Window based software for Neuro-Fuzzy Classification of Remotely Sensed Image (Stand along application and extension for ArcGIS) Xiaogang Yang POEC 6387.

Slides:



Advertisements
Similar presentations
Geo GIS Practicuum Introduction to ArcGIS 8 Exercise 5 - ESRI Virtual Campus Chapters 1-2, ArcGIS Methods …
Advertisements

Spotlight on Presentations
Water Rights Accounting. New Accounting Model New Technology: 1979 versus 2011 – Faster processors – Faster graphics – Larger, faster, memory – Larger,
Page 1 of 50 Optimization of Artificial Neural Networks in Remote Sensing Data Analysis Tiegeng Ren Dept. of Natural Resource Science in URI (401)
Creating Accessible Word Documents by Debbie Lyn Jones, IT Manager I, NSU Webmaster FRIDAY, JANUARY 23, 2015.
Urbanization and Land Cover Change in Dakota County, Minnesota Kylee Berger and Julia Vang FR 3262 Remote Sensing Section 001/002.
Danish Meteorological Institute, Ice Charting and Remote Sensing Division “SIKU” Sea Ice Mapping System The DMI Approach Henrik Steen Andersen Danish Meteorological.
ANALYSIS 3 - RASTER What kinds of analysis can we do with GIS? 1.Measurements 2.Layer statistics 3.Queries 4.Buffering (vector); Proximity (raster) 5.Filtering.
Intro to ArcMap Customization with Visual Basic  Create your own toolbars, buttons, interactive tools, and programs  Runs behind the scenes in ArcMap.
SuperPad 3 Full-Function Mobile GIS Software. Overview  SuperPad, full-function mobile GIS software, is designed for field survey and data collection.
Lecture 6 Graphics, Number Systems. 7.2 Bit-map Graphics Similar to real painting on the canvas, there is no way to change something but paint over it.
Evaluation of MineSet 3.0 By Rajesh Rathinasabapathi S Peer Mohamed Raja Guided By Dr. Li Yang.
Visual C++.NET Hong Li. Introduction to.NET Microsoft announced in June 2000 Microsoft announced in June 2000 A new software –development model that allows.
Unsupervised Classification of Higgins Beach and Vicinity Remote Sensing (GEO 205) Author: Stanley Max Final Project Using ERDAS Imagine 8.7 to Conduct.
ESRM 250 & CFR 520: Introduction to GIS © Phil Hurvitz, KEEP THIS TEXT BOX this slide includes some ESRI fonts. when you save this presentation,
Introduction to ArcGIS Add-Ins Exercises GIS/LIS Conference, 2014 Rochester, MN.
A Billiards Point of Sale Application Christopher Ulmer CS 470 Final Presentation.
Lesson 4 Computer Software
ArcGIS Overview Lecture 1: Software Layer characteristics Thematic maps.
Artificial Neural Network Applications on Remotely Sensed Imagery Kaushik Das, Qin Ding, William Perrizo North Dakota State University
1 Integrated Development Environment Building Your First Project (A Step-By-Step Approach)
Lesson 24: Adding Graphics, Animation, and Sound.
Introduction to ArcGIS. Goals Become familiar with ArcGIS ▫Locating and running the program ▫Introduction to the 3 ArcGIS interfaces ▫Experience with.
Using a Template to Create a Resume and Sharing a Finished Document
Welcome to DEP’s GIS Workshop Series Workshop 3 Introduction to ArcGIS Desktop 1.
Internet and Distributed Representation of Agent Based Model by- Manish Sharma.
