image classification taxonomy

Guillermo VILLAIGN Spain

From Classifications, Legends and Nomenclatures to Parametric Object Oriented Databases: a paradigm shift in Geographic

Information

CEN TC 287 Mediterranean Workshop. Athens, 14 March 2008

2 2CEN TC 287 Mediterranean Workshop. Athens, 14 March 2008

Warning: This presentation is intentionallyprovocative and “politically incorrect”

We apologize for the annoyances it may cause


paradigm= unquestioned* ‘true’ in a scientific or technical domain

(*) in a certain historical time


Outline

1. Introduction2. Example: Database of people3. Example: Land Cover classifications4. New solution: Parametric Object Oriented

databases. Application to the Land Cover case

5. Classifications, legends and nomenclatures “hidden” in other G.I. themes

6. Conclusions


Everybody agrees on the importance ofgeographical information (G.I.) but…


Why is geographical information so difficult to achieve correctly ?


Our world is infinitely complex, and it is made by multiple interaction of myriads of phenomenon that go from de atomic scale to geographical scale

It is constantly changing (plant fenology, agricultural cycles, climatology, human action…)

G.I. Information uses concepts and terms:With “fuzzy” definitions and significancesFrom science and technique as well as everyday useChanging from one place to another of the world (same term for different thing and different terms for same thing)

Because …


G.I. needs to “mix” concepts and terms from many different thematic fields:

Geology, Geomorphology, EdaphologyHidrography, HydrologyBotanics, AgricultureForestry, Ecology, ChemistryUrban PlanningEconomic ActivityInfrastructuresArchitectureClimatologyEtc….

Because …


• Historically, the information has been stored in paper maps

• So it was useless to retrieve information impossible to be stored in a paper map

Historical evolution of geographicinformation storing technologies

PaperMaps

PaperMaps GIS

Databases

GIS Databases

Digital Maps

(CAD)

Digital Maps

(CAD)

TIME LINE


• The problem is that information you can store in a paper map is a very small part of information you could retrieve or need about reality

• Paper maps are a good way to show information, but a very bad way to store it

Amount of information in a paper map

NeededInformation

NeededInformation

Paper MapInfo.

Paper MapInfo.

Reality


• The first information that was introduced in digital databases was the info already present in paper maps

Databases designed to contain onlyinformation already present in paper maps

Paper MapInfo.

Paper MapInfo.

The first digital databases were designed to store only the information that was already in the maps

NeededInformation

NeededInformation

Reality

old G.I.databases

Map-centric data model


• Databases that would be able to store all the information needed are completely different (and more complex) compared with old G.I. databases

Databases able to store all theinformation needed about reality

Paper MapInfo.

Paper MapInfo.

Neededdatabase

old G.I.database

NeededInformation

NeededInformation


That most of present GI databases are obsolete, because they were designed only to store information in paper maps

That many of new data models being built today are also obsolete, because they are “contaminated” (“poluted”) by “map centric” “out of date” way of thinking. (E.g: the use of classifications, legendsor nomenclatures)

That it is imperative to change all this data models and databases if we want GI to achieve the goals that we expect in the 21st century

In this presentation we will try to show:


Outline



5. Classifications, legends and nomenclatures “hidden” in other G.I. themes

6. Conclusions


Suppose we need to build a database of “people”


Characteristics considered

- fat- medium weigh- thin

- tall- medium height- small

- man- woman

Possible values

3weight

3height

2gender

Number of values

Characteristic


Characteristics considered

- fat- medium weigh- thin

- tall- medium height- small

- man- woman

Possible values

3weight

3height

2gender

Number of values

Characteristic

Classification Number of classes = 2 x 3 x 3 = 18


“Hierarchical classification” of people

2 x 3 x 3 = 18 classes

1. Men1.1. Tall men

1.1.1. Tall and fat men1.1.2. Tall and medium-weight men1.1.3. Tall and thin men

1.2. Medium height men1.2.1. Medium height and fat men1.2.2. Medium height and medium-weight men1.2.3. Medium height and thin men

1.3. Small men1.3.1. Small and fat men1.3.2. Small and medium-weight men1.3.3. Small and thin men

2. Women2.1.Tall women

2.1.1. Tall and fat women2.1.2. Tall and medium-weight women2.1.3. Tall and thin women

2.2. Medium height women2.2.1. Medium height and fat women2.2.2. Medium height and medium-weight women2.2.3. Medium height and thin women

2.3. Small women2.3.1. Small and fat women2.3.2. Small and medium-weight women2.3.3. Small and thin women


But there are many other possible characteristics to be considered:

- nationality- age- study level- work- residence- eyes color- hair color- diseases- marital status- number of sons- hobbies- religion- etc, etc, etc…..


What would be the number of classes needed to store all this information ?

