope for improving

More information

Coherence Based Polarimetric SAR Tomography

Coherence Based Polarimetric SAR Tomography I J C T A, 9(3), 2016, pp. 133-141 International Science Press Coherence Based Polarimetric SAR Tomography P. Saranya*, and K. Vani** Abstract: Synthetic Aperture Radar (SAR) three dimensional image provides

More information

mechanical properties such that the waves emanated almost entirely polarisized. In a simple radar system, the same antenna is often arranged so that t

mechanical properties such that the waves emanated almost entirely polarisized. In a simple radar system, the same antenna is often arranged so that t EXTRACTING KEY FOR LANDCOVER CHANGE USING MULTITEMPORAL PALSAR IMAGES & ITS CALIBRATION TO RELEVANT OPTICAL IMAGES PI No 389 Fahmi Amhar, Antonius B. Wijanarto Geomatics Research Division National Coordinating

More information

Exploiting the High Dimensionality of Polarimetric Interferometric Synthetic Aperture Radar Observations

Exploiting the High Dimensionality of Polarimetric Interferometric Synthetic Aperture Radar Observations Exploiting the High Dimensionality of Polarimetric Interferometric Synthetic Aperture Radar Observations Robert Riley rriley@sandia.gov R. Derek West rdwest@sandia.gov SAND2017 11133 C This work was supported

More information

ADVANCED CONCEPTS IN POLARIMETRY PART 2 (Polarimetric Target Classification) 1 INTRODUCTION

ADVANCED CONCEPTS IN POLARIMETRY PART 2 (Polarimetric Target Classification) 1 INTRODUCTION ADVANCED CONCEPTS IN POLARIMETRY PART 2 (Polarimetric Target Classification) Eric POTTIER (1), Jong-Sen LEE (2), Laurent FERRO-FAMIL (1) (1) I.E.T.R UMR CNRS 6164 University of Rennes1 Image and Remote

More information

MODELLING OF THE SCATTERING BY A SMOOTH DIELECTRIC CYLINDER: STUDY OF THE COMPLEX SCATTERING MATRIX

MODELLING OF THE SCATTERING BY A SMOOTH DIELECTRIC CYLINDER: STUDY OF THE COMPLEX SCATTERING MATRIX MODELLING OF THE SCATTERING BY A SMOOTH DIELECTRIC CYLINDER: STUDY OF THE COMPLEX SCATTERING MATRIX L Thirion 1, C Dahon 2,3, A Lefevre 4, I Chênerie 1, L Ferro-Famil 2, C Titin-Schnaider 3 1 AD2M, Université

More information

Classifying UAVSAR Polarimetric Synthetic Aperture Radar (PolSAR) Imagery Using Target Decomposition Features

Classifying UAVSAR Polarimetric Synthetic Aperture Radar (PolSAR) Imagery Using Target Decomposition Features Proceedings Classifying UAVSAR Polarimetric Synthetic Aperture Radar (PolSAR) Imagery Using Target Decomposition Features Ghazaleh Alijani 1, *, Mahdi Hasanlou 2 and Zahra Azizi 1 1 Department of GIS/RS,

More information

Decision Fusion of Classifiers for Multifrequency PolSAR and Optical Data Classification

Decision Fusion of Classifiers for Multifrequency PolSAR and Optical Data Classification Decision Fusion of Classifiers for Multifrequency PolSAR and Optical Data Classification N. Gökhan Kasapoğlu and Torbjørn Eltoft Dept. of Physics and Technology University of Tromsø Tromsø, Norway gokhan.kasapoglu@uit.no

More information

Polarimetric SAR Image Classification Using Radial Basis Function Neural Network

Polarimetric SAR Image Classification Using Radial Basis Function Neural Network PIERS ONLINE, VOL. 6, NO. 5, 2010 470 Polarimetric SAR Image Classification Using Radial Basis Function Neural Network Turker Ince Izmir University of Economics, Izmir, Turkey Abstract This paper presents

More information

Image Compression: An Artificial Neural Network Approach

Image Compression: An Artificial Neural Network Approach Image Compression: An Artificial Neural Network Approach Anjana B 1, Mrs Shreeja R 2 1 Department of Computer Science and Engineering, Calicut University, Kuttippuram 2 Department of Computer Science and

More information

Image Classification and Processing using Modified Parallel-ACTIT

Image Classification and Processing using Modified Parallel-ACTIT Proceedings of the 2009 IEEE International Conference on Systems, Man, and Cybernetics San Antonio, TX, USA - October 2009 Image Classification and Processing using Modified Parallel-ACTIT Jun Ando and

