A Method on Land Cover Classification by Combining Unsupervised Algorithm and Training Data

Size: px
Start display at page:

Download "A Method on Land Cover Classification by Combining Unsupervised Algorithm and Training Data"

Transcription

1 A Method on Land Cover Classification by Combining Unsupervised Algorithm and Training Data Chen Xiuwan Institute of Remote Sensing and GIS, Peking University Beijing , China Hu Heping Department of Hydraulic Engineering Tsinghua University, Beijing , China Ryutaro Tateishi Center for Environmental Remote Sensing (CEReS) Chiba University, Chiba 263, Japan Chung-Hyun Ahn Electric and Telecommunication Research Institute P. O. Box 1, Yusung-gu, Taejon , Korea Abstract In this paper, a method on land cover identifying by combining unsupervised algorithm and training data (CUT) was developed. The procedures of land cover classification by using the CUT method are: (a) to carry out remotely sensed image classification by using an unsupervised algorithm (e.g. ISODATA unsupervised classification) to make a land cover classification map, MAP 1, with n classes, where n is much greater than the proposed number of land cover classes, m, in the study area; (b) to collect training data for each of the proposed m classes; (c) to make a mask by using training data sets and statistically compute MAP 1 ; (d) to assign the class h in MAP 1 to class c in the final classification map, MAP 2, if and only if the number of pixels in class c is with the maximum ratio at the statistic. The CUT method was also used to produce a land cover classification map in a test area, Ansan City of Korea, with Thematic Mapper (TM) data acquired by Landsat-5. The accuracy analysis on the classification map, as compared to an unsupervised algorithm, showed that the CUT method is simple and reasonable. Introduction Land cover and land cover change are important elements of global environmental change processes (Dickinson, 1995; Hall et al., 1995), and the classification and change detection of land cover has great potential in remote sensing applications. A large body of research has been carried out by using various methodologies and algorithms to derive land cover and change information from different remotely sensed data (e.g., Bach et al, 1994; Carl and Roland, 1994; Chen, 1997; Lichtenegger, 1992; Sailer et al., 1997; Stolz and Wolfram, 1995; Tateishi and Kajiwara, 1991; Tateishi et al., 1991; Tateishi and Wen, 1996; Wismann, 1994). Traditional approaches to automated land cover mapping using remotely sensed data have employed pattern recognition techniques including both supervised and unsupervised approaches (Richards, 1992). More recently, techniques such as expert systems and neural networks have been used (Gong et al., 1996; Benediktsson et al., 1990; Wharton, 1989; Fried and Brodley, 1997). However, the complex component of terrestrial land cover makes it difficult to develop a general method for all applications in different regions in the world, even the best algorithms that have been developed are far from satisfactory given the requirements of land cover monitoring while using different remotely sensed data in different areas. Knowledge-based methodology has great potential for information extraction from remotely sensed data, but there still is much work to be done. In particular, the efforts by integrating multiple approaches, for example supervised and unsupervised algorithms, should be paid special attention. The accuracy of land cover mapping by using a supervised algorithm is only dependent on the accuracy and reasonableness of the training data collected and by using Geocarto International, Vol. 14, No. 4, December 1999 Published by Geocarto International Centre, G.P.O. Box 4122, Hong Kong. 15

2 unsupervised algorithm is only determined by the spectral data itself without any information about ground truth. The main purpose of the method on land cover identifying by combining unsupervised algorithm and training data (CUT) is to improve the accuracy of land cover classification made by unsupervised algorithm using ground truth data. Methodology By comprehensively making use of the spectral information acquired by the satellite sensor, ground truth information and training data, the CUT method integrates unsupervised clustering with ISODATA and error matrix analysis with training data. Land cover mapping by using CUT method starts from a clustering technique Using an unsupervised algorithm. The Iterative Self-Organizing Data Analysis Technique (ISODATA) was used to perform the classification from multispectal remotely sensed data. For example, a land cover classification map, MAP 1, with n classes was produced by ISODATA clustering, i.e. CLASS 1 = {C 1, C 2,..., C n } (1) and the proposed final classification map, MAP 2, is with m classes, where n is much greater than m. Training data in k spectral bands were collected for each of the proposed m classes, the training dataset for the ith class is DATA i = {D i1, D i2,..., D ij,...,d ik } (2) where i = 1,2,..., m j = 1,2,..., k the size of sample data for the ith class is P i (i = 1,2,..., m). To make a mask by using training data to produce m images IMAGE.MSK = {I 1.msk, I 2.msk,..., I i.msk,..., I m.msk} (3) where i = 1, 2,..., m. The next step is to overlay the image I i.msk with classification map, MAP 1, and perform a statistical analysis on MAP 1. Suppose the P i pixels on MAP 1 include r classes with the size of P i1, P i2,..., P ir, for class c 1, c 2,..., c r, respectively, where r < = m and r P i = Σ P ij. An index ID ij is calculated by normalizing P ij, j=1 ID ij = P ij /P i (4) Therefore, decide class h on MAP 1 is in class c on MAP 2 if, and only if, ID hc = MAX (ID c1, ID c2,..., ID ci,..., ID cm ) (5) where, i=1, 2,..., m. ISODATA Classification Algorithm Hundreds of clustering methods have been developed for land cover / use investigation in the field of remote sensing (Jensen, 1996). Clustering algorithms used for the unsupervised classification of remotely sensed data generally vary according to the efficiency with which the clustering takes place. Different criteria of efficiency lead to different approaches (Haralick and Fu, 1983). ISODATA is a widely used clustering algorithm (Tou and Gonzalez, 1977; Sabins, 1987; Jain, 1989). It represents a fairly comprehensive set of heuristic (rule-of thumb) procedures that have been incorporated into an iterative classification algorithm (ERDAS, 1994; USGS, 1990; Hayward, 1993). Many of the steps incorporated into the algorithm are a result of experience gabled through experimentation. ISODATA calculates class means which are evenly distributed in the data space and then iteratively clusters the remaining pixels using minimum distance techniques. Each iteration recalculates means and reclassifies pixels with respect to the new means. This process continues until the number of pixels in each class changes by less than the selected pixel change threshold or the maximum number of iterations is reached. Accuracy Assessment To correctly perform classification accuracy assessment, it is necessary to compare two sources of information: (1) the remote-sensing-derived classification map and (2) what we will call reference test information (which may in fact contain error). The relationship between these two sets of information is commonly summarized in an error matrix. The ideal situation to perform error evaluation is to locate reference test pixels in the study area. Most analysts prefer stratified random sampling by which a minimum number of samples are selected from each strata (i.e., land-use category). Some combination of random and stratified sampling provides the best balance between statistical validity and practical application (Dicks and Lo. 1990). Ideally, the x, y location of the reference test sites is determined using global positioning system (GPS) instruments (Abler, 1993). After the test reference information has been collected from the randomly located sites, it is compared on a pixelby-pixel basis with the information present in the remotesensing-derived classification map. Agreement and disagreement are summarized in the cells of the error matrix. By using simple descriptive statistical technique, overall accuracy is computed by dividing the total correct (sum of the major diagonal) by the total number of pixels in the matrix. Results and Discussion Test Area The study area, Ansan City, is located in the west coastal region of Korea (see Figure 1). The selected area is km 2 (18 km x 18 km), which includes forest, grassland, urban and built-up land, lakes and reservoirs, sea and tidal zone, saltpan, agricultural land and wetland. 16

