Скачать презентацию Geospatial Data Mining at University of Texas at Скачать презентацию Geospatial Data Mining at University of Texas at

2c4e250f086f7e34dcd36406a3133e04.ppt

  • Количество слайдов: 24

Geospatial Data Mining at University of Texas at Dallas Dr. Bhavani Thuraisingham (Computer Science) Geospatial Data Mining at University of Texas at Dallas Dr. Bhavani Thuraisingham (Computer Science) Dr. Latifur Khan (Computer Science) Dr. Fang Qiu (GIS) Students Shaofei Chen (GIS) Mohammad Farhan (CS) Shantnu Jain (GIS), Lei Wang (CS) Post Doc: Dr. Chuanjun Li This Research is Partly Funded by Raytheon

Outline l Case Study - ASTER Dataset - Technical Challenges - Sketches l Process Outline l Case Study - ASTER Dataset - Technical Challenges - Sketches l Process of Our Approach - Pixel classification using SVM Classifiers - Ontology Driven Mining l Pixel Merging l Output l Related Work l Future Work

Case Study: Dataset l ASTER (Advanced Spaceborne Thermal Emission and Reflection Radiometer) To obtain Case Study: Dataset l ASTER (Advanced Spaceborne Thermal Emission and Reflection Radiometer) To obtain detailed maps of land surface temperature, reflectivity and elevation. l ASTER obtains high-resolution (15 to 90 square meters per pixel) images of the Earth in 14 different wavelengths of the electromagnetic spectrum, ranging from visible to thermal infrared light. l ASTER data is used to create detailed maps of land surface temperature, emissivity, reflectivity, and elevation. -

Case Study: Dataset & Features l Remote sensing data used in this study is Case Study: Dataset & Features l Remote sensing data used in this study is ASTER image acquired on 31 December 2005. Covers northern part of Dallas with Dallas-Fort Worth International Airport located in southwest of the image. l ASTER data has 14 channels from visible through thermal infrared regions of the electromagnetic spectrum, providing detailed information on surface temperature, emissive, reflectance, and elevation. l ASTER is comprised of the following three radiometers : Visible and Near Infrared Radiometer (VNIR --band 1 through band 3) has a wavelength range from 0. 56~0. 86μm. - -

Case Study: Dataset & Features l Short Wavelength Infrared Radiometer (SWIR-- band 4 through Case Study: Dataset & Features l Short Wavelength Infrared Radiometer (SWIR-- band 4 through band 9) has a wavelength range from 1. 60~2. 43μm. Mid-infrared regions. Used to extract surface features. l Thermal Infrared Radiometer (TIR --band 10 through band 14) covers from 8. 125~11. 65μm. Important when research focuses on heat such as identifying mineral resources and observing atmospheric condition by taking advantage of their thermal infrared characteristics. -

ASTER Dataset: Technical Challenges l Testing will be done based on pixels l Goal: ASTER Dataset: Technical Challenges l Testing will be done based on pixels l Goal: Region-based classification and identify high level concepts l Solution Grouping adjacent pixels that belong to same class Identify high level concepts using ontology-based mining -

Sketches: Process of Our Approach Training Data ASTER Image Feature Extraction Features (14/pixel) Test Sketches: Process of Our Approach Training Data ASTER Image Feature Extraction Features (14/pixel) Test Data Feature Extraction Features (14/pixel) Validation Features (14/pixel) Classification All Pixel Data Feature Extraction Classifier Training High Level Concepts SVM Classifiers Pixel Grouping

Process of Our Approach Testing Image Pixels Training Image Pixels SVM Classifier Classified Pixels Process of Our Approach Testing Image Pixels Training Image Pixels SVM Classifier Classified Pixels Pixel Merging Concepts and Classes Ontology Driven Mining High Level Concepts

SVM Classifiers: Atomic Concepts Classes Train set Test set Water 1175 1898 Barren Lands SVM Classifiers: Atomic Concepts Classes Train set Test set Water 1175 1898 Barren Lands 1005 1617 Grass 952 1331 Trees 887 1479 Buildings 1041 768 Road 435 648 House 1584 1364 # of instances 7079 9105 Different Class Distribution of Training and Test Sets