More information

A Vector Agent-Based Unsupervised Image Classification for High Spatial Resolution Satellite Imagery

A Vector Agent-Based Unsupervised Image Classification for High Spatial Resolution Satellite Imagery A Vector Agent-Based Unsupervised Image Classification for High Spatial Resolution Satellite Imagery K. Borna 1, A. B. Moore 2, P. Sirguey 3 School of Surveying University of Otago PO Box 56, Dunedin,

More information

MULTI-TEMPORAL SAR DATA FILTERING FOR LAND APPLICATIONS. I i is the estimate of the local mean backscattering

MULTI-TEMPORAL SAR DATA FILTERING FOR LAND APPLICATIONS. I i is the estimate of the local mean backscattering MULTI-TEMPORAL SAR DATA FILTERING FOR LAND APPLICATIONS Urs Wegmüller (1), Maurizio Santoro (1), and Charles Werner (1) (1) Gamma Remote Sensing AG, Worbstrasse 225, CH-3073 Gümligen, Switzerland http://www.gamma-rs.ch,

More information

ADVANCED CONCEPTS IN POLARIMETRY PART 2 (Polarimetric Target Classification) 1 INTRODUCTION

ADVANCED CONCEPTS IN POLARIMETRY PART 2 (Polarimetric Target Classification) 1 INTRODUCTION ADVANCED CONCEPTS IN POLARIMETRY PART 2 (Polarimetric Target Classification) Eric POTTIER (1), Jong-Sen LEE (2), Laurent FERRO-FAMIL (1) (1) I.E.T.R UMR CNRS 6164 University of Rennes1 Image and Remote

More information

Nearest Clustering Algorithm for Satellite Image Classification in Remote Sensing Applications

Nearest Clustering Algorithm for Satellite Image Classification in Remote Sensing Applications Nearest Clustering Algorithm for Satellite Image Classification in Remote Sensing Applications Anil K Goswami 1, Swati Sharma 2, Praveen Kumar 3 1 DRDO, New Delhi, India 2 PDM College of Engineering for

More information

A *69>H>N6 #DJGC6A DG C<>C::G>C<,8>:C8:H /DA 'D 2:6G, ()-"&"3 -"(' ( +-" " " % '.+ % ' -0(+$,

A *69>H>N6 #DJGC6A DG C<>C::G>C<,8>:C8:H /DA 'D 2:6G, ()-&3 -(' ( +-   % '.+ % ' -0(+$, The structure is a very important aspect in neural network design, it is not only impossible to determine an optimal structure for a given problem, it is even impossible to prove that a given structure

More information

GIS. PDF created with pdffactory Pro trial version ... SPIRIT. *

GIS. PDF created with pdffactory Pro trial version  ... SPIRIT. * Vol8, No 4, Winter 07 Iranian Remote Sensing & - * // // RVOG /4 / 7/4 99754 * 0887708 Email aghababaee@mailkntuacir PDF created with pdffactory Pro trial version wwwpdffactorycom Treuhaft and Cloude,

More information

Open Access Research on the Prediction Model of Material Cost Based on Data Mining

Open Access Research on the Prediction Model of Material Cost Based on Data Mining Send Orders for Reprints to reprints@benthamscience.ae 1062 The Open Mechanical Engineering Journal, 2015, 9, 1062-1066 Open Access Research on the Prediction Model of Material Cost Based on Data Mining

More information

Revision of a Floating-Point Genetic Algorithm GENOCOP V for Nonlinear Programming Problems

Revision of a Floating-Point Genetic Algorithm GENOCOP V for Nonlinear Programming Problems 4 The Open Cybernetics and Systemics Journal, 008,, 4-9 Revision of a Floating-Point Genetic Algorithm GENOCOP V for Nonlinear Programming Problems K. Kato *, M. Sakawa and H. Katagiri Department of Artificial

More information

Do It Yourself 8. Polarization Coherence Tomography (P.C.T) Training Course

Do It Yourself 8. Polarization Coherence Tomography (P.C.T) Training Course Do It Yourself 8 Polarization Coherence Tomography (P.C.T) Training Course 1 Objectives To provide a self taught introduction to Polarization Coherence Tomography (PCT) processing techniques to enable

More information

Course Outline (1) #6 Data Acquisition for Built Environment. Fumio YAMAZAKI

Course Outline (1) #6 Data Acquisition for Built Environment. Fumio YAMAZAKI AT09.98 Applied GIS and Remote Sensing for Disaster Mitigation #6 Data Acquisition for Built Environment 9 October, 2002 Fumio YAMAZAKI yamazaki@ait.ac.th http://www.star.ait.ac.th/~yamazaki/ Course Outline