250 * 100 * 4 * 100 * 250 * 5 * 4 * 20 * 4 * 10 * 20 * 10 =


250 * 100 * 4 * 100 * 250 * 5 * 4 * 20 * 4 * 10 * 20 * 10 =

= 8,000,000,000,000,000

= 8 * 1015 classes !!


• Would these classes be useful in practice?• Would it be possible to implement them in an

information system?

⇒ not at all !!


This is called by computer engineersthe ‘class explosion’ problem


So… this is clearly not the way to go…


Outline



5. Classifications, legends and nomenclatures “hidden” in other GI themes

6. Conclusions

26 26December 2007 INSPIRE D2.6 workshop Ispra

3.1. The actual ‘paradigm’*:Land Cover Classifications

(*) paradigm= unquestioned ‘true’ in a certain technical domain


‘Hierarchical classification’ of people

2 x 3 x 3 = 18 classes

1. Men1.1. Tall men

1.1.1. Tall and fat men1.1.2. Tall and medium-weight men1.1.3. Tall and thin men

1.2. Medium height men1.2.1. Medium height and fat men1.2.2. Medium height and medium-weight men1.2.3. Medium height and thin men

1.3. Small men1.3.1. Small and fat men1.3.2. Small and medium-weight men1.3.3. Small and thin men

2. Women2.1.Tall women

2.1.1. Tall and fat women2.1.2. Tall and medium-weight women2.1.3. Tall and thin women

2.2. Medium height women2.2.1. Medium height and fat women2.2.2. Medium height and medium-weight women2.2.3. Medium height and thin women

2.3. Small women2.3.1. Small and fat women2.3.2. Small and medium-weight women2.3.3. Small and thin women


LEVEL 1 LEVEL 2 LEVEL 3 LEVEL 41.1.1.1 Residential continuous dense urban fabric.Residential structures cover more than 80% of the total surface. More than 50% of the buildings have three or more stories.1.1.1.2 Residential continuous medium dense urban fabric.Residential structures cover more than 80% of the total surface. Less than 50% of the buildings have three or more stories.1.1.1.3 Informal settlements1.1.2.1 Residential discontinuous dense urban fabric.Buildings, roads and artificially surface areas cover between 50% and 80% of the total surface area of the unit.1.1.2.2 Residential discontinuous sparse urban fabric.Buildings, roads and artificially surface areas cover between 10% and 50% of the total surface area of the unit. The vegetated areas are predominant by but is not land dedicated to forestry or agriculture.

1.1.2.3 Residential urban blocks1.1.2.4 Informal discontinuous residential structures

1.1. Urban fabric: 1. ARTIFICIAL AREAS

1.1.1. Continuous urban fabric:Most of the land is covered by structures and transport network. Buildings, roads and artificially surface areas cover more than 80% of the total surface. Non-linear areas of vegetation and bare soil are exceptional

1.1.2 Discontinuous urban fabricMost of the land is covered by structures. Buildings, roads and artificially surface areas are associated with vegetated areas and bare soil, which occupy discontinuous but significant surfaces. Between 10% and 80% of the land is covered by residential structures.

Corine - Moland Classifications

This is the same methodology used in Land Cover Classification databases. E.g: Corine LC, Moland, Anderson,…


3.2. Problems experienced during the design, production and useof Land Cover classifications (CORINE, Moland, etc…)


Proliferation of “difficult to use” classes, due to the multiple “crossings” of several classification criteria

1) Class “explosion” (in detailed nomenclatures)

This has been a great problem in the effort to develop and use of Spanish 5 level 84 classes developed for CLC2000


Complex definitions, in which several “classification rules” apply simultaneously, cause incoherencies:- “overlapping definitions” (some polygons can be assigned to more than one class)- “un-definitions” (some polygons cannot be assigned to any of the classes)

- E.g.: Moland 1.1.1.1. Residential continuous dense urban fabric:- Most of the land is covered by structures and transport network.- Buildings, roads and artificially surface areas cover more than 80% of the total surface- Non-linear areas of vegetation and bare soil are exceptional- Residential structures cover more than 80% of the total surface- More than 50% of the buildings have three or more stories.”

2) Class definition incoherencies


Information stored in the database is much less than information acquired by the photointerpreter:

E.g.: The photointerpreter evaluates a certain polygon’s trees percentageas 75 %, and in consequence he labels it as Corine 3.1.1. “Broad-leaved forest”.

… But the user only receives the informationthat trees are “more than 30 %”

3) Important information lost


4) Mixed classes problems

Need to create “mixed classes”, due to the obligation to assign a single class to mixed polygonsE.g: “Mixed forest”, “Complex cultivation patterns”,…

- Mixed classes provide little information to user:E.g.: “Complex cultivation patterns”,…???