Process of Our Approach Testing Image Pixels Training Image Pixels SVM Classifier Classified Pixels Process of Our Approach Testing Image Pixels Training Image Pixels SVM Classifier Classified Pixels Pixel Merging Concepts and Classes Ontology Driven Mining High Level Concepts

Ontology-Driven Mining - Ontology will be represented as a directed acyclic graph (DAG). Each Ontology-Driven Mining - Ontology will be represented as a directed acyclic graph (DAG). Each node in DAG represents a concept Interrelationships are represented by labeled arcs/links. Various kinds of interrelationships are used to create an ontology such as specialization (Is-a), instantiation (Instance-of), and component membership (Part-of). IS-A Urban Residential Part-of Apartment Single Family Home Multi-family Home

Ontology-Driven Mining l We will develop domain-dependent ontologies - Provide for specification of fine Ontology-Driven Mining l We will develop domain-dependent ontologies - Provide for specification of fine grained concepts - Concept, “Residential Area” can be further categorized into concepts, “House”, “Grass” and “Tree” etc. l Generic ontologies provide concepts in coarser grain

Ontology Driven Mining Target Area Urban Area Building Road Residential Area Tree House Grass Ontology Driven Mining Target Area Urban Area Building Road Residential Area Tree House Grass Open Area Water Barren Land

Challenges l Region growing - Find out regions of the same class - Find Challenges l Region growing - Find out regions of the same class - Find out neighboring regions - Merge neighboring regions - Not scalable l Irregular regions l Of different sizes l Hard to track boundaries or neighboring regions l Pixel merging - Only neighboring pixels considered - Pixels are converted into Concepts - Linear

Pixels Merging Pixels Merging

Pixels Merging Pixels Merging

Complexity l There are two iterations: - First iteration converts signature classes into Concepts Complexity l There are two iterations: - First iteration converts signature classes into Concepts - Second iteration converts remaining classes and isolated concepts into Dominating classes l Each pixels take O(1) time l Target area takes O(n) time, where n is the number of pixels in the target area l Example (next slide): Signature classes: c 1, c 2, c 3 Non-signature class: c 4 Concepts: C 1, C 2, C 3 -

Pixels Merging c 1 c 2 c 2 C 2 c 1 c 2 Pixels Merging c 1 c 2 c 2 C 2 c 1 c 2 c 2 c 1 c 3 c 2 C 2 c 3 c 2 c 2 c 3 c 3 c 2 c 3 c 3 c 4 c 3 c 3 c 3 c 4 c 4 c 3 (a) (b) (c) C 2 c 1 c 2 c 2 C 2 c 3 c 2 c 2 C 2 c 3 c 2 c 3 C 3 c 3 c 2 c 3 c 3 c 4 c 3 c 3 C 3 c 4 c 3 c 3 c 4 c 4 c 3 (d) (e) (f)

Implementation l Software: - Arc. GIS 9. 1 software. - For programming, we use Implementation l Software: - Arc. GIS 9. 1 software. - For programming, we use Visual Basic 6. 0 embedded in the software.

Output: Output:

Output Output

Output Output

Related Work l Classification (SVM) l Farid Melgani, Lorenzo Bruzzone, Classification of hyperspectral remote-sensing Related Work l Classification (SVM) l Farid Melgani, Lorenzo Bruzzone, Classification of hyperspectral remote-sensing images with support vector machines. l Zhu, G. and D. G. Blumberg. (2002). Classification using ASTER data and SVM algorithms - The case study of Beer Sheva, Israel. l Huang C. ; Davis L. S. ; Townshend J. R. G. (2002) An assessment of support vector machines for land cover classification.

Future Work l Develop Full Fledged Prototype (By January 31, 2007) l Generate Rules Future Work l Develop Full Fledged Prototype (By January 31, 2007) l Generate Rules automatically (By June 30, 2007) - Ripper–Semi-automatically - Association mining