More information

FIRST RESULTS OF THE ALOS PALSAR VERIFICATION PROCESSOR

FIRST RESULTS OF THE ALOS PALSAR VERIFICATION PROCESSOR FIRST RESULTS OF THE ALOS PALSAR VERIFICATION PROCESSOR P. Pasquali (1), A. Monti Guarnieri (2), D. D Aria (3), L. Costa (3), D. Small (4), M. Jehle (4) and B. Rosich (5) (1) sarmap s.a., Cascine di Barico,

More information

ALOS-PALSAR performances on a multiple sensor DInSAR scenario for deformation monitoring

ALOS-PALSAR performances on a multiple sensor DInSAR scenario for deformation monitoring ALOS-PALSAR performances on a multiple sensor DInSAR scenario for deformation monitoring Pablo Blanco, Roman Arbiol and Vicenç Palà Remote Sensing Department Institut Cartogràfic de Catalunya (ICC) Parc

More information

4-Component Scattering Power Decomposition with Phase Rotation of Coherency Matrix

4-Component Scattering Power Decomposition with Phase Rotation of Coherency Matrix 4-Component Scattering Power Decomposition with Phase Rotation o Coherency Matrix Gulab Singh*, Yoshio Yamaguchi and S.-E. Park Niigata University *g.singh@wave.ie.niigata-u.ac.jp Outline Introduction:

More information

A Classifier with the Function-based Decision Tree

A Classifier with the Function-based Decision Tree A Classifier with the Function-based Decision Tree Been-Chian Chien and Jung-Yi Lin Institute of Information Engineering I-Shou University, Kaohsiung 84008, Taiwan, R.O.C E-mail: cbc@isu.edu.tw, m893310m@isu.edu.tw

More information

In addition, the image registration and geocoding functionality is also available as a separate GEO package.

In addition, the image registration and geocoding functionality is also available as a separate GEO package. GAMMA Software information: GAMMA Software supports the entire processing from SAR raw data to products such as digital elevation models, displacement maps and landuse maps. The software is grouped into

More information

Memorandum. Clint Slatton Prof. Brian Evans Term project idea for Multidimensional Signal Processing (EE381k)

Memorandum. Clint Slatton Prof. Brian Evans Term project idea for Multidimensional Signal Processing (EE381k) Memorandum From: To: Subject: Date : Clint Slatton Prof. Brian Evans Term project idea for Multidimensional Signal Processing (EE381k) 16-Sep-98 Project title: Minimizing segmentation discontinuities in

More information

Disaster Monitoring by Fully Polarimetric SAR Data Acquired with ALOS-PALSAR

Disaster Monitoring by Fully Polarimetric SAR Data Acquired with ALOS-PALSAR 1 Disaster Monitoring by Fully Polarimetric SAR Data Acquired with ALOS-PALSAR Yoshio Yamaguchi, Fellow, IEEE Abstract This paper presents scattering power decomposition images of fully polarimetric synthetic

More information

AN INTEGRATED APPROACH TO AGRICULTURAL CROP CLASSIFICATION USING SPOT5 HRV IMAGES

AN INTEGRATED APPROACH TO AGRICULTURAL CROP CLASSIFICATION USING SPOT5 HRV IMAGES AN INTEGRATED APPROACH TO AGRICULTURAL CROP CLASSIFICATION USING SPOT5 HRV IMAGES Chang Yi 1 1,2,*, Yaozhong Pan 1, 2, Jinshui Zhang 1, 2 College of Resources Science and Technology, Beijing Normal University,

More information

Compression of RADARSAT Data with Block Adaptive Wavelets Abstract: 1. Introduction

Compression of RADARSAT Data with Block Adaptive Wavelets Abstract: 1. Introduction Compression of RADARSAT Data with Block Adaptive Wavelets Ian Cumming and Jing Wang Department of Electrical and Computer Engineering The University of British Columbia 2356 Main Mall, Vancouver, BC, Canada

More information

A Comparative Study of Conventional and Neural Network Classification of Multispectral Data

A Comparative Study of Conventional and Neural Network Classification of Multispectral Data A Comparative Study of Conventional and Neural Network Classification of Multispectral Data B.Solaiman & M.C.Mouchot Ecole Nationale Supérieure des Télécommunications de Bretagne B.P. 832, 29285 BREST