- Mixed classes lead to erroneous conclusions in the use of the database:E.g.: If one wants to know how many vineyards there are in a certain region, he will search for the class 2.2.1: “Vineyards”. But there can also be plenty of vineyards “hidden” in other classes as: 2.2.3: “Olive groves”(which includes the association of olives trees and vines); 2.4.2: “Complex cultivation patterns”, etc…


Important spatial variations in certain parameters values do notappear in the database if this variations do not “cross” the “threshold line”

5) Important spatial variations not registered

- E.g.: Urban areas with very different levels of building densities (as 10 % and 50 %) have to be assigned to the sameMoland class (1.1.2.2. Residential discontinuous sparse urban fabric.)


Important temporal changes do not appear in the changes database, because:

- These changes do not “cross” the “definition rule” threshold.E.g.: If the building density of a polygon has increased from 11% to 79 %in the time between 2 revisions of the database, this polygon is labeled as Corine´s 1.1.2. “Discontinuous urban fabric”, in both databases, and so no change is registered.

and/or:- These changes are “hidden” inpolygons assigned to dominantclasses or to mixed classes.

6) Important temporal changes not detected


Many parameters and “Indicators” could be calculated from the values of the parameters appearing in class definitions (sometimes “crossing” them with exogenous information such as population, etc…).

Eg:• building density (m3/m2)in an area• m2 of building per person in an area• average height of buildings in a town• % of impervious surface in an area• % of trees in a forest• m2 of green areas per person in an area• land take by transport infrastructures in a city• etc…

7) Parameters and Indicators calculations not possible


Need for calculation of parameters and Indicators

WorldWorld

Database1

Database1

Datamodel

1

Datamodel

1 DatasetA

DatasetA

Environ-mental

Processesmodels

Environ-mental

Processesmodels

Predictionsof Future

Predictionsof Future- Laws

- Policies- Laws- Policies

Database2

Database2

Datamodel

2

Datamodel

2Dataset

B

DatasetB

Databasen

Databasen

DataModel

n

DataModel

n

DatasetN

DatasetN

MultilayerGeoprocessingMultilayer

Geoprocessing

MultilayerGeoprocessing

New data sets:

- Parameters

- Agri-environmental Indicators

Interpretation

Actions

Political decisions

DatabasesData specifications

e.g: Land Cover e.g: Urban sprawl

e.g: Climatic

change

e.g: Future climatee.g: Kioto Protocol


Land Cover Classifications do not allow calculating these indicators, because de real values of the different parameters are not storedin the database (only “intervals”):

E.g: You can not divide “Artificially surfaced areas are more than 80 %” by a surface

Calculations not possible …


It is impossible to compare, “translate” or mosaic two databases built with different Nomenclatures:

E.g.: When we have a 3.1.1. “Broad leaved forest” polygon in Corine (defined as having more than 30 % of canopy closure)

→ there is no way to know if it should be labeled as “Forest” in a database with a different Nomenclature where “forests” are defined as “more than 50 % of canopy closure”.

8) Mosaicking different databases not possible


If one wants to derive a smaller scale database (through a “generalization” process), one must aggregate polygons into bigger ones.But there is no way to automatically derive the class of the resultant polygon:

E.g: A polygon classified as Corine´s 1.1.1 (“Continuous urban fabric”) aggregated with a polygon classified as 1.1.2 (“Discontinuous urban fabric”) could result in an aggregated polygon that should be classified as 1.1.1 or 1.1.2.

There is no way to know, without repeating the interpretation !

9) Automatic generalizations not possible


3.3. UN FAO´s LCCS (Land Cover Classification System) approach


Land Cover Classification System (LLCS) has been developed by UN-FAO in an effort to solve the problems associated with existing Classification databases.

LCCS establishes a standardized comprehensive system that allows one to build “a priori” classification “nomenclatures”and “legends” in a more rigorous and coherent way

LCCS approach


LCCS: our opinion

LCCS correctly exposes some of the problems of Land Cover classifications mentioned before

In particular, it addresses and solves quite wellProblem Number 2 (Class definitions incoherencies)


.. But there are still many remaining problems with LCCS approach…

LCCS: our opinion (2)


• Plenty of information lost• Mixed classes problems• Spatial variations not registered• Temporal variations not detected• Parameters and Indicators calculations not possible• Database mosaicking not possible• Automatic generalization not possible

Problems remaining


LCCS makes the same mistake than traditional HC LU/LC nomenclatures:

It tries to classify each polygon in one and only one class, using the values of the “classifiers” to put sequentially the polygon to one side or the other of the “classification rules”

(It is important to note that the values that this classifiers haIt is important to note that the values that this classifiers have in a ve in a particular polygon are not stored in the database. Only the particular polygon are not stored in the database. Only the polygonpolygon’’s resultant class label is stored in the databases resultant class label is stored in the database)

LCCS: our opinion (3)


• “Special”, non-standard “language” and software

Other problems of LCCS (1)


• Doesn’t fulfill ISO 19100 standards

• Not object oriented

• Not UML

• Attributes values not stored in the database: it is still only a Classification Method !