3 the Landsat TM data of May 20, 1993, one is subr 9305.img which includes seven TM bands, the other is r-ndvi93.img. which includes seven TM bands and Normalized Difference Vegetation Index (NDVI) band. Training Datasets Collecting In order to perform training data collection, it is necessary to make false color composite images. In reviewing the work of Chen, 1997, the best composite scheme for our purpose is: R:G:B = (0.7 * TM * TM6) : (0.5 * TM * TM4) : (0.3 * TM * TM * TM7) This was used to produce false color composite image, r93fcc.img. Two training datasets, roi and roi, were collected randomly from the false color composite image r93fcc.img. One of the two datasets was used to perform supervised classification while the other was used to assess the accuracy of classification maps. Figure 1 Location of the Study Area (Ansan City, Korea). Satellite Data The remotely sensed data were acquired by Thematic Mapper (TM) on Landsat 5 on May , which covers a region cross Ansan, Incheon, and Seoul. This image consists of 7 bands by 2377 lines and 2357 samples and thus has a total of 5,602,589 points for each band. The data used in this study were extracted as a subscene from the original dataset, with 600 x 600 points which covers the study area shown in Figure 1. The statistical characteristics of TM data in the study area were shown in Table 1. Land Cover Classification System Certain classification schemes have been developed that can readily incorporate land-use and/or land-cover data obtained by interpreting remotely sensed data, e.g., U.S. Geological Survey Land Use/Land Cover Classification System (Anderson et al., 1976; USGS, 1990; Jensen, 1996), U.S. Fish & Wildlife Service Wetland Classification System (Cowardin et al., 1979; Jensen, 1996) and NOAA CoastWatch Land Cover Classification System (Dobson et al., 1995; Jensen, 1996). The U.S. Geological Survey Land Use/ Land Cover Classification System was chosen and referred to form the classification system for this study. By considering on the four levels of the U.S. Geological Survey Land Use/ Land Cover Classification System and the type of remotely sensed data typically used to provide the information, the classification system was created as in Table 2. Dataset Formation By image preprocessing including atmospheric and geometric corrections, two datasets were prepared based on Classifying For the comparable purpose, ISODATA unsupervised classification algorithm and CUT method were used to process the TM datasets subr9305.img and r-ndvi93.img. By ISODATA clustering, two classification maps, r-9.cla and rv-9.cla with 9 categories, were yielded. By using the CUT method, two classification maps, r-25.cla and rv- 25.cla with 25 classes, were made by ISODATA clustering. Then the training dataset roi was used to make masks and statistically compute the two maps, r-25.cla and rv-25.cla. Finally, the decision with the rule in equation (5) was applied to the final classification maps, thus cr-25.cla and crv-25.cla with 9 categories were produced. Accuracy Assessment The error matrices of the four classification maps r- 9.cla, rv-9.cla, cr-25.cla and crv-25.cla were analyzed by using the training data roi. As an example, Table 3 gives the error matrix of the classification map crv-25.cla, which shows that the map has high accuracy for identifying water area except the reservoir at the upper-right corner of the image, difficult to distinguish rangeland from forest land, saltpan from agricultural land, and urban and built-up land from barren land, and very difficult to distinguish wetland from tidal zone. Table 4 gives the overall accuracy calculated based on the error matrix analysis of each classification maps. For the two datasets, with and without NDVI, the classification accuracy is 0.68 and 0.82 by CUT method while it is 0.64 and 0.78 by ISODATA method. It is obvious that the accuracy of classification maps can be improved by using CUT method. Conclusion This study shows that the CUT method is a reasonable approach and useful tool to derive land cover information 17

4 Table 1 Statistic Characteristics of Landsat TM Data in Ansan, Korea Band Min Max Mean Stdev Eigenval Covariance Matrix Band Band 1 Band 2 Band 3 Band 4 Band 5 Band 6 Band Correlation Matrix Band Band 1 Band 2 Band 3 Band 4 Band 5 Band 6 Band Eigenvectors Band Band 1 Band 2 Band 3 Band 4 Band 5 Band 6 Band Table 2 Land Cover Classification System in Ansan, Korea Table 3 Error Matrix of the Classification Map Derived from Landsat Data of Ansan, Korea (crv-25.cla) Class Description Unclassified 1 Forest land 2 Rangeland 3 Agricultural land 4 Wetland 5 Barren land 6 Urban and/or built-up land 7 Salt pan 8 Tidal zone 9 Water (sea and inland water body) Classification Forest Range- Agricultural Wet- Barren Urban and Salt Tidal Water Row land land land land land built-up land pan zone Total Forest land Range land Agricultural Wetland Barren land Urban and built-up land Salt pan Tidal zone Water Column Total Overall Accuracy = 41017/49769 =

5 Method Table 4 from remotely sensed data, can provide estimates of land cover classification to an acceptable accuracy. It is undoubted that the CUT method can improve the accuracy of classification map made by ISODATA unsupervised algorithm. The accuracy of land cover classification in this study was influenced by the lack of ground truth information of the study area. With little information about the study area, it is difficult to collect accurate training data that is the key factor for classification. It is essential to collect in situ data by investigation. Ideally, the x, y location of the training sites is determined using global positioning system (GPS) instruments. Ancillary data, such as the maps of elevation, slope, aspect, geology, soils, hydrology, transportation network, boundaries, vegetation, etc., should be incorporated in the classification process to improve the accuracy and quality of remote-sensing-derived land-cover classification, if possible. The CUT method, in addition to ground truth data, yields a high accuracy. The authors wish the method would be tested and applied in land cover classification in other research areas. References Overall accuracy on the classification maps Accuracy of Results without NDVI band combining with NDVI ISODATA CUT Abler, R. F Everything in its place: GPS, GIS. and geography in 1990s. Professional Geographer, 45(2): Anderson, J. R., E. Hardy, J. Roach, and R. Witmer A land Use and Land Cover Classification System for Use with Remote Sensor Data. Washington, DC: U.S. Geological Survey Profession Paper 964, 28p. Bach, H.; A. Demircan; and W. Mauser The use of AVIRIS data for the determination of agricultural plant development and water content. Earth Observation Quarterly (ISSN X), no. 46, Dec. 1994, p Benediktsson, J.; P. Swain; and O. K. Ersoy Neural network approaches versus statistical methods in classification of multisource remote sensing data. IEEE Transactions on Geoscience and Remote Sensing 28: Campbell, J Introduction to Remote Sensing. New York: Guilford Press, 551p. Carl, Sebastian and Kraft Roland Landuse classification of ERS-1 images with an artificial neural network. Image and signal processing for remote sensing; Proceedings of the Meeting, Rome, Italy, Sept , 1994 (A ), Bellingham. WA, Society of Photo-Optical Instrumentation Engineers (SPIE Proceedings. Vol. 2315), 1994, p Chen, Xiuwan Analysis on Land Cover Change and Its Impacts on Sustainable Development based on Remote Sensing and GIS: A Case Study in Ansan, Korea. Systems Engineering Research Institute, Korea Institute of Science and Technology, Taejon, Korea. pp. 84. Cowardin. L. M., V Carter, F. C. Golet, and E. T. LaRoe Classification of Wetlands and Deepwater Habitats of the United States. Washington, DC: U.S. Fish and Wildlife Service, FWS/ OBS-79/31, 103p. Dickinson, R Land processes in climate models. Remote Sensing of Environment, 51: Dobson, J. R., E. A. Bright, D. W. Field, L. L. Wood, K. D. Haddad, H. Iredale, J. R. Jensen, V. V. Klemas, R. J. Orth, and J. P. Thomas NOAA Coastal Change Analysis Program (C-CAP): Guidance for Regional Implementation. Washington, DC: National Oceanic and Atmospheric Administration, NMFS 123, 92p. ERDAS ERDAS Field Guide. Atlanta, GA: ERDAS, Inc., 628p. Friedl, M. A. and C. E. Brodley Decision tree classification of land cover from remotely sensed data. Remote Sensing of Environment, 61: Gong P., R. Pu and J. Chen Mapping ecological land systems and classification uncertainties from digital elevation and forestcover data using neural networks. Photogrammetric Engineering & Remote Sensing, 62(11): Hall, F. G.; J. R. Townsend; and E. T. Engman Status of remote sensing algorithms for estimation of land surface state parameters. Remote Sensing of Environment, 51: Haralick, R. M. and K. Fu Pattern recognition and classification. Chapter 8 in Manual of Remote Sensing, R. Colwell, ed. Falls Church, VA: American Society of Photogrammetry, 1: Hayward, D Correspondence about Earth Resource Mapping ISODATA Algorithm. San Diego, CA: ERM, Inc., 21p. Hudson, W. and C. Ramm Correct formulation of the Kappa coefficient of agreement. Photogrammetric Engineering and Remote Sensing, 53(4): Jain, A. K Fundamentals of Digital Image Processing. Englewood Cliffs, NJ: Prentice Halls p Jensen, J. R Introductory Digital Image Processing - A Remote Sensing Perspective. Second Edition. Prentice Hall, Upper Saddle River, New Jersey p. Sabins, M. J Convergence and consistency of fuzzy c-means/ ISODATA algorithms. IEEE Transactions on Pattern Analysis and Machine Intelligence, 9: Sailer, C. T., E. L. E. Eason, and J. L. Brickey Operational multispectral information extraction: the DLPO image interpretation program. Photogrammetric Engineering and Remote Sensing 63(2): , Stolz, Roswitha; Mauser, Wolfram First evaluations of Shuttle X-SAR and SIR-C data on land cover Erste Auswertungen von Shuttle X-SAR und SIR-C Daten zur Oberflaechenbedeckung. Kleinheubacher Berichte (ISSN ), vol , p Tateishi, R. and C. Wen Four-minute land cover dataset of Asia. Proceedings of International Symposium on Remote Sensing October 24-25, 1996, Cheju, Korea. 19