More information

Network Routing Protocol using Genetic Algorithms

Network Routing Protocol using Genetic Algorithms International Journal of Electrical & Computer Sciences IJECS-IJENS Vol:0 No:02 40 Network Routing Protocol using Genetic Algorithms Gihan Nagib and Wahied G. Ali Abstract This paper aims to develop a

More information

Change Detection in Remotely Sensed Images Based on Image Fusion and Fuzzy Clustering

Change Detection in Remotely Sensed Images Based on Image Fusion and Fuzzy Clustering International Journal of Electronics Engineering Research. ISSN 0975-6450 Volume 9, Number 1 (2017) pp. 141-150 Research India Publications http://www.ripublication.com Change Detection in Remotely Sensed

More information

K&C Phase 3. Earth Observation Research Group (EO), CSIR, PO Box 395, Pretoria, 0001, b

K&C Phase 3. Earth Observation Research Group (EO), CSIR, PO Box 395, Pretoria, 0001,  b WOODY STRUCTURAL MODELLING IN SOUTHERN AFRICAN SAVANNAHS USING MULTI-FREQUENCY SAR AND OPTICAL INTEGRATED DATA APPROACHES: ONE STEP TO REGIONAL MAPPING K&C Phase 3 Renaud Mathieu a, Laven Naidoo a, Konrad

More information

The Open Statistics & Probability Journal

The Open Statistics & Probability Journal Send Orders for Reprints to reprints@benthamscience.ae 10 The Open Statistics & Probability Journal, 2016, 7, 10-19 The Open Statistics & Probability Journal Content list available at: www.benthamopen.com/tospj/

More information

A Novel Technique for Optimizing the Hidden Layer Architecture in Artificial Neural Networks N. M. Wagarachchi 1, A. S.

A Novel Technique for Optimizing the Hidden Layer Architecture in Artificial Neural Networks N. M. Wagarachchi 1, A. S. American International Journal of Research in Science, Technology, Engineering & Mathematics Available online at http://www.iasir.net ISSN (Print): 2328-3491, ISSN (Online): 2328-3580, ISSN (CD-ROM): 2328-3629

More information

Neural Network Approach for Automatic Landuse Classification of Satellite Images: One-Against-Rest and Multi-Class Classifiers

Neural Network Approach for Automatic Landuse Classification of Satellite Images: One-Against-Rest and Multi-Class Classifiers Neural Network Approach for Automatic Landuse Classification of Satellite Images: One-Against-Rest and Multi-Class Classifiers Anil Kumar Goswami DTRL, DRDO Delhi, India Heena Joshi Banasthali Vidhyapith

More information

COMBINING HIGH SPATIAL RESOLUTION OPTICAL AND LIDAR DATA FOR OBJECT-BASED IMAGE CLASSIFICATION

COMBINING HIGH SPATIAL RESOLUTION OPTICAL AND LIDAR DATA FOR OBJECT-BASED IMAGE CLASSIFICATION COMBINING HIGH SPATIAL RESOLUTION OPTICAL AND LIDAR DATA FOR OBJECT-BASED IMAGE CLASSIFICATION Ruonan Li 1, Tianyi Zhang 1, Ruozheng Geng 1, Leiguang Wang 2, * 1 School of Forestry, Southwest Forestry

More information

Design and Analysis of an Euler Transformation Algorithm Applied to Full-Polarimetric ISAR Imagery

Design and Analysis of an Euler Transformation Algorithm Applied to Full-Polarimetric ISAR Imagery Design and Analysis of an Euler Transformation Algorithm Applied to Full-Polarimetric ISAR Imagery Christopher S. Baird Advisor: Robert Giles Submillimeter-Wave Technology Laboratory (STL) Presented in

More information

Signal Processing Laboratory

Signal Processing Laboratory C.S.L Liege Science Park Avenue du Pré-Aily B-4031 ANGLEUR Belgium Tel: +32.4.382.46.00 Fax: +32.4.367.56.13 Signal Processing Laboratory Anne Orban VITO June 16, 2011 C. Barbier : the team Remote Sensing

More information

Fisher Distance Based GA Clustering Taking Into Account Overlapped Space Among Probability Density Functions of Clusters in Feature Space

Fisher Distance Based GA Clustering Taking Into Account Overlapped Space Among Probability Density Functions of Clusters in Feature Space Fisher Distance Based GA Clustering Taking Into Account Overlapped Space Among Probability Density Functions of Clusters in Feature Space Kohei Arai 1 Graduate School of Science and Engineering Saga University