Other problems of LCCS (2)


Outline

1. Introduction2. Example: Database of people3. Example: Land Cover classifications4. New solution:

Parametric Object Oriented databases.Application to the Land Cover case


6. Conclusions


Characteristics to be considered:- nationality- age- study level- work- residence- eyes color- hair color- diseases- married ?- number of sons- hobbies- religion…….…..

Back to the example: “People”


Parametric database of “people”

- Gender: controlled list (man, women)- Height (m): real- Weigh (Kg): real- Nationality: controlled list (country table)- Age (years): integer- Study level: controlled list- Work: controlled list- Residence: text- Eyes color: controlled list- Hair color: controlled list- Diseases: controlled list- Married: boolean- Number of sons: integer- Hobbies: controlled list- Religion: controlled list

People


One instance of “people”

- Gender: man- Height (m): 1.77- Weigh (Kg): 82.6- Nationality: USA- Age (years): 52- Study level: University- Work: Engineer- Residence: San Diego, CA- Eyes color: brown- Hair color: blond- Diseases: none- Married: yes- Number of sons: 2- Hobbies: golf, sailing- Religion: protestant

John Smith


• A data model is the description of what we are storing in a database and how.

• It is the “link” between reality and the Database

What is a Data Model ?

WorldWorld DatabaseDatabaseData

Model

DataModel


• “Object Orientation” is the standard in Computer Science today

• Parametric Object Oriented Data Models (POODM) are used extensively in every type of databases and Information Systems (airports, hospitals, production facilities,..)….

….including “some” GIS databases

What is a Object Orientation ?


UML (Unified Modeling Language)

The standard for Object Oriented ModelsUsed by ISO in its standards


Principal relationships between classes:

Inheritance (Generalization / Specialization): A class inherits (or specializes) the state and behavior of another class

Aggregation: allows to capture the structural relationshipsamong entities in the real world (part-of)

Association: allows to capture other kinds any of relationships among entities in the real world


Standards – ISO 19109

Example: Three features (Property Parcel, Building and Loan)


• POODM (Parametric Object Oriented Data Models) allow an unprecedented flexibility and capability in de design and use of very complex Information Systems

POODM


• POODM is the best technology to address the great complexity of Geographic information:

Represent the “systemic” nature of the world

Define “objects” of different scales (Covers, Elements,…) and the relations between them

Assign attribute values to each one of these “objects” in a structured and organized way


UML (Universal Modeling Language) lets us express, store, modify, extend,… this structure easily and make it understandable by anybody


• Land Cover has been traditionally modeled (Corine, MolandAndersons,…) using classifications, legends, nomenclatures…. … All of them obsolete techniques

• Up to now (to our knowledge) POODM have not been used for Land Cover Information

POODM for Land Cover Information







Density thresholds

Land Cover Elements

Percentage of polygon occupation

Attributes

Land Cover Classifications (Moland legend)







Density thresholds:

- somewhat “arbitrary”

- induce class proliferation







Simple components:

- not structured

- not explicit (“hidden” in de definitions of the classes)

- incomplete

- not “extensible” (one can not subdivide a component in different types)







Attributes:

- not structured

- not explicit in the database (“hidden” in de definitions of the classes)

- incomplete

- actual values not stored (only “ranges”)

- not “extensible” (one can not add new attributes)







Percentage of polygon occupation:

- sometimes expressed vaguely (e.g: “predominant”)

- actual values not stored in database

- not explicit (“hidden” in the definition of the classes)


Land Cover elements:- complete

- structured

- explicit

- extensible

Attributes:- complete

- structured

- explicit

- exact values measured

and stored in database

- extensible

Percentage of polygon occupation:

- explicit

- expressed rigorously:

(type: real, integer, boolean, list,…)

- exact values measured and

stored in database

Parametric object oriented data model (POODM)


• From the “Conceptual Model” in an UML diagram an expert in Relational Databases can easily derive a “Physical Implementation” in any standard RDBMS

• This RDB stores all the objects and attributes in a structured and robust way, and allows to interact with all these data through:• SQL queries• Different databases “crossing”• Interaction with an specific “application”


The use of POODM for Land Cover Information has been developed, tested and is working in the Spanish SIOSEProject, which is in advanced production phase(finishing by end of 2008)


A physical implementation (Relational Database and an Application to fill it) according with data model specifications have been developed and are in use in SIOSE production


We are presenting here an “evolution” of SIOSE Data Model, designed to allow for:

Different scalesDifferent geographical areasDifferent needsDifferent production methodology



Land Cover

Elements

Land Cover

Classes

Core Clases


Basic principles of POODM (1)

We do not “classify” polygons. We describe polygons

Each polygon has one or more “Land covers” (LC)

We do not use “mixed classes”: we store in the database the % of the polygon occupied by each “Land cover”


Basic principles of POODM (2)

Land Covers are made up of“Land Cover Elements” (LCE)

We store in the database the % of each land cover occupied by each element.