Exploring the Synergies between ‘Commercial’ and Open Source Software Gregg Petrie, Cosmic Project Lee Miller, Pacific Northwest National Laboratory.
Introduction to ArcView NPS Introduction to GIS: Lecture 2 Based on NINC, ESRI and Other Sources.
Introduction of Geoprocessing Topic 7a 4/10/2007.
Conclusions and Future Considerations: Parallel processing of raster functions were 3-22 times faster than ArcGIS depending on file size. Also, processing.
Change Detection in the Metro Area Michelle Cummings Laura Cossette.
Introduction to ArcGIS for Environmental Scientists Module 1 – Data Visualization Chapter 3 – Symbology and Labeling.
Click on these! %2Fblank%2Fbrowse.asp%3FA%3D383%26BMDRN%3D2000%26BCOB%3D0% 26C%3D64893.
Copyright © 2009 Pearson Education, Inc. Publishing as Prentice Hall. 1 Skills for Success with Microsoft ® Office 2007 PowerPoint Lecture to Accompany.
Chernobyl Nuclear Power Plant Explosion
Microsoft Visual Basic 2005 BASICS Lesson 1 A First Look at Microsoft Visual Basic.
1 LAITS, George Mason University The Use of GIS to Support Atmospheric and Oceanographic Data Management and Visualization Fan Hong 1,2 Di Liping 1 Zhao.
BOĞAZİÇİ UNIVERSITY DEPARTMENT OF MANAGEMENT INFORMATION SYSTEMS MATLAB AS A DATA MINING ENVIRONMENT.
Project Two Adding Web Pages, Links, and Images Define and set a home page Add pages to a Web site Describe Dreamweaver's image accessibility features.
474/574 Remote sensing Lab: Digitizing Sweet water Wetland Park areas, Tucson AZ by using remote sensing imagery (Aerial and Landsat) and ArcGIS software.
This is how you invoke the Microsoft Visual Studio 2010 Software. All Programs >> Microsoft Visual Studio 2010.
Introduction of Geoprocessing Lecture 9 3/24/2008.
CONVERSION OF CAD DATA TO GIS LAYERS Challenges and Techniques Compiled by: Tope Bello Summer 2005 Instructor POEC 6387 GIS Workshop Professor Ronald Briggs.
Scale is the relationship between the size of features on a map and the size of the corresponding objects in the real world. Scale is commonly expressed.
Adding a Picture in ArcGIS. Getting Started Open ArcMap in ArcGIS Add shape files Find pictures on the web save in folder with shape files you added to.
CHANGE DETECTION ANALYSIS USING REMOTE SENSING TECHNIQUES Change in Urban area from 1992 to 2001 in COIMBATORE, INDIA. FNRM 5262 FINAL PROJECT PRESENTATION.
Image Processing Software Options Which types of software can be used to view and process remotely sensed imagery?
26. Classification Accuracy Assessment
Introduction to Computers
Atlas.ti Training Manual
Development Environment
Lesson 7 Learning Objectives: Insert pictures from files
LAND COVER CLASSIFICATION WITH THE IMPACT TOOL
Computer Software: Programming
An Introduction to Computers and Visual Basic
The University of Texas at Dallas
Introduction to ArcGIS Add-Ins
An Introduction to Computers and Visual Basic
Using PowerPoint to Present Research Results
Writing Geoprocessing Scripts With ArcGIS
Introduction to Computers
6th Lecture – Rectangles and Regions, and intro to Bitmap Images
Digital Image Processing
A TYPE OF COMPOSITION IN PHOTOGRAPHY
An Introduction to Computers and Visual Basic
Hill Country Associates Progress Report
Images into PowerPoint
Calculating land use change in west linn from
Presentation transcript:

Window based software for Neuro-Fuzzy Classification of Remotely Sensed Image (Stand along application and extension for ArcGIS) Xiaogang Yang POEC 6387 GIS Workshop Final presentation Director: Dr. Fang Qiu Dr. Ron Briggs

Contents Background and Objectives Methodology Challenge Issue Progress and Results Case Study Conclusion Future Work

Background and Objectives 1.Project background  Based on the research work of Dr. Fang Qiu: Neuro-Fuzzy Classification of Remotely Sensed Image “Neuro-Fuzzy Classification of Remotely Sensed Image”  Unix and C/C++ language environment.  Erdas Image dependent 2. Objective:  Develop window based software for Neuro-Fuzzy Classification of Remotely Sensed Image  Design Graphic Use Interface.  Erdas Image independent  Design a Extension for ArcGIS.

Methodology First Part: (before mid presentation) Stand along window based Software Coding: Microsoft VC++, recoding from C ->VC++ GUI: MFC Dialogue based Interface. VC6 and VC.NET compatible

Methodology Cont. Second Part: Extension for ArcGIS (ArcMap) VC/VB/ArcObject. Active DLL project: easy to be used by ArcMap. Provide factions: Sampling, Training, Classification, etc.

Challenge Issue 1.Programming skill. –Language: C, C++, VB, ArcObject, –Tools: VC6, MFC, VB6, VBA, DLL, Active Control. 2.Large remote sensed image file: –20MB-200MB. 3.Performance: –Memory issue: –Running speed: C++ for image processing (Training and Classification) VB for Sampling BIP format

Stand along application Easy to use without Any tools Provided the Training Data. Click to start the Demo:

Stand along application Enter Page Screen Shot

Stand along application Cont. Main page Screen Shot

Stand along application Cont. Training Screen Shot

Weight File Standard Deviation File Stand along application Cont. Stand along application Cont. Training Results one

Stand along application Cont. Stand along application Cont. Training Results Two

Stand along application Cont. Stand along application Cont. Aeverage Error per Pattern vs. Training Cycle

Classification Screen Shot Stand along application Cont.

Case Study one Study Area: Jacksonville Beach, FL Data Set: National Aerial Photography Program (NAPP) Digital Orthophotoquad, 1 x 1 m, RGB = NIR, R, G, Size: KB

GIS Extension Click to demo GIS Customization. Function: Sampling, Training, Classification. Etc.

GIS Extension Cont. GIS Extension Cont. (Sampling)

GIS Extension Cont. GIS Extension Cont. (Training)

GIS Extension Cont. GIS Extension Cont. (Classification)

Case Study two Remote Sensed Image for North Texas Data prepare Data Source: TM7 Path 027 Row 037 8/19/2000 Original Geo TIFF Format 9 file. Use Erdas Image: –combined 6 bands TIFF file into one IMG file format –Select sub area –convert IMG to BIP format, Size: 44MB

Case Study two Map for North Dallas

Case Study two Remote Sensed Image for North Dallas (Top: , Left: , Bottom: , Right ) Band1 Band3 Band5

Case Study two Remote Sensed Image for North Dallas Classification Water Bare & Grassland Forest Urban

Case Study two map (Near City of Rowlett)

Case Study two Case Study two Aerial Photo (Near City of Rowlett)

Case Study two Remote sensed image (Near City of Rowlett)

Case Study two Case Study two Image Classification (Near City of Rowlett)

Conclusion The neruo fuzzy network is a very power method for remote sensed image classification This Software provide a tool for image classification. Challenge: How to select sampling pixels? experience?

Future Work Improvement Add more functions to this extension –Analysis? Statistic? Graphic? –Conversion? Create shape point file during sampling. –Easy to visualize the location classification and distribution of sampling points. –Modify the points (location and class) as needed. –Using shape file instead of native txt file during training.

End

Neuro-fuzzy Learning, Classification, Deffuzification Learning Rules: Learning Rules:  w ij = r (x-w ij ) (i is winner)  w ij = -r (x-w ij ) (Otherwise)  ij = r (|w ij -x|-  ij  (i is winner)  ij = 0 (Otherwise) Fuzzy Classification: Fuzzy Classification: F i (I) = (exp((-1/2)  j (w ij -I j ) 2 /  ij 2 )) 1/n Defuzzification: Defuzzification: F w (I) = max (F i (I): i = 1…m)