Remote Sensing Unsupervised Image Classification.

Slides:



Advertisements
Similar presentations
With support from: NSF DUE in partnership with: George McLeod Prepared by: Geospatial Technician Education Through Virginia’s Community Colleges.
Advertisements

Object-oriented classification
Major Operations of Digital Image Processing (DIP) Image Quality Assessment Radiometric Correction Geometric Correction Image Classification Introduction.
Image Indexing and Retrieval using Moment Invariants Imran Ahmad School of Computer Science University of Windsor – Canada.
Thresholding Otsu’s Thresholding Method Threshold Detection Methods Optimal Thresholding Multi-Spectral Thresholding 6.2. Edge-based.
Clustering… in General In vector space, clusters are vectors found within  of a cluster vector, with different techniques for determining the cluster.
An Overview of RS Image Clustering and Classification by Miles Logsdon with thanks to Robin Weeks Frank Westerlund.
Image Classification.
Unsupervised Training and Clustering Alexandros Potamianos Dept of ECE, Tech. Univ. of Crete Fall
Basics: Notation: Sum:. PARAMETERS MEAN: Sample Variance: Standard Deviation: * the statistical average * the central tendency * the spread of the values.
Lecture 14: Classification Thursday 18 February 2010 Reading: Ch – 7.19 Last lecture: Spectral Mixture Analysis.
Image Classification To automatically categorize all pixels in an image into land cover classes or themes.
Pattern Recognition. Introduction. Definitions.. Recognition process. Recognition process relates input signal to the stored concepts about the object.
Classification of Remotely Sensed Data General Classification Concepts Unsupervised Classifications.
Lecture 14: Classification Thursday 19 February Reading: “Estimating Sub-pixel Surface Roughness Using Remotely Sensed Stereoscopic Data” pdf preprint.
Digital Imaging and Remote Sensing Laboratory Real-World Stepwise Spectral Unmixing Daniel Newland Dr. John Schott Digital Imaging and Remote Sensing Laboratory.
Introduction to Digital Data and Imagery
Digital Imaging and Remote Sensing Laboratory Mixed Pixels and Spectral Unmixing 1 Spectral Mixtures areal aggregate intimate Linear mixing models (areal.
Image Classification: Supervised Methods
Image Classification: Redux
Pixel-based image classification
Chapter 12 Spatial Sharpening of Spectral Image Data.
Image Classification
Introduction to Image Processing Grass Sky Tree ? ? Review.
Remote Sensing Hyperspectral Remote Sensing. 1. Hyperspectral Remote Sensing ► Collects image data in many narrow contiguous spectral bands through the.
Image Classification: Introduction Lecture Notes 6 prepared by R. Lathrop 11/99 updated 3/04 Readings: ERDAS Field Guide 6th Ed. CH. 6.
Environmental Remote Sensing Lecture 5: Image Classification " Purpose: – categorising data – data abstraction / simplification – data interpretation –
October 14, 2014Computer Vision Lecture 11: Image Segmentation I 1Contours How should we represent contours? A good contour representation should meet.
Image Classification: Introduction Lecture Notes 7 prepared by R. Lathrop 11/99 updated 3/04 Readings: ERDAS Field Guide 5th Ed. CH. 6:
Land Cover Classification Defining the pieces that make up the puzzle.
1 Remote Sensing and Image Processing: 6 Dr. Mathias (Mat) Disney UCL Geography Office: 301, 3rd Floor, Chandler House Tel:
Summer Session 09 August Tips for the Final Exam Make sure your answers clear, without convoluted language. Read questions carefully – are you answering.
Image Classification 영상분류
Remote Sensing Supervised Image Classification. Supervised Image Classification ► An image classification procedure that requires interaction with the.
EECS 274 Computer Vision Segmentation by Clustering II.
Today Ensemble Methods. Recap of the course. Classifier Fusion
Lecture 3 The Digital Image – Part I - Single Channel Data 12 September
Map of the Great Divide Basin, Wyoming, created using a neural network and used to find likely fossil beds See:
14 ARM Science Team Meeting, Albuquerque, NM, March 21-26, 2004 Canada Centre for Remote Sensing - Centre canadien de télédétection Geomatics Canada Natural.
Levels of Image Data Representation 4.2. Traditional Image Data Structures 4.3. Hierarchical Data Structures Chapter 4 – Data structures for.
Supervised Classification in Imagine D. Meyer E. Wood
Remote Sensing Theory & Background III GEOG370 Instructor: Yang Shao.
CZ5211 Topics in Computational Biology Lecture 4: Clustering Analysis for Microarray Data II Prof. Chen Yu Zong Tel:
Classification Categorization is the process in which ideas and objects are recognized, differentiated and understood. Categorization implies that objects.
Unsupervised Classification
Image Enhancement Band Ratio Linear Contrast Enhancement
Fuzzy Logic in Pattern Recognition
Supervised Training and Classification
Urban growth pattern of the San Antonio area
Object-based Classification
Lecture 21: GIS Analytical Functionality (V)
LAND COVER CLASSIFICATION WITH THE IMPACT TOOL
IMAGE PROCESSING RECOGNITION AND CLASSIFICATION
Digital Data Format and Storage
Unsupervised Classification in Imagine
Classification of Remotely Sensed Data
Class 10 Unsupervised Classification
Map of the Great Divide Basin, Wyoming, created using a neural network and used to find likely fossil beds See:
University College London (UCL), UK
Supervised Classification
pub/ hurtado/5336
Unsupervised Classification
Image Information Extraction
Chap.8 Image Analysis 숙명여자대학교 컴퓨터과학과 최 영 우 2005년 2학기.
University College London (UCL), UK
ALI assignment – see amended instructions
Environmental Remote Sensing GEOG 2021
EM Algorithm and its Applications
Class 10 Unsupervised Classification
Presentation transcript:

Remote Sensing Unsupervised Image Classification

1. Unsupervised Image Classification ► The process requires a minimal amount of initial input from the analyst ► A numeric operation searches for natural grouping of the spectral properties of pixels ► The analyst determines the information class for each spectral class after the spectral classes are formed

1. Unsupervised Classification ► Chain method ► ISODATA ► Spectral mixture analysis ► Object-based image analysis

2. Chain Method ► Pass 1 builds clusters and calculates their mean vectors ► Pass 2 assigns pixels to clusters based on the minimum-distance rule

Pass 1. Cluster Building ► R, a spectral radius used to determine whether a new cluster should be formed (e.g., 15 brightness) ► N, the number of pixels to be evaluated between each major merging of the clusters (e.g., 2000)

Pass 1. Cluster Building ► C, a spectral distance used to determine merging clusters when N is reached (e.g., 30 brightness) ► Cmax, the maximum number of spectral clusters (categories) (e.g., 20) to be identified

Pass 1 ► The operation evaluates pixels sequentially, combining successive pixels into a cluster if their spectral distance < R ► A cluster is complete when N is reached ► If the spectral distance between two clusters is < C, the two clusters are merged, until no clusters with distance < C ► The new mean is the weighted average of the two original clusters

Pass 2. Assigning Pixels ► Assigns pixels based on the minimum distance classifier ► Manual modification based on knowledge of the area, co- spectral plots, and interactive display

3. ISODATA Method ► Iterative Self Organizing Data Analysis Technique

ISODATA Parameters required: ► Cmax, the maximum number of spectral clusters ► T, maximum % of pixels whose classes are allowed to be unchanged between iterations ► M, the max number of times of classifying pixels and calculating cluster mean vectors

ISODATA ► Minimum members in a cluster (%). For example, if the % <0.01, the cluster is deleted ► Maximum Std Dev, when a std dev > specified Max-std-dev and the number of members > 2*Min members, the cluster is split

ISODATA ► Split separation: when the value is changed from 0.0, it replaces Std Dev to determine the locations of the new mean vectors plus and minus this split separation value ► Minimum distance between cluster means. Clusters with a weighted distance < this value (e.g., 3.0) are merged

ISODATA ► It uses a large number of passes ► The initial means are determined based on the mean and std dev of each band

► dv0 dv0 dv0

Iterations ► Assigns each pixel using the minimum distance classifier ► The second to M th iteration re-calculate the mean vectors examine Min members(%) Max std dev Max std dev split separation split separation Min distance between clusters Min distance between clusters ► The iteration stops when T or M is reached

Readings ► Jensen nd Edition or rd Edition, Introductory Digital Image Processing. Prentice Hall.

4. Classification of Mixed Pixels ► Mixed pixels - when a sensor’s IFOV covers more than one land cover feature e.g. tree leaves, grass, and bare soil ► Depends on the spatial resolution of sensors and the scale of features ► Sub-pixel classification - spectral mixture analysis - spectral mixture analysis

Spectral Mixture Analysis ► Mixed spectral signatures are compared to pure reference spectra ► The pure signature is measured in the lab, field, or from images ► Assuming that the variation in an image is a mixture of a limited number of features ► Estimates approx proportion of each pure feature in a pixel

Spectral Mixture Analysis.. ► Linear mixture models - assuming a linear mixture of pure features ► Endmembers - the pure reference signatures ► Weight - the proportion of the area occupied by an endmember ► Output - fraction image for each endmember showing the fraction occupied by an endmember in a pixel

Spectral Mixture Analysis.. Gap, water, Mangrove, forest Kemal G o kkaya 2008

Tole L., Changes in the built vs. non-built environment in a rapidly urbanizing region: A case study of the Greater Toronto Area, Computers, Environment and Urban Systems, 32(5):

Spectral Mixture Analysis.. ► Two basic conditions ► I. The sum of fractions of all endmembers in a pixel must equal 1  F i = F 1 + F 2 + … + F n = 1 ► II. The DN of a pixel is the sum of the DNs of endmembers weighted by their area fractions D  = F 1 D  1 + F 2 D  2 + … + F n D  n +E D  = F 1 D  1 + F 2 D  2 + … + F n D  n +E

Spectral Mixture Analysis.. ► One D   equation for each band, plus one  F i equation for all bands ► Number of endmembers = number of bands + 1 One exact solution without the E term One exact solution without the E term ► Number of endmembers < number of bands +1 Fs and E can be estimated statistically Fs and E can be estimated statistically ► Number of endmembers > number of bands +1 No unique solution No unique solution

Spectral Mixture Analysis.. ► Advantages/characteristics - a realistic representation of features - a deterministic, not a statistic, method - fuzzy set theory vs. fuzzy classification ► Disadvantages - does not account for multiple reflections - does not account for multiple reflections

5. Object-based Classification ► Also called object-based image analysis (OBIA) ► vs. per pixel classification All classifiers so far consider the spectral info of a single pixel regardless of its neighbors All classifiers so far consider the spectral info of a single pixel regardless of its neighbors

Kutztown GEOEYE-1 Sean Ahearn, Hunter college

5. Object-based Classification.. ► A two-step process I. segmentation of the image into objects I. segmentation of the image into objects II. Classiication of the objects II. Classiication of the objects Works at multiple scales and uses color, shape, size, texture, pattern, and context information to group pixels into objects

5. Object-based Classification.. ► Two sets of characteristics can be used to classify the objects The characteristics of the object itself (spectral, texture, shape, etc.) The relationship between objects (connectivity, proximity, etc.)

5. Object-based Classification.. ► Advantages ► Disadvantages ► E-cognition, Definiens and Trimble

Readings ► Chapter 7