Each LC and LCE can have “attributes”

The actual values of all attributes for each LC and LCE are storedin the database


Land cover 1: 100% of poligon’s surfaceArtificial area. Built-up area. ResidentialLand Cover Elements in it:

• 50% Artificial element. Structure. Building+individual house

• 15% Artificial element. Artificial surface. Road• 15% Vegetation. Trees• 15% Vegetation. Herbaceous. • 5% Artificial liquid

Examples


Land cover 1: 2% of polygon´s surfaceAgricultural area. Herbaceous crops+Greenhouses: yesLand Cover Elements in it:

• Vegetation. Herbaceous.

Land cover 2: 70% of polygon’s surfaceAgricultural area. Herbaceous cropsLand Cover Elements in it:

• Vegetation. Herbaceous. Wheat

Land cover 3: 20% of polygon’s surfaceAgricultural area. Permanent crop. Fruit trees plantationLand Cover Elements in it:

• 60% Vegetation. Woody. Tree. Orange trees• 40% Vegetation. Woody. Tree. Lemon trees

Land cover 4: 8%of polygon’s surfaceArtificial area. Infrastructure. ReservoirsLand Cover Elements in it:

• Natural terrain. Water

Examples


Land cover 1: 100% of polygon’s surfaceNatural area. Terrestrial. Natural area with woodland crops

Land Cover Elements in it:• 45% Vegetation. Woody. Tree.

+ Pinus pinaster• 55% Vegetation. Woody. Tree.

+ Quercus ilex

Examples


“Backward” compatibility

From a robust and well designed Parametric Object Oriented Land Cover Database, land cover classifications and nomenclaturescan be derived by making appropriate SQL queries to the database


“Forward” compatibility

The information in existing Land Cover classifications datasets can be entered in an adequately designed POO database:

Class definitions attributes intervals

+ attribute_max+ attribut_min


Adequacy to INSPIRE data flows ?


YESYes, but not applicable because of point 2.

3. Semantic generalization

2. Extensibility

1. Spatial generalization

Need

YESNO- Proliferation of unusable classes, due to the multiple “crossings” of several classification criteria- It is impossible to add external information from a specialized field to a HC database

YESNOWhen we aggregate polygons into bigger ones, there is no way to automatically derive the class of the resultant polygon

Object OrientedData Models

Land Cover classifications

Adequacy to INSPIRE data flows


YESOne can update certain “covers”, elements or attributes of an Object Oriented database more frequently. E.g:- urban fabric: 1 year- forest trees: 5 years

NO

Each polygon has a single attribute: the class label. Is has to be updated at once

4. Different update periods

YESThe mean of continuous value variables for each polygon´s area can then be input and stored in the OODM database as a parameter that qualifies each polygon

NOEach polygon has a single attribute: the

class label

6. Integration with remote sensing automatically derived parameters

5. Allow formulti- layer geoprocessing

Need

YESNOIt is not possible to calculate derived Parameters (and agri-environmental indicators) based on database's parameter values, because these values are not stored in the database

Object OrientedData Models


Adequacy to Inspire data flows


YES

One can translate existing classifications to a common POODB

NO

There is no way to know de label of a polygon in a DB with a different Nomenclature

7. Mosaicking of existing Land Cover databases

Need Object OrientedData Models


Adequacy to Inspire data flows


Outline




6. Conclusions


Classifications “hidden” in other GI themes

Road networks:Main roadsSecondary roadsLocal roads…

Hidrology:First order riversSecond order rivers………


Outline




6. Conclusions


Conclusions (1)

Geographic Information should not be modeled by classifications / legends / nomenclatures, as they imply a great decrease in the quantity and usefulness of information stored

FAO’s LCCS (Land Cover Classification System) is notan acceptable solution either

Land Cover, as any other G.I. theme can and shouldbe modeled in UML using Parametric Object Orientedtechnology


Conclusions (2)

The ideas and problems presented here are applicableto the development of many other Inspire Themes Data Models

Most of present GI databases are obsolete, because they were designed only to store information in paper maps

Many of new data models being built today are also obsolete, because they are “contaminated” (“poluted”) by “map centric” “out of date” way of thinking. (E.g: the use of classifications, legends or nomenclatures)¡


Many GMES data models currently in use suffer from this same problems

Conclusions (3)


Some of this obsolete “map centric” data models are even being proposed as international standards (ISO, INSPIRE,…)

CEN and INSPIRE should be careful not to adopt obsolete data models as standards

Conclusions (4)


It is imperative to change all this data models and databases if we want G.I. to achieve the goals that we expect of it in the 21st century

INSPIRE is designed mainly to permit the interaction between existing databases…

As most existing G.I. databases are “map based”….