6 Tateishi, R. and K. Kajiwara Global land cover monitoring by NOAA NDVI data. Proceedings of the International Workshop of Environmental Monitoring from Space, November 15-18, Taejon, Korea, p Tateishi, R., K. Kajiwara and T. Odajima Global land cover classification by phenological methods using NOAA GVI data. Asian-Pacific Remote Sensing Journal, Vol. 4, No.1. Tou, J. T. and R. C. Gonzalez Pattern Recognition Principles. Reading MA: Addison-Wesley 377p. USGS Land Analysis System (LAS) V.5 User Guide. Sioux Falls, SD: EROS Data Center, 330p. Wharton, S. W Knowledge-based spectral classification of remotely sensed image data. Theory and Applications of Optical Remote Sensing (G. Asrar, Ed.), Wiley, New York. Wismann, V. R Land surface monitoring using the ERS-I scatterometer. Earth Observation Quarterly (ISSN X), no. 44, June 1994, p

Remote Sensing and Land Use Classification: Supervised vs. Unsupervised Classification Glen Busch

Remote Sensing and Land Use Classification: Supervised vs. Unsupervised Classification Glen Busch Remote Sensing and Land Use Classification: Supervised vs. Unsupervised Classification Glen Busch Introduction In this time of large-scale planning and land management on public lands, managers are increasingly

More information

Land Use/Land Cover Map of the Central Facility of ARM in the Southern Great Plains Site Using DOE s Multi-Spectral Thermal Imager Satellite Images

Land Use/Land Cover Map of the Central Facility of ARM in the Southern Great Plains Site Using DOE s Multi-Spectral Thermal Imager Satellite Images Land Use/Land Cover Map of the Central Facility of ARM in the Southern Great Plains Site Using DOE s Multi-Spectral Thermal Imager Satellite Images S. E. Báez Cazull Pre-Service Teacher Program University

More information

WATER BODY EXTRACTION FROM MULTI SPECTRAL IMAGE BY SPECTRAL PATTERN ANALYSIS

WATER BODY EXTRACTION FROM MULTI SPECTRAL IMAGE BY SPECTRAL PATTERN ANALYSIS WATER BODY EXTRACTION FROM MULTI SPECTRAL IMAGE BY SPECTRAL PATTERN ANALYSIS Nguyen Dinh Duong Department of Environmental Information Study and Analysis, Institute of Geography, 18 Hoang Quoc Viet Rd.,

More information

Environmental Remote Sensing GEOG 2021

Environmental Remote Sensing GEOG 2021 Environmental Remote Sensing GEOG 2021 Lecture 4 Image classification 2 Purpose categorising data data abstraction / simplification data interpretation mapping for land cover mapping use land cover class

More information

Some elements of photo. interpretation

Some elements of photo. interpretation Some elements of photo Shape Size Pattern Color (tone, hue) Texture Shadows Site Association interpretation Olson, C. E., Jr. 1960. Elements of photographic interpretation common to several sensors. Photogrammetric

More information

CROP CLASSIFICATION WITH HYPERSPECTRAL DATA OF THE HYMAP SENSOR USING DIFFERENT FEATURE EXTRACTION TECHNIQUES

CROP CLASSIFICATION WITH HYPERSPECTRAL DATA OF THE HYMAP SENSOR USING DIFFERENT FEATURE EXTRACTION TECHNIQUES Proceedings of the 2 nd Workshop of the EARSeL SIG on Land Use and Land Cover CROP CLASSIFICATION WITH HYPERSPECTRAL DATA OF THE HYMAP SENSOR USING DIFFERENT FEATURE EXTRACTION TECHNIQUES Sebastian Mader

More information

Analysis of Landsat ETM+ Image Enhancement for Lithological Classification Improvement in Eagle Plain Area, Northern Yukon

Analysis of Landsat ETM+ Image Enhancement for Lithological Classification Improvement in Eagle Plain Area, Northern Yukon Analysis of Landsat ETM+ Image Enhancement for Lithological Classification Improvement in Eagle Plain Area, Northern Yukon Shihua Zhao, Department of Geology, University of Calgary, zhaosh@ucalgary.ca,

More information

Partitioning the Conterminous United States into Mapping Zones for Landsat TM Land Cover Mapping

Partitioning the Conterminous United States into Mapping Zones for Landsat TM Land Cover Mapping Partitioning the Conterminous United States into Mapping Zones for Landsat TM Land Cover Mapping Collin Homer Raytheon, EROS Data Center, Sioux Falls, South Dakota 605-594-2714 homer@usgs.gov Alisa Gallant

More information

APPLICATION OF MULTITEMPORAL LANDSAT DATA TO MAP AND MONITOR LAND COVER AND LAND USE CHANGE IN THE CHESAPEAKE BAY WATERSHED

APPLICATION OF MULTITEMPORAL LANDSAT DATA TO MAP AND MONITOR LAND COVER AND LAND USE CHANGE IN THE CHESAPEAKE BAY WATERSHED APPLICATION OF MULTITEMPORAL LANDSAT DATA TO MAP AND MONITOR LAND COVER AND LAND USE CHANGE IN THE CHESAPEAKE BAY WATERSHED S. J. GOETZ Woods Hole Research Center Woods Hole, Massachusetts 054-096 USA

More information

Accuracy Assessment of Land Use Land Cover Classification using Google Earth

Accuracy Assessment of Land Use Land Cover Classification using Google Earth American Journal of Environmental Protection 25; 4(4): 9-98 Published online July 2, 25 (http://www.sciencepublishinggroup.com/j/ajep) doi:.648/j.ajep.2544.4 ISSN: 228-568 (Print); ISSN: 228-5699 (Online)

More information

Analysis of Land Use/Land Cover Change in Jammu District Using Geospatial Techniques

