T11_Clasification_3slides

T11_Clasification_3slides - Geography 333 Remote Sensing I...

Info iconThis preview shows pages 1–6. Sign up to view the full content.

View Full Document Right Arrow Icon
1 Geography 333 Remote Sensing I Topic 11: Image Classification 2 Readings Topic 11: Chapter 9 – Classification & Thematic Information Extraction: Pattern Recognition pg 337-389 Topic 12: GEOBIA GEOBIA reading (Hay and Castilla, 2008) on BB. 3 Outline Overview: Thematic information extraction Classification basics Landcover classification schemes Basic image statistics Univariate Multivariate Supervised classification Unsupervised classification Training site selection Feature selection Graphic methods Statistical methods
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
2 4 Thematic Information Extraction Define the classification problem: Determine the study area boundary Identify classes of interest Acquire the appropriate data: Remote sensing, DEM, ancillary data ‘Ground truth’ information of study area Perform pre-processing tasks: Radiometric correction Geometric correction Data integration 5 Thematic Information Extraction, cont… Perform image processing for thematic information extraction Select classification logic and algorithms Perform image transformation/parameter selection Extract initial training data (if required) Select most appropriate input variables Extract final training data (if required) Extract thematic information Assess classification accuracy 6 Thematic Information Extraction, cont… Report and distribute Image and map lineage report Metadata Distribute digital/analog products
Background image of page 2
3 7 Thematic Information Extraction (details) Fig 9.1 – Jensen – pg 339 8 Classification Basics To arrange image components into classes or categories Transform data into information Pixels to geo-information 9
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
4 10 Classification Basics Pattern recognition Spectral, spatial, temporal Many different classification algorithms Unsupervised, supervised, hybrid Classes can be ‘hard’ or ‘fuzzy’ Hard : each pixel can only belong to one class ; boundaries between classes are distinct Fuzzy : each pixel can be a heterogeneous mix of classes ; boundaries between classes can be gradual 11 Spectral and Information Classes Information classes Categories of interest to the analyst • Agricultural crops, forest cover types, etc Spectral/data classes ‘Natural’ groupings of the data • Groups of pixels that are similar with regards to spectral observations Rarely is there perfect agreement between spectral and information classes *** 12 Classification Schemes The first step in thematic information extraction: define the information classes of interest Should be exhaustive and mutually exclusive • i.e., a 6 sided die (1,2,3,4,5,6) Should be achievable , given the available data and methods All other decisions flow from here Should be a collaborative effort between product generators and users “…If you do not know where you are going, any road wil take you there…” - Sterling Hol oway, (1904 - )
Background image of page 4
5 13 USGS Land Use/Land Cover Classification System A hierarchical classification scheme designed specifically for remote sensing classification GeoEye, IKONOS pan, Quickbird pan, 1:20,000 air photos IV IRS pan, IKONOS ms, Quickbird ms, 1:50,000 air photos III
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 6
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 20

T11_Clasification_3slides - Geography 333 Remote Sensing I...

This preview shows document pages 1 - 6. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online