Conclusions (5)


…. INSPIRE is in great danger of implementingobsolete specifications (Corine Land Cover, LCCS,…)

Conclusions (6)


We need a new ‘paradigm’ in 21st century geographic information !

Conclusions (7)


Thank you !

[email protected]


Extra slides…..


Principles

1) The working area must be divided in a set of closed polygons, each one containing a surface that is as homogeneous as possible.

2) Our aim is not to classify each polygon but to “describe” each one as well as possible. These descriptions are made associating “Land Covers”, “Land Cover Elements” and “attributes” for them to each polygon.

3) “Land Covers” are thematic categories. They are defined with conceptual definitions of biophysical or socio-economic criteria (morphology, structure, relation with other land cover entities, etc….)


Principles

4) “Land Cover Elements” are the objects found in the terrain that make up “Land Covers”. Land cover elements (e.g.: buildings, trees, rock, sand, etc…) are the basic components of land cover.

5) Each “Land Cover” (LC) and “Land Cover Element” (LCE) has its own attributes. Attributes are observable characteristics (biophysical or socio-economic) that describe LC or LCE in more detail. These attributes take different values in each “instance” (appearance of the LC or LCE).


Principles

6) Some attributes are simple variables of the adequate type (e.g.: number of floors: integer). Other attributes are “Controlled lists” (e.g.: “vegetation distribution geometry”). Controlled lists are defined as “enumerations” in UML. Other attributes are more complex (e.g.: “vegetation state”) and are represented as “UML classes” (white rectangles in the UML diagram).

100100CEN TC 287 Mediterranean Workshop. Athens, 14 March 2008

Principles

7) Homogeneous polygons (at the scale of the database) have one Land Cover.

8) When homogeneous surfaces have an area smaller than the Minimum Mapping Unit, the photointerpreter must draw a non-homogeneous polygon that encloses areas with different characteristics. In this case, thephotointerpreter must measure (or estimate), and store in the database, the percentage of surface in which each “Land Cover” is present in the polygon. The sum of all percentages of each polygon must be 100 %.

9) For each “Land Cover” found in a polygon, the photointerpreter must study its “inner composition”, and measure and store in the database:

- The exact values for each of the attributes in this “Land Cover”- The “Land Cover Elements” present in this “Land Cover”, and the percentage of

the surface that each occupies.- The exact values for each of the attributes in each “Land Cover Element”. (e.g.:

trunk diameter=0.40m; Number of floors = 4)


Principles

10) All the information of each polygon (percentage of surface of each LC present, average values of each parameter affecting each LC or LCE,…) is stored in an alphanumerical relational database (RDB). This RDB has been designed with two objectives in mind:

- Materialize as exactly as possible the Parametric Object Oriented Data Model represented in the UML diagram.

- Allow for unlimited future extensions of the model, making it as easy as possible to add more classes, parameters, conditions, etc…







Murbandy/Moland legend (1/9)


1.2.1.1. Industrial areasSurfaces occupied by industrial activities, including their related areas.1.2.1.2. Commercial areasSurfaces basically occupied by commercial activities, including their related areas.

1.2.1.3 Public and private services not related to the transport systemSurfaces occupied by general government, semi-public or private administrations, including their related areas.1.2.1.4 Technological infrastructures for public services1.2.1.5 Archaeological sites1.2.1.6 Places of worship1.2.1.7 Non-vegetated cemeteries1.2.1.8 Hospitals1.2.1.9 Restricted access services1.2.1.10 Agro-industrial complexes1.2.1.11 Surface pipelines1.2.2.1 Fast transit roads and associated landMotorways, by-pass roads, toll-ways, etc1.2.2.2 Other roads and associated land1.2.2.3 Railways and associated land1.2.2.4 Other railways1.2.2.5 Additional transport structures1.2.2.6 Parking sites for private vehicles1.2.2.7 Parking sites for public vehicles

1.2.3 Port areasInfrastructure of port areas, including quays, dockyards and marinas1.2.4 AirportsAirport installations: runways, buildings and associated land

1.2. Industrial, commercial and transport units

1.2.1 Industrial, commercial, public and private units:Artificially surface areas devoid of vegetation, occupy more then 50% of the area in question, which also contains buildings and /or vegetated areas.

1.2.2 Road and rail networks and associated landMotorways, railways, including associated installations . Minimum width to include: 25 m



1.3.1 Mineral extraction sitesAreas with open-pit extraction of industrial minerals or other minerals (opencast mines). Included flooded gravel pits, except for river-bed extraction.1.3.2 Dump sitesLandfill or mine dump sites, industrial or public.1.3.3 Construction sitesSpaces under construction development, soil or bedrock excavations, earthworks.1.3.4 Abandoned land 1.3.4.1 Bombed areas1.4.1 Green urban areasAreas with vegetation within urban fabric. Includes parks (and cemeteries with vegetation)

1.4.1.1. Vegetated cemeteries

1.4.2 Sport and leisure facilitiesCamping grounds, sport grounds, leisure parks, golf courses, racecourses, etc. Includes formal parks not surrounded by urban zones.