Analysis of Land Use/Land Cover Change in Jammu District Using Geospatial Techniques Analysis of Land Use/Land Cover Change in Jammu District Using Geospatial Techniques Dr. Anuradha Sharma 1, Davinder Singh 2 1 Head, Department of Geography, University of Jammu, Jammu-180006, India 2

More information

Landsat Monitoring our Earth s Condition for over 40 years

Landsat Monitoring our Earth s Condition for over 40 years Landsat Monitoring our Earth s Condition for over 40 years Thomas Cecere Land Remote Sensing Program USGS ISPRS:Earth Observing Data and Tools for Health Studies Arlington, VA August 28, 2013 U.S. Department

More information

Generation of Cloud-free Imagery Using Landsat-8

Generation of Cloud-free Imagery Using Landsat-8 Generation of Cloud-free Imagery Using Landsat-8 Byeonghee Kim 1, Youkyung Han 2, Yonghyun Kim 3, Yongil Kim 4 Department of Civil and Environmental Engineering, Seoul National University (SNU), Seoul,

More information

Digital Remote Sensing Data Processing Digital Remote Sensing Data Processing and Analysis: An Introduction and Analysis: An Introduction

Digital Remote Sensing Data Processing Digital Remote Sensing Data Processing and Analysis: An Introduction and Analysis: An Introduction Digital Remote Sensing Data Processing Digital Remote Sensing Data Processing and Analysis: An Introduction and Analysis: An Introduction Content Remote sensing data Spatial, spectral, radiometric and

More information

How To Update A Vegetation And Land Cover Map For Florida

How To Update A Vegetation And Land Cover Map For Florida Florida Vegetation and Land Cover Data Derived from 2003 Landsat ETM+ Imagery Beth Stys, Randy Kautz, David Reed, Melodie Kertis, Robert Kawula, Cherie Keller, and Anastasia Davis Florida Fish and Wildlife

More information

COASTAL MONITORING & OBSERVATIONS LESSON PLAN Do You Have Change?

COASTAL MONITORING & OBSERVATIONS LESSON PLAN Do You Have Change? Coastal Change Analysis Lesson Plan COASTAL MONITORING & OBSERVATIONS LESSON PLAN Do You Have Change? NOS Topic Coastal Monitoring and Observations Theme Coastal Change Analysis Links to Overview Essays

More information

Remote Sensing in Natural Resources Mapping

Remote Sensing in Natural Resources Mapping Remote Sensing in Natural Resources Mapping NRS 516, Spring 2016 Overview of Remote Sensing in Natural Resources Mapping What is remote sensing? Why remote sensing? Examples of remote sensing in natural

More information

ANALYSIS OF FOREST CHANGE IN FIRE DAMAGE AREA USING SATELLITE IMAGES

ANALYSIS OF FOREST CHANGE IN FIRE DAMAGE AREA USING SATELLITE IMAGES ANALYSIS OF FOREST CHANGE IN FIRE DAMAGE AREA USING SATELLITE IMAGES Joon Mook Kang, Professor Joon Kyu Park, Ph.D Min Gyu Kim, Ph.D._Candidate Dept of Civil Engineering, Chungnam National University 220

More information

An Assessment of the Effectiveness of Segmentation Methods on Classification Performance

An Assessment of the Effectiveness of Segmentation Methods on Classification Performance An Assessment of the Effectiveness of Segmentation Methods on Classification Performance Merve Yildiz 1, Taskin Kavzoglu 2, Ismail Colkesen 3, Emrehan K. Sahin Gebze Institute of Technology, Department

More information

Land Use/ Land Cover Mapping Initiative for Kansas and the Kansas River Watershed

Land Use/ Land Cover Mapping Initiative for Kansas and the Kansas River Watershed Land Use/ Land Cover Mapping Initiative for Kansas and the Kansas River Watershed Kansas Biological Survey Kansas Applied Remote Sensing Program April 2008 Previous Kansas LULC Projects Kansas LULC Map

More information

Methods for Monitoring Forest and Land Cover Changes and Unchanged Areas from Long Time Series

Methods for Monitoring Forest and Land Cover Changes and Unchanged Areas from Long Time Series Methods for Monitoring Forest and Land Cover Changes and Unchanged Areas from Long Time Series Project using historical satellite data from SACCESS (Swedish National Satellite Data Archive) for developing

More information

ENVIRONMENTAL MONITORING Vol. I - Remote Sensing (Satellite) System Technologies - Michael A. Okoye and Greg T. Koeln

ENVIRONMENTAL MONITORING Vol. I - Remote Sensing (Satellite) System Technologies - Michael A. Okoye and Greg T. Koeln REMOTE SENSING (SATELLITE) SYSTEM TECHNOLOGIES Michael A. Okoye and Greg T. Earth Satellite Corporation, Rockville Maryland, USA Keywords: active microwave, advantages of satellite remote sensing, atmospheric

More information

Multiscale Object-Based Classification of Satellite Images Merging Multispectral Information with Panchromatic Textural Features

Multiscale Object-Based Classification of Satellite Images Merging Multispectral Information with Panchromatic Textural Features Remote Sensing and Geoinformation Lena Halounová, Editor not only for Scientific Cooperation EARSeL, 2011 Multiscale Object-Based Classification of Satellite Images Merging Multispectral Information with

More information

Objectives. Raster Data Discrete Classes. Spatial Information in Natural Resources FANR 3800. Review the raster data model

Objectives. Raster Data Discrete Classes. Spatial Information in Natural Resources FANR 3800. Review the raster data model Spatial Information in Natural Resources FANR 3800 Raster Analysis Objectives Review the raster data model Understand how raster analysis fundamentally differs from vector analysis Become familiar with

More information

A KNOWLEDGE-BASED APPROACH FOR REDUCING CLOUD AND SHADOW ABSTRACT

A KNOWLEDGE-BASED APPROACH FOR REDUCING CLOUD AND SHADOW ABSTRACT A KNOWLEDGE-BASED APPROACH FOR REDUCING CLOUD AND SHADOW Mingjun Song, Graduate Research Assistant Daniel L. Civco, Director Laboratory for Earth Resources Information Systems Department of Natural Resources

More information

Texas Prairie Wetlands Project (TPWP) Performance Monitoring

Texas Prairie Wetlands Project (TPWP) Performance Monitoring Texas Prairie Wetlands Project (TPWP) Performance Monitoring Relationship to Gulf Coast Joint Venture (GCJV) Habitat Conservation: Priority Species: Wintering waterfowl species in the Texas portion of

More information

2002 URBAN FOREST CANOPY & LAND USE IN PORTLAND S HOLLYWOOD DISTRICT. Final Report. Michael Lackner, B.A. Geography, 2003

2002 URBAN FOREST CANOPY & LAND USE IN PORTLAND S HOLLYWOOD DISTRICT. Final Report. Michael Lackner, B.A. Geography, 2003 2002 URBAN FOREST CANOPY & LAND USE IN PORTLAND S HOLLYWOOD DISTRICT Final Report by Michael Lackner, B.A. Geography, 2003 February 2004 - page 1 of 17 - TABLE OF CONTENTS Abstract 3 Introduction 4 Study

More information

SAMPLE MIDTERM QUESTIONS

SAMPLE MIDTERM QUESTIONS Geography 309 Sample MidTerm Questions Page 1 SAMPLE MIDTERM QUESTIONS Textbook Questions Chapter 1 Questions 4, 5, 6, Chapter 2 Questions 4, 7, 10 Chapter 4 Questions 8, 9 Chapter 10 Questions 1, 4, 7