More information

Orthorectifying ALOS PALSAR. Quick Guide

Orthorectifying ALOS PALSAR. Quick Guide Orthorectifying ALOS PALSAR Quick Guide Copyright Notice This publication is a copyrighted work owned by: PCI Geomatics 50 West Wilmot Street Richmond Hill, Ontario Canada L4B 1M5 www.pcigeomatics.com

More information

Detection of Buried Objects using GPR Change Detection in Polarimetric Huynen Spaces

Detection of Buried Objects using GPR Change Detection in Polarimetric Huynen Spaces Detection of Buried Objects using GPR Change Detection in Polarimetric Huynen Spaces Firooz Sadjadi Lockheed Martin Corporation Saint Anthony, Minnesota USA firooz.sadjadi@ieee.org Anders Sullivan Army

More information

SAM and ANN classification of hyperspectral data of seminatural agriculture used areas

SAM and ANN classification of hyperspectral data of seminatural agriculture used areas Proceedings of the 28th EARSeL Symposium: Remote Sensing for a Changing Europe, Istambul, Turkey, June 2-5 2008. Millpress Science Publishers Zagajewski B., Olesiuk D., 2008. SAM and ANN classification

More information

Review on Methods of Selecting Number of Hidden Nodes in Artificial Neural Network

Review on Methods of Selecting Number of Hidden Nodes in Artificial Neural Network Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology IJCSMC, Vol. 3, Issue. 11, November 2014,

More information

OCCLUSION BOUNDARIES ESTIMATION FROM A HIGH-RESOLUTION SAR IMAGE

OCCLUSION BOUNDARIES ESTIMATION FROM A HIGH-RESOLUTION SAR IMAGE OCCLUSION BOUNDARIES ESTIMATION FROM A HIGH-RESOLUTION SAR IMAGE Wenju He, Marc Jäger, and Olaf Hellwich Berlin University of Technology FR3-1, Franklinstr. 28, 10587 Berlin, Germany {wenjuhe, jaeger,

More information

Automated feature extraction by combining polarimetric SAR and object-based image analysis for monitoring of natural resource exploitation

Automated feature extraction by combining polarimetric SAR and object-based image analysis for monitoring of natural resource exploitation DLR.de Chart 1 Automated feature extraction by combining polarimetric SAR and object-based image analysis for monitoring of natural resource exploitation Simon Plank, Alexander Mager, Elisabeth Schoepfer

More information

SAR IMAGE PROCESSING FOR CROP MONITORING

SAR IMAGE PROCESSING FOR CROP MONITORING SAR IMAGE PROCESSING FOR CROP MONITORING Anne Orban, Dominique Derauw, and Christian Barbier Centre Spatial de Liège Université de Liège cbarbier@ulg.ac.be Agriculture and Vegetation at a Local Scale Habay-La-Neuve,

More information

ALOS PALSAR VERIFICATION PROCESSOR

ALOS PALSAR VERIFICATION PROCESSOR ALOS PALSAR VERIFICATION PROCESSOR P. Pasquali (1), A. Monti Guarnieri (2), D. D Aria (3), L. Costa (3), D. Small (4), M. Jehle (4) and B. Rosich (5) (1) sarmap s.a., Cascine di Barico, 6989 Purasca, Switzerland,

More information

Forest Retrievals. using SAR Polarimetry. (Practical Session D3P2a)

Forest Retrievals. using SAR Polarimetry. (Practical Session D3P2a) Forest Retrievals using SAR Polarimetry (Practical Session D3P2a) Laurent FERRO-FAMIL - Eric POTTIER University of Rennes 1 Pol-InSAR Practical Forest Application PolSARpro SIM PolSARproSim is a rapid,

More information

Remote Sensing Image Classification Based on a Modified Self-organizing Neural Network with a Priori Knowledge

Remote Sensing Image Classification Based on a Modified Self-organizing Neural Network with a Priori Knowledge Sensors & Transducers 2013 by IFSA http://www.sensorsportal.com Remote Sensing Image Classification Based on a Modified Self-organizing Neural Network with a Priori Knowledge 1 Jian Bo Xu, 2 Li Sheng Song,

More information

PCA vs. ICA Decomposition of High Resolution SAR Images: Application to Urban Structures Recognition

PCA vs. ICA Decomposition of High Resolution SAR Images: Application to Urban Structures Recognition PCA vs. ICA Decomposition of High Resolution SAR Images: Application to Urban Structures Recognition Houda Chaabouni-Chouayakh a and Mihai Datcu a,b a German Aerospace Center (DLR), Oberpfaffenhofen D-82234