1.3.Mine, dump and construction sites

1.4.Artificial non-agricultural vegetated areas



2.1.1.1 Arable land without dispersed vegetation

2.1.1.2 Arable land with scattered vegetation

2.1.1.3 Greenhouses

2.1.1.4 Drained arable land

2.1.2 Permanently irrigated landCrops irrigated permanently or periodically, using a permanently infrastructure. Most of these crops cannot be cultivated without an artificial water supply.2.1.3 Rice fieldsLand prepared for rice cultivation. Flat surfaces with irrigated channels. Surfaces periodically flooded.

2.2.1 VineyardsAreas planted with vines, when the vineyards parcels exceed the 50% of the area and/or they determine the land use of the area.

2.2.2 Fruit trees and berry plantationsParcels planted with fruit trees or shrubs: single or mixed fruit species, fruit trees mixed with permanent grass surfaces.

2.2.3 Olive grovesAreas planted with olive tress, including mixed occurrence of olive trees and vines on the same parcel.

2. AGRICULTURAL AREAS

2.1.1 Non-irrigated arable landCereals, legumes, fodder crops, root crops and fallow land, flowers, vegetables, nurseries of fruit trees, whether open field, under plastic or glass. Includes other annually harvested plants with more than 75% of the area under a rotation system.

2.1 Arable land

2.2 Permanent crops



2.3.1.1 Pastures without trees and shrubs

2.3.1.2 Pastures with trees and shrubs

2.4.1 Annual crops associated with permanent cropsNon permanent crops (arable land or pastures) associated with permanent crops on the same parcel

2.4.2.1 Complex cultivation patterns without settlement

2.4.2.2 Complex cultivation patterns with scattered settlement

2.4.3.1 Prevalence of arable land and significant areas of natural vegetation

2.4.3.2 Prevalence of pastures and significant areas of natural vegetation

2.4.4 Agro-forestry areasAnnual crops or grazing land, covering less than 50% of the surface, under the wooded cover of forestry species.

2.3.1 PasturesDense grass cover, of floral composition, dominated by graminaceas, not under a rotation system. Mainly for grazing , but the fodder can be harvested mechanically.

2.4.3 Land principally occupied by agriculture, with significant areas of natural vegetationAreas principally occupied by agriculture, interspersed with significant natural areas, including wetlands or water bodies, out crops

2.4.2 Complex cultivation patternsJuxtaposition of small parcels of diverse annual crops, pastures and/or permanent crops.

2.4 Heterogeneous agricultural areas

2.3 Pastures



3.1.1.1 Deciduous forest with continuous canopy

3.1.1.2 Deciduous forest with discontinuous canopy

3.1.1.3 Evergreen forest with continuous canopy

3.1.1.4 Evergreen forest with discontinuous canopy

3.1.2.1 Coniferous forest with continuous canopy

3.1.2.2 Coniferous forest with discontinuous canopy

3.1.3.1 Forest mixed by alternancy of single trees with continuous canopy3.1.3.2 Forest mixed by alternancy of single trees with discontinuous canopy3.1.3.3 Forest mixed by alternancy of stand of trees with continuous canopy3.1.3.4 Forest mixed by alternancy of stand of trees with discontinuous canopy3.2.1.1 Coarse permanent grassland / Tall herbs without trees and shrubs

3.2.1.2 Coarse permanent grassland / Tall herbs with trees and shrubs

3.2.1.3 Coastal and floodplain meadows

3.2.2.1 Heath land

3.2.2.2 Dwarf pine

3.2.3 Sclerophyllous vegetationBushy sclerophyllous vegetation, includes maquis and garriga. In case of shrub vegetation areas composed of sclerophyllous species and heathland species with no visible dominance (each species occupy about 50% of the area), priority will be given to sclerophyllous vegetation and the whole class will be assigned class 323.

3.2.4.1 Artificial young stands3.2.4.2 Natural young deciduous stands3.2.4.3 Natural young coniferous stands3.2.4.4 Wooded fens, bogs and wooded transitional bog

3. FOREST AND SEMI-NATURAL AREAS

3.1.2 Coniferous forestVegetated formation composed principally of trees, including shrub and bush understoreys, where coniferous species predominate (more than 75% of the formation)

3.1.3 Mixed forestVegetated formation composed principally of trees, including shrub and bush understoreys, where neither broad-leaved nor coniferous species predominate.

3.2.1 Natural grasslandLow productivity grassland (at least 75% of the surface). Often situated in areas of rough, uneven ground. Frequently included rocky areas, briars and heathland.

3.2.2 Moors and heathlandVegetation with low and closed cover, dominated by bushes, shrubs and herbaceous plants (heather, briars, broom, gorse, laburnum, etc).