More information

Cafcam: Crisp And Fuzzy Classification Accuracy Measurement Software

Cafcam: Crisp And Fuzzy Classification Accuracy Measurement Software Cafcam: Crisp And Fuzzy Classification Accuracy Measurement Software Mohamed A. Shalan 1, Manoj K. Arora 2 and John Elgy 1 1 School of Engineering and Applied Sciences, Aston University, Birmingham, UK

More information

Calculation of Minimum Distances. Minimum Distance to Means. Σi i = 1

Calculation of Minimum Distances. Minimum Distance to Means. Σi i = 1 Minimum Distance to Means Similar to Parallelepiped classifier, but instead of bounding areas, the user supplies spectral class means in n-dimensional space and the algorithm calculates the distance between

More information

Extraction of Satellite Image using Particle Swarm Optimization

Extraction of Satellite Image using Particle Swarm Optimization Extraction of Satellite Image using Particle Swarm Optimization Er.Harish Kundra Assistant Professor & Head Rayat Institute of Engineering & IT, Railmajra, Punjab,India. Dr. V.K.Panchal Director, DTRL,DRDO,

More information

DETECTING LANDUSE/LANDCOVER CHANGES ALONG THE RING ROAD IN PESHAWAR CITY USING SATELLITE REMOTE SENSING AND GIS TECHNIQUES

DETECTING LANDUSE/LANDCOVER CHANGES ALONG THE RING ROAD IN PESHAWAR CITY USING SATELLITE REMOTE SENSING AND GIS TECHNIQUES ------------------------------------------------------------------------------------------------------------------------------- Full length Research Paper -------------------------------------------------------------------------------------------------------------------------------

More information

Supervised Classification workflow in ENVI 4.8 using WorldView-2 imagery

Supervised Classification workflow in ENVI 4.8 using WorldView-2 imagery Supervised Classification workflow in ENVI 4.8 using WorldView-2 imagery WorldView-2 is the first commercial high-resolution satellite to provide eight spectral sensors in the visible to near-infrared

More information

GEOG 579 - Remote Sensing 76634-001

GEOG 579 - Remote Sensing 76634-001 GEOG 579 - Remote Sensing 76634-001 Syllabus Instructor: Dr. Ron Resmini Course description and objective: GEOG 579, Remote Sensing, will provide graduate students with the concepts, principles, and methods

More information

RESOLUTION MERGE OF 1:35.000 SCALE AERIAL PHOTOGRAPHS WITH LANDSAT 7 ETM IMAGERY

RESOLUTION MERGE OF 1:35.000 SCALE AERIAL PHOTOGRAPHS WITH LANDSAT 7 ETM IMAGERY RESOLUTION MERGE OF 1:35.000 SCALE AERIAL PHOTOGRAPHS WITH LANDSAT 7 ETM IMAGERY M. Erdogan, H.H. Maras, A. Yilmaz, Ö.T. Özerbil General Command of Mapping 06100 Dikimevi, Ankara, TURKEY - (mustafa.erdogan;

More information

ENVI Classic Tutorial: Classification Methods

ENVI Classic Tutorial: Classification Methods ENVI Classic Tutorial: Classification Methods Classification Methods 2 Files Used in this Tutorial 2 Examining a Landsat TM Color Image 3 Reviewing Image Colors 3 Using the Cursor Location/Value 4 Examining

More information

Review for Introduction to Remote Sensing: Science Concepts and Technology

Review for Introduction to Remote Sensing: Science Concepts and Technology Review for Introduction to Remote Sensing: Science Concepts and Technology Ann Johnson Associate Director ann@baremt.com Funded by National Science Foundation Advanced Technological Education program [DUE

More information

COMPARISON OF OBJECT BASED AND PIXEL BASED CLASSIFICATION OF HIGH RESOLUTION SATELLITE IMAGES USING ARTIFICIAL NEURAL NETWORKS

COMPARISON OF OBJECT BASED AND PIXEL BASED CLASSIFICATION OF HIGH RESOLUTION SATELLITE IMAGES USING ARTIFICIAL NEURAL NETWORKS COMPARISON OF OBJECT BASED AND PIXEL BASED CLASSIFICATION OF HIGH RESOLUTION SATELLITE IMAGES USING ARTIFICIAL NEURAL NETWORKS B.K. Mohan and S. N. Ladha Centre for Studies in Resources Engineering IIT

More information

y = Xβ + ε B. Sub-pixel Classification

y = Xβ + ε B. Sub-pixel Classification Sub-pixel Mapping of Sahelian Wetlands using Multi-temporal SPOT VEGETATION Images Jan Verhoeye and Robert De Wulf Laboratory of Forest Management and Spatial Information Techniques Faculty of Agricultural

More information

COMPARING DIFFERENT SATELLITE IMAGE CLASSIFICATION METHODS: AN APPLICATION IN AYVALIK DISTRICT,WESTERN TURKEY.

COMPARING DIFFERENT SATELLITE IMAGE CLASSIFICATION METHODS: AN APPLICATION IN AYVALIK DISTRICT,WESTERN TURKEY. COMPARING DIFFERENT SATELLITE IMAGE CLASSIFICATION METHODS: AN APPLICATION IN AYVALIK DISTRICT,WESTERN TURKEY. Aykut AKGÜN a,*, A.Hüsnü ERONAT b and Necdet TÜRK a - (aykut.akgun@deu.edu.tr) a Dokuz Eylul

More information

Object-Oriented Approach of Information Extraction from High Resolution Satellite Imagery

Object-Oriented Approach of Information Extraction from High Resolution Satellite Imagery IOSR Journal of Computer Engineering (IOSR-JCE) e-issn: 2278-0661,p-ISSN: 2278-8727, Volume 17, Issue 3, Ver. IV (May Jun. 2015), PP 47-52 www.iosrjournals.org Object-Oriented Approach of Information Extraction

More information

MODIS IMAGES RESTORATION FOR VNIR BANDS ON FIRE SMOKE AFFECTED AREA

MODIS IMAGES RESTORATION FOR VNIR BANDS ON FIRE SMOKE AFFECTED AREA MODIS IMAGES RESTORATION FOR VNIR BANDS ON FIRE SMOKE AFFECTED AREA Li-Yu Chang and Chi-Farn Chen Center for Space and Remote Sensing Research, National Central University, No. 300, Zhongda Rd., Zhongli

More information

Digital image processing

Digital image processing 746A27 Remote Sensing and GIS Lecture 4 Digital image processing Chandan Roy Guest Lecturer Department of Computer and Information Science Linköping University Digital Image Processing Most of the common

More information

III THE CLASSIFICATION OF URBAN LAND COVER USING REMOTE SENSING

III THE CLASSIFICATION OF URBAN LAND COVER USING REMOTE SENSING The Dynamics of Global Urban Expansion 31 III THE CLASSIFICATION OF URBAN LAND COVER USING REMOTE SENSING 1. Overview and Rationale The systematic study of global urban expansion requires good data that

More information

VCS REDD Methodology Module. Methods for monitoring forest cover changes in REDD project activities

VCS REDD Methodology Module. Methods for monitoring forest cover changes in REDD project activities 1 VCS REDD Methodology Module Methods for monitoring forest cover changes in REDD project activities Version 1.0 May 2009 I. SCOPE, APPLICABILITY, DATA REQUIREMENT AND OUTPUT PARAMETERS Scope This module

More information

A STRATEGY FOR ESTIMATING TREE CANOPY DENSITY USING LANDSAT 7 ETM+ AND HIGH RESOLUTION IMAGES OVER LARGE AREAS

A STRATEGY FOR ESTIMATING TREE CANOPY DENSITY USING LANDSAT 7 ETM+ AND HIGH RESOLUTION IMAGES OVER LARGE AREAS A STRATEGY FOR ESTIMATING TREE CANOPY DENSITY USING LANDSAT 7 ETM+ AND HIGH RESOLUTION IMAGES OVER LARGE AREAS Chengquan Huang*, Limin Yang, Bruce Wylie, Collin Homer Raytheon ITSS EROS Data Center, Sioux