More information

SAR Interferogram Phase Filtering Using Wavelet Transform

SAR Interferogram Phase Filtering Using Wavelet Transform Formatted: Font: 16 pt, Nazanin, 16 pt, (Complex) Farsi, 12 pt SAR Interferogram Phase Filtering Using Wavelet Transform V. Akbari, M. Motagh and M. A. Rajabi 1 Dept. o Surveying Eng., University College

More information

HIERARCHICAL CLASSIFICATION OF POLARIMETRIC SAR IMAGE BASED ON STATISTICAL REGION MERGING

HIERARCHICAL CLASSIFICATION OF POLARIMETRIC SAR IMAGE BASED ON STATISTICAL REGION MERGING HIERARCHICAL CLASSIFICATION OF POLARIMETRIC SAR IMAGE BASED ON STATISTICAL REGION MERGING F. Lang a*, J. Yang a, L. Zhao a, D. Li a a State Key Laboratory of Information Engineering in Surveying, Mapping

More information

Traffic Signs Recognition using HP and HOG Descriptors Combined to MLP and SVM Classifiers

Traffic Signs Recognition using HP and HOG Descriptors Combined to MLP and SVM Classifiers Traffic Signs Recognition using HP and HOG Descriptors Combined to MLP and SVM Classifiers A. Salhi, B. Minaoui, M. Fakir, H. Chakib, H. Grimech Faculty of science and Technology Sultan Moulay Slimane

More information

ALOS-2/PALSAR-2 Calibration and Validation Results

ALOS-2/PALSAR-2 Calibration and Validation Results ALOS-2/PALSAR-2 Calibration and Validation Results Ver. 2018.08.07 JAXA EORC & ALOS-2 Project Team 1 Content 1. Update of the calibration factor (CF) 2. Evaluation results for PALSAR-2 standard products

More information

Development and Applications of an Interferometric Ground-Based SAR System

Development and Applications of an Interferometric Ground-Based SAR System Development and Applications of an Interferometric Ground-Based SAR System Tadashi Hamasaki (1), Zheng-Shu Zhou (2), Motoyuki Sato (2) (1) Graduate School of Environmental Studies, Tohoku University Aramaki

More information

InSAR Operational and Processing Steps for DEM Generation

InSAR Operational and Processing Steps for DEM Generation InSAR Operational and Processing Steps for DEM Generation By F. I. Okeke Department of Geoinformatics and Surveying, University of Nigeria, Enugu Campus Tel: 2-80-5627286 Email:francisokeke@yahoo.com Promoting

More information

Channel Performance Improvement through FF and RBF Neural Network based Equalization

Channel Performance Improvement through FF and RBF Neural Network based Equalization Channel Performance Improvement through FF and RBF Neural Network based Equalization Manish Mahajan 1, Deepak Pancholi 2, A.C. Tiwari 3 Research Scholar 1, Asst. Professor 2, Professor 3 Lakshmi Narain

More information

Automata Construct with Genetic Algorithm

Automata Construct with Genetic Algorithm Automata Construct with Genetic Algorithm Vít Fábera Department of Informatics and Telecommunication, Faculty of Transportation Sciences, Czech Technical University, Konviktská 2, Praha, Czech Republic,

More information

ADVANCED CONCEPTS IN POLARIMETRIC SAR IMAGE ANALYSIS A TUTORIAL REVIEW

ADVANCED CONCEPTS IN POLARIMETRIC SAR IMAGE ANALYSIS A TUTORIAL REVIEW ADVANCED CONCEPTS IN POLARIMETRIC SAR IMAGE ANALYSIS A TUTORIAL REVIEW ABSTRACT Eric POTTIER (), Jong-Sen LEE (2), Laurent FERRO-FAMIL () () : I.E.T.R UMR CNRS 664, University of Rennes Image and Remote

More information

Lab 9. Julia Janicki. Introduction

Lab 9. Julia Janicki. Introduction Lab 9 Julia Janicki Introduction My goal for this project is to map a general land cover in the area of Alexandria in Egypt using supervised classification, specifically the Maximum Likelihood and Support

More information

Research Article Path Planning Using a Hybrid Evolutionary Algorithm Based on Tree Structure Encoding

Research Article Path Planning Using a Hybrid Evolutionary Algorithm Based on Tree Structure Encoding e Scientific World Journal, Article ID 746260, 8 pages http://dx.doi.org/10.1155/2014/746260 Research Article Path Planning Using a Hybrid Evolutionary Algorithm Based on Tree Structure Encoding Ming-Yi