3.1.1. Broad-leaved forestVegetated formation composed principally of trees, including shrub and bush understoreys, where broad-leaved species predominate (more than 75% of the formation)

3.1 ForestAreas occupied by forest or woodland with a vegetation pattern composed of native or exotic trees and which can be used for the production of timber or other forest products. The forest trees are under normal climatic conditions higher than 5 m with a canopy closure of 30% at least.

3.2 Shrubs and/or herbaceous vegetation associations

3.2.4 Transitional woodland/shrubBushy or herbaceous vegetation with scattered trees. Can represent either woodland degradation or forest regeneration/recolonisation.



3.3.1.1 Dunes

3.3.1.2 Beaches

3.3.1.3 Inland sand

3.3.2.1 Littoral/sub-littoral rocks

3.3.2.2 Coastal cliffs

3.3.2.3 Inland cliffs/ bare rocks/ volcanic debris

3.3.3.1 Sparse vegetation on sand

3.3.3.2 Sparse vegetation on bare rocks

3.3.4 Burnt and damaged by disaster areasAreas affected by recent fires, still mainly black.

3.3.4.1 Burnt areas

3.3.5 Glaciers and perpetual snowLand cover by glaciers or permanent snowfields (glaciers and perpetual snow more than 50%)

3.3.3 Sparsely vegetated areasIncludes steppes, tundra and badlands. Scattered high-altitude vegetation. Vegetation layer covers between 15% and 50% of the surface.

3.3 Open spaces with little or no vegetation

3.3.1 Beaches, dunes and sand planesBeaches, dunes and expanses of sand or pebbles in coastal or continental locations, including beds of stream channels with torrential regime.3.3.2 Bare rockScree, cliffs, rock outcrops, including active erosion, rocks and reef flats situated above the high-water mark (75% of the land surface is covered by rocks).



4.1.1.1 Marshes with reeds 4.1.1.2 Marshes without reeds 4.1.1.3 Open fen and transitional bog 4.1.2.1 Exploited peat bog with lawn communities4.1.2.2 Unexploited peat bog with lawn communities4.1.2.3 Peat bog with pool communities4.2.1.1 Salt marshes with reeds

4.2.1.2 Salt marshes without reeds

4.2.2 SalinesSalt-pans, active or in process of abandonment. Sections of saltmarsh exploited for the production of salt by evaporation. They areclearly distinguishable from the rest of the marsh by theirparcellation and embankment systems.

4.2.3 Intertidal flatsGenerally unvegetated expanses of mud, sand or rock lyingbetween high and low water marks. 0 m contour on maps.

4.1.2 Peat bogsPeatland consisting mainly of decomposed moss and vegetable matter. May or may not be exploited.

4.1.1 Inland marshesLow-lying land usually flooded in winter, and more or less saturated by water all year around.

4. WETLANDS

4.2 Coastal wetlands

4.1 Inland wetlands

4.2.1 Salt marshesVegetated low-lying areas, above the high-tide line, susceptible to flooding by seawater. Often in the process of filling in, gradually being colonized by halophilic plants.



5.1.1.1 Canals

5.1.1.2 Rivers

5.1.2.1 Natural standing water5.1.2.2 Artificial reservoirs

5.2.1 Coastal lagoonsStretches of salt or brackish water in coastal areas which areseparated from the sea by a tongue of land or other similartopography. These water bodies can be connected to the sea atlimited points, either permanently or for parts of the year only.

5.2.2 EstuariesThe mouth of a river within which the tide ebbs and flows.

5.2.3 Sea and oceanZone seaward of the lowest tide limit.

5.2 Marine waters

5. WATER BODIES 5.1.1 Water coursesNatural or artificial water-courses serving as water drainage channels. Include canals. Minimum width for inclusion: 25 m

5.1.2 Water bodiesNatural or artificial stretches of water.

5.1 Inland waters



Open issues


Open issues (1)

What is the best way to model land use: new dm, complex attributes to land cover classes, methods,…?

More “levels” in the data model (e.g: polygon > land cover > patch/stand > population/set > individual > part > material)

Hierarchical polygons ?

Attributes values by mean + standard deviation of the population/set?

Temporal existence/presence of elements?

“Multiple fuzzy membership”?


Open issues (2)

Model and measure “mobile” elements presence ?:

Artificial: cars, trains,..

Natural:Animals:

Wild

Cattle

People


Open issues (3)

Buildings

VegetationGeology

SoilsOther artificial elements

Agriculture Aquaculture

Natural areas:Seas

BiotopesHydrography

TransportIndustrial

EnergyMineralUtilities


Open issues (4)

Buildings

VegetationGeology

SoilsOther artificial elements

Agriculture Aquaculture

Natural areas:Seas

BiotopesHydrography

TransportIndustrial

EnergyMineralUtilities

Land Cover =(part of) the Core of theInspire ConsolidatedUML model ?

Documents

image classification taxonomy