More information

CIESIN Columbia University

CIESIN Columbia University Conference on Climate Change and Official Statistics Oslo, Norway, 14-16 April 2008 The Role of Spatial Data Infrastructure in Integrating Climate Change Information with a Focus on Monitoring Observed

More information

Forest Biometrics From Space

Forest Biometrics From Space Forest Biometrics From Space Timothy B. Hill Lead Remote Sensing / GIS Analyst Geographic Resource Solutions 1125 16th Street, Suite 213 Arcata, CA 95521 ABSTRACT Geographic Resource Solutions (GRS) recently

More information

Remote Sensing and GIS Application In Change Detection Study In Urban Zone Using Multi Temporal Satellite

Remote Sensing and GIS Application In Change Detection Study In Urban Zone Using Multi Temporal Satellite Remote Sensing and GIS Application In Change Detection Study In Urban Zone Using Multi Temporal Satellite R.Manonmani, G.Mary Divya Suganya Institute of Remote Sensing, Anna University, Chennai 600 025

More information

Remote Sensing an Introduction

Remote Sensing an Introduction Remote Sensing an Introduction Seminar: Space is the Place Referenten: Anica Huck & Michael Schlund Remote Sensing means the observation of, or gathering information about, a target by a device separated

More information

A HIERARCHICAL APPROACH TO LAND USE AND LAND COVER MAPPING USING MULTIPLE IMAGE TYPES ABSTRACT INTRODUCTION

A HIERARCHICAL APPROACH TO LAND USE AND LAND COVER MAPPING USING MULTIPLE IMAGE TYPES ABSTRACT INTRODUCTION A HIERARCHICAL APPROACH TO LAND USE AND LAND COVER MAPPING USING MULTIPLE IMAGE TYPES Daniel L. Civco 1, Associate Professor James D. Hurd 2, Research Assistant III Laboratory for Earth Resources Information

More information

Pixel-based and object-oriented change detection analysis using high-resolution imagery

Pixel-based and object-oriented change detection analysis using high-resolution imagery Pixel-based and object-oriented change detection analysis using high-resolution imagery Institute for Mine-Surveying and Geodesy TU Bergakademie Freiberg D-09599 Freiberg, Germany imgard.niemeyer@tu-freiberg.de

More information

Assessing Hurricane Katrina Damage to the Mississippi Gulf Coast Using IKONOS Imagery

Assessing Hurricane Katrina Damage to the Mississippi Gulf Coast Using IKONOS Imagery Assessing Hurricane Katrina Damage to the Mississippi Gulf Coast Using IKONOS Imagery Joseph P. Spruce Science Systems and Applications, Inc. John C., MS 39529 Rodney McKellip NASA Project Integration

More information

Outline. Multitemporal high-resolution image classification

Outline. Multitemporal high-resolution image classification IGARSS-2011 Vancouver, Canada, July 24-29, 29, 2011 Multitemporal Region-Based Classification of High-Resolution Images by Markov Random Fields and Multiscale Segmentation Gabriele Moser Sebastiano B.

More information

Modelling, Extraction and Description of Intrinsic Cues of High Resolution Satellite Images: Independent Component Analysis based approaches

Modelling, Extraction and Description of Intrinsic Cues of High Resolution Satellite Images: Independent Component Analysis based approaches Modelling, Extraction and Description of Intrinsic Cues of High Resolution Satellite Images: Independent Component Analysis based approaches PhD Thesis by Payam Birjandi Director: Prof. Mihai Datcu Problematic

More information

Land Cover Mapping of the Comoros Islands: Methods and Results. February 2014. ECDD, BCSF & Durrell Lead author: Katie Green

Land Cover Mapping of the Comoros Islands: Methods and Results. February 2014. ECDD, BCSF & Durrell Lead author: Katie Green Land Cover Mapping of the Comoros Islands: Methods and Results February 2014 ECDD, BCSF & Durrell Lead author: Katie Green About the ECDD project The ECDD project was run by Bristol Conservation & Science

More information

Geospatial intelligence and data fusion techniques for sustainable development problems

Geospatial intelligence and data fusion techniques for sustainable development problems Geospatial intelligence and data fusion techniques for sustainable development problems Nataliia Kussul 1,2, Andrii Shelestov 1,2,4, Ruslan Basarab 1,4, Sergii Skakun 1, Olga Kussul 2 and Mykola Lavreniuk

More information

Global environmental information Examples of EIS Data sets and applications

Global environmental information Examples of EIS Data sets and applications METIER Graduate Training Course n 2 Montpellier - february 2007 Information Management in Environmental Sciences Global environmental information Examples of EIS Data sets and applications Global datasets

More information

National Land Cover Database Visualization and Information Tool

National Land Cover Database Visualization and Information Tool CDI SSF Category 3: Data and Information Assets National Land Cover Database Visualization and Information Tool Applicants/Principle Investigators(s): Collin Homer, USGS EROS, 47914 252 nd St, Sioux Falls,

More information

Research On The Classification Of High Resolution Image Based On Object-oriented And Class Rule

Research On The Classification Of High Resolution Image Based On Object-oriented And Class Rule Research On The Classification Of High Resolution Image Based On Object-oriented And Class Rule Li Chaokui a,b, Fang Wen a,b, Dong Xiaojiao a,b a National-Local Joint Engineering Laboratory of Geo-Spatial

More information

Land-Cover and Imperviousness Data for Regional Areas near Denver, Colorado; Dallas- Fort Worth, Texas; and Milwaukee-Green Bay, Wisconsin - 2001

Land-Cover and Imperviousness Data for Regional Areas near Denver, Colorado; Dallas- Fort Worth, Texas; and Milwaukee-Green Bay, Wisconsin - 2001 U.S. Geological Survey Data Series Land-Cover and Imperviousness Data for Regional Areas near Denver, Colorado; Dallas- Fort Worth, Texas; and Milwaukee-Green Bay, Wisconsin - 2001 By James Falcone and

More information

The Idiots Guide to GIS and Remote Sensing

The Idiots Guide to GIS and Remote Sensing The Idiots Guide to GIS and Remote Sensing 1. Picking the right imagery 1 2. Accessing imagery 1 3. Processing steps 1 a. Geocorrection 2 b. Processing Landsat images layerstacking 4 4. Landcover classification

More information

SPECIAL PERTURBATIONS UNCORRELATED TRACK PROCESSING

SPECIAL PERTURBATIONS UNCORRELATED TRACK PROCESSING AAS 07-228 SPECIAL PERTURBATIONS UNCORRELATED TRACK PROCESSING INTRODUCTION James G. Miller * Two historical uncorrelated track (UCT) processing approaches have been employed using general perturbations

More information

Noise estimation in remote sensing imagery using data masking

Noise estimation in remote sensing imagery using data masking INT. J. REMOTE SENSING, 2003, VOL. 24, NO. 4, 689 702 Noise estimation in remote sensing imagery using data masking B. R. CORNER, R. M. NARAYANAN* and S. E. REICHENBACH Department of Electrical Engineering,

More information

SEMI-AUTOMATED CLOUD/SHADOW REMOVAL AND LAND COVER CHANGE DETECTION USING SATELLITE IMAGERY

SEMI-AUTOMATED CLOUD/SHADOW REMOVAL AND LAND COVER CHANGE DETECTION USING SATELLITE IMAGERY SEMI-AUTOMATED CLOUD/SHADOW REMOVAL AND LAND COVER CHANGE DETECTION USING SATELLITE IMAGERY A. K. Sah a, *, B. P. Sah a, K. Honji a, N. Kubo a, S. Senthil a a PASCO Corporation, 1-1-2 Higashiyama, Meguro-ku,

More information

Remote Sensing for Geographical Analysis

Remote Sensing for Geographical Analysis Remote Sensing for Geographical Analysis Geography 651, Fall 2008 Department of Geography Texas A&M University (3 credit hours) Instructor: Dr. Hongxing Liu Office hours: Tue & Thur 10:00AM-12:00AM, O&M

More information

KEYWORDS: image classification, multispectral data, panchromatic data, data accuracy, remote sensing, archival data

KEYWORDS: image classification, multispectral data, panchromatic data, data accuracy, remote sensing, archival data Improving the Accuracy of Historic Satellite Image Classification by Combining Low-Resolution Multispectral Data with High-Resolution Panchromatic Data Daniel J. Getman 1, Jonathan M. Harbor 2, Chris J.