More information

Color-Based Classification of Natural Rock Images Using Classifier Combinations

Color-Based Classification of Natural Rock Images Using Classifier Combinations Color-Based Classification of Natural Rock Images Using Classifier Combinations Leena Lepistö, Iivari Kunttu, and Ari Visa Tampere University of Technology, Institute of Signal Processing, P.O. Box 553,

More information

An Improved Snake Model for Automatic Extraction of Buildings from Urban Aerial Images and LiDAR Data Using Genetic Algorithm

An Improved Snake Model for Automatic Extraction of Buildings from Urban Aerial Images and LiDAR Data Using Genetic Algorithm An Improved Snake Model for Automatic Extraction of Buildings from Urban Aerial Images and LiDAR Data Using Genetic Algorithm Mostafa Kabolizade 1, Hamid Ebadi 2, Salman Ahmadi 3 1. Ph.D. Student in Photogrammetry

More information

1. Introduction. 2. Motivation and Problem Definition. Volume 8 Issue 2, February Susmita Mohapatra

1. Introduction. 2. Motivation and Problem Definition. Volume 8 Issue 2, February Susmita Mohapatra Pattern Recall Analysis of the Hopfield Neural Network with a Genetic Algorithm Susmita Mohapatra Department of Computer Science, Utkal University, India Abstract: This paper is focused on the implementation

More information

A USER-FRIENDLY AUTOMATIC TOOL FOR IMAGE CLASSIFICATION BASED ON NEURAL NETWORKS

A USER-FRIENDLY AUTOMATIC TOOL FOR IMAGE CLASSIFICATION BASED ON NEURAL NETWORKS A USER-FRIENDLY AUTOMATIC TOOL FOR IMAGE CLASSIFICATION BASED ON NEURAL NETWORKS B. Buttarazzi, F. Del Frate*, C. Solimini Università Tor Vergata, Ingegneria DISP, Via del Politecnico 1, I-00133 Rome,

More information

Bistatic SAR coherence improvement through spatially variant polarimetry

Bistatic SAR coherence improvement through spatially variant polarimetry 1 Bistatic SAR coherence improvement through spatially variant polarimetry By Daniel Andre Centre for Electronic Warfare, Cranfield University, Defence Academy of the United Kingdom, Shrivenham, UK. Abstract

More information

Dynamic Analysis of Structures Using Neural Networks

Dynamic Analysis of Structures Using Neural Networks Dynamic Analysis of Structures Using Neural Networks Alireza Lavaei Academic member, Islamic Azad University, Boroujerd Branch, Iran Alireza Lohrasbi Academic member, Islamic Azad University, Boroujerd

More information

A New Method for Correcting ScanSAR Scalloping Using Forests and inter SCAN Banding Employing Dynamic Filtering

A New Method for Correcting ScanSAR Scalloping Using Forests and inter SCAN Banding Employing Dynamic Filtering A New Method for Correcting ScanSAR Scalloping Using Forests and inter SCAN Banding Employing Dynamic Filtering Masanobu Shimada Japan Aerospace Exploration Agency (JAXA), Earth Observation Research Center

More information

Inducing Parameters of a Decision Tree for Expert System Shell McESE by Genetic Algorithm

Inducing Parameters of a Decision Tree for Expert System Shell McESE by Genetic Algorithm Inducing Parameters of a Decision Tree for Expert System Shell McESE by Genetic Algorithm I. Bruha and F. Franek Dept of Computing & Software, McMaster University Hamilton, Ont., Canada, L8S4K1 Email:

More information

Visual object classification by sparse convolutional neural networks

Visual object classification by sparse convolutional neural networks Visual object classification by sparse convolutional neural networks Alexander Gepperth 1 1- Ruhr-Universität Bochum - Institute for Neural Dynamics Universitätsstraße 150, 44801 Bochum - Germany Abstract.

More information

Estimation of Natural Hazard Damages through the Fusion of Change Maps Obtained from Optical and Radar Earth Observations

Estimation of Natural Hazard Damages through the Fusion of Change Maps Obtained from Optical and Radar Earth Observations Proceedings Estimation of Natural Hazard Damages through the Fusion of Change Maps Obtained from Optical and Radar Earth Observations Reza Shah-Hosseini 1, *, Abdolreza Safari 1 and Saeid Homayouni 2 1

More information

IMPROVING DEMS USING SAR INTERFEROMETRY. University of British Columbia. ABSTRACT

IMPROVING DEMS USING SAR INTERFEROMETRY. University of British Columbia.  ABSTRACT IMPROVING DEMS USING SAR INTERFEROMETRY Michael Seymour and Ian Cumming University of British Columbia 2356 Main Mall, Vancouver, B.C.,Canada V6T 1Z4 ph: +1-604-822-4988 fax: +1-604-822-5949 mseymour@mda.ca,