More information

Closest Spectral Fit for Removing Clouds and Cloud Shadows

Closest Spectral Fit for Removing Clouds and Cloud Shadows Closest Spectral Fit for Removing Clouds and Cloud Shadows Qingmin Meng, Bruce E. Borders, Chris J. Cieszewski, and Marguerite Madden Abstract Completely cloud-free remotely sensed images are preferred,

More information

Monitoring and Evaluating Land Cover Change in The Duhok City, Kurdistan Region-Iraq, by Using Remote Sensing and GIS

Monitoring and Evaluating Land Cover Change in The Duhok City, Kurdistan Region-Iraq, by Using Remote Sensing and GIS International Journal of Engineering Inventions ISSN: 2278-7461, ISBN: 2319-6491 Volume 1, Issue 11 (December2012) PP: 28-33 Monitoring and Evaluating Land Cover Change in The Duhok City, Kurdistan Region-Iraq,

More information

Received in revised form 24 March 2004; accepted 30 March 2004

Received in revised form 24 March 2004; accepted 30 March 2004 Remote Sensing of Environment 91 (2004) 237 242 www.elsevier.com/locate/rse Cloud detection in Landsat imagery of ice sheets using shadow matching technique and automatic normalized difference snow index

More information

Forest Service Southern Region Jess Clark & Kevin Megown USFS Remote Sensing Applications Center (RSAC)

Forest Service Southern Region Jess Clark & Kevin Megown USFS Remote Sensing Applications Center (RSAC) Hurricane Katrina Damage Assessment on Lands Managed by the Desoto National Forest using Multi-Temporal Landsat TM Imagery and High Resolution Aerial Photography Renee Jacokes-Mancini Forest Service Southern

More information

COLOR-BASED PRINTED CIRCUIT BOARD SOLDER SEGMENTATION

COLOR-BASED PRINTED CIRCUIT BOARD SOLDER SEGMENTATION COLOR-BASED PRINTED CIRCUIT BOARD SOLDER SEGMENTATION Tz-Sheng Peng ( 彭 志 昇 ), Chiou-Shann Fuh ( 傅 楸 善 ) Dept. of Computer Science and Information Engineering, National Taiwan University E-mail: r96922118@csie.ntu.edu.tw

More information

Digital Classification and Mapping of Urban Tree Cover: City of Minneapolis

Digital Classification and Mapping of Urban Tree Cover: City of Minneapolis Digital Classification and Mapping of Urban Tree Cover: City of Minneapolis FINAL REPORT April 12, 2011 Marvin Bauer, Donald Kilberg, Molly Martin and Zecharya Tagar Remote Sensing and Geospatial Analysis

More information

San Francisco Bay Margin Conservation Decision Support System (DSS)

San Francisco Bay Margin Conservation Decision Support System (DSS) San Francisco Bay Margin Conservation Decision Support System (DSS) Presented by Brian Fulfrost1, MS David Thomson2, MS 1 Brian Fulfrost and Associates 2 San Francisco Bay Bird Observatory Transitional

More information

Introduction to GIS (Basics, Data, Analysis) & Case Studies. 13 th May 2004. Content. What is GIS?

Introduction to GIS (Basics, Data, Analysis) & Case Studies. 13 th May 2004. Content. What is GIS? Introduction to GIS (Basics, Data, Analysis) & Case Studies 13 th May 2004 Content Introduction to GIS Data concepts Data input Analysis Applications selected examples What is GIS? Geographic Information

More information

MASTERS OF PHILOSOPHY (M. PHIL.) GEOGRAPHY DETAILED SYLLABUS SESSION 2013-14

MASTERS OF PHILOSOPHY (M. PHIL.) GEOGRAPHY DETAILED SYLLABUS SESSION 2013-14 MASTERS OF PHILOSOPHY (M. PHIL.) GEOGRAPHY DETAILED SYLLABUS SESSION 2013-14 UNIT - I PAPER I RESEARCH METHODOLOGY THEORY AND TECHNIQUES Research: Definition, Importance and Meaning of research, Characteristics

More information

CLOUD FREE MOSAIC IMAGES

CLOUD FREE MOSAIC IMAGES CLOUD FREE MOSAIC IMAGES T. Hosomura, P.K.M.M. Pallewatta Division of Computer Science Asian Institute of Technology GPO Box 2754, Bangkok 10501, Thailand ABSTRACT Certain areas of the earth's surface

More information

The use of GIS and remote sensing techniques to classify the Sundarbans Mangrove vegetation

The use of GIS and remote sensing techniques to classify the Sundarbans Mangrove vegetation The use of GIS and remote sensing techniques to classify the Sundarbans Mangrove vegetation M. A. Salam 1, Lindsay 2, G. Ross 2 and C. M. C. Beveridge 2 1 Department of Aquaculture, Bangladesh Agricultural

More information

ASSESSMENT OF FOREST RECOVERY AFTER FIRE USING LANDSAT TM IMAGES AND GIS TECHNIQUES: A CASE STUDY OF MAE WONG NATIONAL PARK, THAILAND

ASSESSMENT OF FOREST RECOVERY AFTER FIRE USING LANDSAT TM IMAGES AND GIS TECHNIQUES: A CASE STUDY OF MAE WONG NATIONAL PARK, THAILAND ASSESSMENT OF FOREST RECOVERY AFTER FIRE USING LANDSAT TM IMAGES AND GIS TECHNIQUES: A CASE STUDY OF MAE WONG NATIONAL PARK, THAILAND Sunee Sriboonpong 1 Yousif Ali Hussin 2 Alfred de Gier 2 1 Forest Resource

More information

Understanding Raster Data

Understanding Raster Data Introduction The following document is intended to provide a basic understanding of raster data. Raster data layers (commonly referred to as grids) are the essential data layers used in all tools developed

More information

Resolutions of Remote Sensing

Resolutions of Remote Sensing Resolutions of Remote Sensing 1. Spatial (what area and how detailed) 2. Spectral (what colors bands) 3. Temporal (time of day/season/year) 4. Radiometric (color depth) Spatial Resolution describes how

More information

Sub-pixel mapping: A comparison of techniques

Sub-pixel mapping: A comparison of techniques Sub-pixel mapping: A comparison of techniques Koen C. Mertens, Lieven P.C. Verbeke & Robert R. De Wulf Laboratory of Forest Management and Spatial Information Techniques, Ghent University, 9000 Gent, Belgium

More information

An Energy-Based Vehicle Tracking System using Principal Component Analysis and Unsupervised ART Network

An Energy-Based Vehicle Tracking System using Principal Component Analysis and Unsupervised ART Network Proceedings of the 8th WSEAS Int. Conf. on ARTIFICIAL INTELLIGENCE, KNOWLEDGE ENGINEERING & DATA BASES (AIKED '9) ISSN: 179-519 435 ISBN: 978-96-474-51-2 An Energy-Based Vehicle Tracking System using Principal

More information

SMEX04 Land Use Classification Data

SMEX04 Land Use Classification Data Notice to Data Users: The documentation for this data set was provided solely by the Principal Investigator(s) and was not further developed, thoroughly reviewed, or edited by NSIDC. Thus, support for

More information

RULE INHERITANCE IN OBJECT-BASED IMAGE CLASSIFICATION FOR URBAN LAND COVER MAPPING INTRODUCTION

RULE INHERITANCE IN OBJECT-BASED IMAGE CLASSIFICATION FOR URBAN LAND COVER MAPPING INTRODUCTION RULE INHERITANCE IN OBJECT-BASED IMAGE CLASSIFICATION FOR URBAN LAND COVER MAPPING Ejaz Hussain, Jie Shan {ehussain, jshan}@ecn.purdue.edu} Geomatics Engineering, School of Civil Engineering, Purdue University

More information

A remote sensing instrument collects information about an object or phenomenon within the

A remote sensing instrument collects information about an object or phenomenon within the Satellite Remote Sensing GE 4150- Natural Hazards Some slides taken from Ann Maclean: Introduction to Digital Image Processing Remote Sensing the art, science, and technology of obtaining reliable information

More information

Comparison of K-means and Backpropagation Data Mining Algorithms

Comparison of K-means and Backpropagation Data Mining Algorithms Comparison of K-means and Backpropagation Data Mining Algorithms Nitu Mathuriya, Dr. Ashish Bansal Abstract Data mining has got more and more mature as a field of basic research in computer science and

More information

Identifying historical and recent land-cover changes in Kansas using post-classification change detection techniques

Identifying historical and recent land-cover changes in Kansas using post-classification change detection techniques TRANSACTIONS OF THE KANSAS ACADEMY OF SCIENCE Vol. 107, no. 3/4 p. 105-118 (2004) Identifying historical and recent land-cover changes in Kansas using post-classification change detection techniques DANA

More information

APPLICATION OF TERRA/ASTER DATA ON AGRICULTURE LAND MAPPING. Genya SAITO*, Naoki ISHITSUKA*, Yoneharu MATANO**, and Masatane KATO***

APPLICATION OF TERRA/ASTER DATA ON AGRICULTURE LAND MAPPING. Genya SAITO*, Naoki ISHITSUKA*, Yoneharu MATANO**, and Masatane KATO*** APPLICATION OF TERRA/ASTER DATA ON AGRICULTURE LAND MAPPING Genya SAITO*, Naoki ISHITSUKA*, Yoneharu MATANO**, and Masatane KATO*** *National Institute for Agro-Environmental Sciences 3-1-3 Kannondai Tsukuba

More information

Using Remote Sensing Imagery to Evaluate Post-Wildfire Damage in Southern California

Using Remote Sensing Imagery to Evaluate Post-Wildfire Damage in Southern California Graham Emde GEOG 3230 Advanced Remote Sensing February 22, 2013 Lab #1 Using Remote Sensing Imagery to Evaluate Post-Wildfire Damage in Southern California Introduction Wildfires are a common disturbance

More information

Adaptive HSI Data Processing for Near-Real-time Analysis and Spectral Recovery *

Adaptive HSI Data Processing for Near-Real-time Analysis and Spectral Recovery * Adaptive HSI Data Processing for Near-Real-time Analysis and Spectral Recovery * Su May Hsu, 1 Hsiao-hua Burke and Michael Griffin MIT Lincoln Laboratory, Lexington, Massachusetts 1. INTRODUCTION Hyperspectral

More information

Preface. Ko Ko Lwin Division of Spatial Information Science University of Tsukuba 2008

Preface. Ko Ko Lwin Division of Spatial Information Science University of Tsukuba 2008 1 Preface Remote Sensing data is one of the primary data sources in GIS analysis. The objective of this material is to provide fundamentals of Remote Sensing technology and its applications in Geographical

More information

Advanced Image Management using the Mosaic Dataset

Advanced Image Management using the Mosaic Dataset Esri International User Conference San Diego, California Technical Workshops July 25, 2012 Advanced Image Management using the Mosaic Dataset Vinay Viswambharan, Mike Muller Agenda ArcGIS Image Management

More information

A PRELIMINARY STUDY OF WEB-BASED SPATIAL DATA ANALYSIS FEASIBILITY - ONE OF POSSIBLE SOLUTIONS FOR DISASTER RESPONSE AND MANAGEMENT

A PRELIMINARY STUDY OF WEB-BASED SPATIAL DATA ANALYSIS FEASIBILITY - ONE OF POSSIBLE SOLUTIONS FOR DISASTER RESPONSE AND MANAGEMENT A PRELIMINARY STUDY OF WEB-BASED SPATIAL DATA ANALYSIS FEASIBILITY - ONE OF POSSIBLE SOLUTIONS FOR DISASTER RESPONSE AND MANAGEMENT Chang Cheak Lim a, *and Kuo-Chen Chang b a Department of Geography, National

More information

INVESTIGATION OF EFFECTS OF SPATIAL RESOLUTION ON IMAGE CLASSIFICATION

INVESTIGATION OF EFFECTS OF SPATIAL RESOLUTION ON IMAGE CLASSIFICATION Ozean Journal of Applied Sciences 5(2), 2012 ISSN 1943-2429 2012 Ozean Publication INVESTIGATION OF EFFECTS OF SPATIAL RESOLUTION ON IMAGE CLASSIFICATION FATIH KARA Fatih University, Department of Geography,

More information

Michigan Tech Research Institute Wetland Mitigation Site Suitability Tool

Michigan Tech Research Institute Wetland Mitigation Site Suitability Tool Michigan Tech Research Institute Wetland Mitigation Site Suitability Tool Michigan Tech Research Institute s (MTRI) Wetland Mitigation Site Suitability Tool (WMSST) integrates data layers for eight biophysical

More information

Scientists typically attempt to determine

Scientists typically attempt to determine Can Error Explain Map Differences Over Time? Robert Gilmore Pontius Jr and Christopher D Lippitt ABSTRACT: This paper presents methods to test whether map error can explain the observed differences between

More information

Selecting the appropriate band combination for an RGB image using Landsat imagery

Selecting the appropriate band combination for an RGB image using Landsat imagery Selecting the appropriate band combination for an RGB image using Landsat imagery Ned Horning Version: 1.0 Creation Date: 2004-01-01 Revision Date: 2004-01-01 License: This document is licensed under a

More information

Development of Method for LST (Land Surface Temperature) Detection Using Big Data of Landsat TM Images and AWS

Development of Method for LST (Land Surface Temperature) Detection Using Big Data of Landsat TM Images and AWS Development of Method for LST (Land Surface Temperature) Detection Using Big Data of Landsat TM Images and AWS Myung-Hee Jo¹, Sung Jae Kim², Jin-Ho Lee 3 ¹ Department of Aeronautical Satellite System Engineering,

More information

PROBLEMS IN THE FUSION OF COMMERCIAL HIGH-RESOLUTION SATELLITE AS WELL AS LANDSAT 7 IMAGES AND INITIAL SOLUTIONS

PROBLEMS IN THE FUSION OF COMMERCIAL HIGH-RESOLUTION SATELLITE AS WELL AS LANDSAT 7 IMAGES AND INITIAL SOLUTIONS ISPRS SIPT IGU UCI CIG ACSG Table of contents Table des matières Authors index Index des auteurs Search Recherches Exit Sortir PROBLEMS IN THE FUSION OF COMMERCIAL HIGH-RESOLUTION SATELLITE AS WELL AS

More information