More information

Real Coded Genetic Algorithm Particle Filter for Improved Performance

Real Coded Genetic Algorithm Particle Filter for Improved Performance Proceedings of 2012 4th International Conference on Machine Learning and Computing IPCSIT vol. 25 (2012) (2012) IACSIT Press, Singapore Real Coded Genetic Algorithm Particle Filter for Improved Performance

More information

Improving the Efficiency of Fast Using Semantic Similarity Algorithm

Improving the Efficiency of Fast Using Semantic Similarity Algorithm International Journal of Scientific and Research Publications, Volume 4, Issue 1, January 2014 1 Improving the Efficiency of Fast Using Semantic Similarity Algorithm D.KARTHIKA 1, S. DIVAKAR 2 Final year

More information

Study of the Effects of Target Geometry on Synthetic Aperture Radar Images using Simulation Studies

Study of the Effects of Target Geometry on Synthetic Aperture Radar Images using Simulation Studies Study of the Effects of Target Geometry on Synthetic Aperture Radar Images using Simulation Studies K. Tummala a,*, A. K. Jha a, S. Kumar b a Geoinformatics Dept., Indian Institute of Remote Sensing, Dehradun,

More information

Unsupervised Classification of PolSAR Data Using a Scattering Similarity Measure Derived from a Geodesic Distance

Unsupervised Classification of PolSAR Data Using a Scattering Similarity Measure Derived from a Geodesic Distance 1 Unsupervised Classification of PolSAR Data Using a Scattering Similarity Measure Derived from a Geodesic Distance Debanshu Ratha Student Member, IEEE, Avik Bhattacharya, Senior Member, IEEE arxiv:1712.00427v1

More information

Distributed Optimization of Feature Mining Using Evolutionary Techniques

Distributed Optimization of Feature Mining Using Evolutionary Techniques Distributed Optimization of Feature Mining Using Evolutionary Techniques Karthik Ganesan Pillai University of Dayton Computer Science 300 College Park Dayton, OH 45469-2160 Dale Emery Courte University

More information

SUPERVISED classification techniques classify the input

SUPERVISED classification techniques classify the input JOURNAL OF L A TEX CLASS FILES, VOL 6, NO 1, JANUARY 2007 1 Feature Selection Based on Hybridization of Genetic Algorithm and Particle Swarm Optimization Pedram Ghamisi, Student Member, IEEE and Jon Atli

More information

Figure 1: Workflow of object-based classification

Figure 1: Workflow of object-based classification Technical Specifications Object Analyst Object Analyst is an add-on package for Geomatica that provides tools for segmentation, classification, and feature extraction. Object Analyst includes an all-in-one

More information

Overview of MOLI data product (MOLI: Multi-footprint Observation Lidar and Imager)

Overview of MOLI data product (MOLI: Multi-footprint Observation Lidar and Imager) Overview of MOLI data product (MOLI: Multi-footprint Observation Lidar and Imager) Jan 7, 2016 JAXA Jumpei Murooka 1 Contents 1. Mission instruments: MOLI 2. Standard products of MOLI 3. Lidar product

More information

An Application of Genetic Algorithm for Auto-body Panel Die-design Case Library Based on Grid

An Application of Genetic Algorithm for Auto-body Panel Die-design Case Library Based on Grid An Application of Genetic Algorithm for Auto-body Panel Die-design Case Library Based on Grid Demin Wang 2, Hong Zhu 1, and Xin Liu 2 1 College of Computer Science and Technology, Jilin University, Changchun

More information

ISSN: [Keswani* et al., 7(1): January, 2018] Impact Factor: 4.116

ISSN: [Keswani* et al., 7(1): January, 2018] Impact Factor: 4.116 IJESRT INTERNATIONAL JOURNAL OF ENGINEERING SCIENCES & RESEARCH TECHNOLOGY AUTOMATIC TEST CASE GENERATION FOR PERFORMANCE ENHANCEMENT OF SOFTWARE THROUGH GENETIC ALGORITHM AND RANDOM TESTING Bright Keswani,

More information

Neural Network Weight Selection Using Genetic Algorithms

Neural Network Weight Selection Using Genetic Algorithms Neural Network Weight Selection Using Genetic Algorithms David Montana presented by: Carl Fink, Hongyi Chen, Jack Cheng, Xinglong Li, Bruce Lin, Chongjie Zhang April 12, 2005 1 Neural Networks Neural networks

More information