igarss 2011.ppt
TRANSCRIPT
![Page 1: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/1.jpg)
Archaeological Land Use Characterization Archaeological Land Use Characterization using Multispectral Remote Sensing Datausing Multispectral Remote Sensing Data
Dr. Iván Esteban Villalón Turrubiates, Dr. Iván Esteban Villalón Turrubiates, Member,Member, IEEE IEEE María de Jesús Llovera TorresMaría de Jesús Llovera Torres
UNIVERSIDAD DE GUADALAJARAUNIVERSIDAD DE GUADALAJARACENTRO UNIVERSITARIO DE LOS VALLESCENTRO UNIVERSITARIO DE LOS VALLES
Monitoring Hidrological Variations using Multispectral Monitoring Hidrological Variations using Multispectral SPOT-5 Data: Regional Case of Jalisco in MexicoSPOT-5 Data: Regional Case of Jalisco in Mexico
Dr. Iván Esteban Villalón Turrubiates, Dr. Iván Esteban Villalón Turrubiates, Member,Member, IEEE IEEE
![Page 2: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/2.jpg)
OverviewOverview
- AbstractAbstract- Remote Sensing DefinitionRemote Sensing Definition- Sensor ResolutionSensor Resolution- Introduction to Image ClassificationIntroduction to Image Classification- Model FormalismModel Formalism- Verification ProtocolsVerification Protocols- Simulation ExperimentsSimulation Experiments- Concluding RemarksConcluding Remarks
![Page 3: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/3.jpg)
AbstractAbstractProposition - A new and efficient classification approach of remote sensing signatures extracted from large-scale multispectral imagery.
Contribution - This approach exploits the idea of combining the spectral signatures from a remote sensing image to perform a novel and accurate classification technique.
Verification - Simulation results are provided to verify the efficiency of the proposed approach.
![Page 4: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/4.jpg)
REMOTE SENSING REMOTE SENSING DEFINITIONDEFINITION
![Page 5: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/5.jpg)
Remote SensingRemote SensingRemote Sensing can be defined as:
"The arte and science to obtain data from an object avoiding direct contact with it” (Jensen 2000).
There is a transmission medium involved?
![Page 6: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/6.jpg)
![Page 7: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/7.jpg)
Remote SensingRemote SensingOf the Environment:
… is the collection of information regarding our Planet surface and its phenomena involving sensors that are not in direct contact with the studied area.
The main focus is in recollected information from a spatial perspective throughout electromagnetic radiation transmission.
![Page 8: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/8.jpg)
![Page 9: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/9.jpg)
Remote SensingRemote Sensing
Sensor election.
Reception, storage and digital signal processing of the data.
Analysis of the resulting information.
![Page 10: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/10.jpg)
A) Illumination Source
B) Radiation
C) Interaction with the object
D) Radiation sensing
E) Transmission, reception and data processing
F) Analysis and interpretation
G) Application
ProcessProcess
![Page 11: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/11.jpg)
SENSOR RESOLUTIONSENSOR RESOLUTION
![Page 12: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/12.jpg)
ResolutionResolution All remote sensing systems use four types of
resolution:
Spatial
Spectral
Temporal
Radiometric
![Page 13: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/13.jpg)
Spatial ResolutionSpatial Resolution
![Page 14: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/14.jpg)
Spectral ResolutionSpectral Resolution
![Page 15: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/15.jpg)
Time
July 1 July 12 July 23 August 3
11 days
16 days
July 2 July 8 August 3
Temporal ResolutionTemporal Resolution
![Page 16: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/16.jpg)
6-bits Range0 63
8-bits Range0 255
010-bits Range
1023
Radiometric ResolutionRadiometric Resolution
![Page 17: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/17.jpg)
INTRODUCTION TO IMAGE INTRODUCTION TO IMAGE CLASSIFICATIONCLASSIFICATION
![Page 18: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/18.jpg)
Image ClassificationImage Classification Why classify?
Make sense of a landscape Place landscape into categories (classes)Forest, Agriculture, Water, Soil, etc.
Classification scheme = structure of classes Depends on needs of users.
![Page 19: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/19.jpg)
Typical usesTypical uses Provide context
Landscape planning or assessment Research projects Natural resources management Archaeological studies
Drive models Meteorology Biodiversity Water distribution Land use
![Page 20: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/20.jpg)
Example: Near Mary’s PeakExample: Near Mary’s Peak•Derived from a 1988 Landsat TM image
•Distinguish types of forest
Open
Semi-open
Broadleaf
Mixed
Young Conifer
Mature Conifer
Old Conifer
Legend
![Page 21: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/21.jpg)
Classification: Critical PointClassification: Critical Point LAND COVER not necessarily equivalent to LAND USE We focus on what’s there: LAND COVER Many users are interested in how what is there is being
used: LAND USE
Example Grass is land cover; pasture and recreational parks are
land uses of grass
![Page 22: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/22.jpg)
Basic Strategy: How to do it? Basic Strategy: How to do it? Use radiometric properties of remote sensor Different objects have different spectral signatures
![Page 23: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/23.jpg)
In an easy world, all “vegetation” pixels would have exactly the same spectral signature.
Then we could just say that any pixel in an image with that signature was vegetation.
We could do the same for soil, water, etc. to end up with a map of classes.
Basic Strategy: How to do it? Basic Strategy: How to do it?
![Page 24: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/24.jpg)
But in reality, that is not the case. Looking at several pixels with vegetation, you’d see variety in spectral signatures.
The same would happen for other types of pixels, as well.
Basic Strategy: How to do it? Basic Strategy: How to do it?
![Page 25: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/25.jpg)
The Classification Trick: The Classification Trick: Deal with variabilityDeal with variability
•Different ways of dealing with the variability lead to different ways of classifying images.
•To talk about this, we need to look at spectral signatures a little differently.
![Page 26: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/26.jpg)
Think of a pixel’s brightness in a 2-Dimensional space. The pixel occupies a point in that space.
The vegetation pixel and the soil pixel occupy different
points in a 2-D space.
![Page 27: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/27.jpg)
With variability, the vegetation pixels now
occupy a region, not a point, of n-Dimensional space.
Soil pixels occupy a different region of n-Dimensional space.
![Page 28: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/28.jpg)
• Classification: • Delineate boundaries of classes in n-dimensional space• Assign class names to pixels using those boundaries
Basic Strategy: Basic Strategy: Deal with variabilityDeal with variability
![Page 29: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/29.jpg)
Classification StrategiesClassification StrategiesTwo basic strategies:
Supervised Classification We impose our perceptions on the spectral data.
Unsupervised Classification Spectral data imposes constraints on our interpretation.
![Page 30: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/30.jpg)
Digital Image
Supervised ClassificationSupervised Classification
The computer then creates...
Supervised classification requires the analyst to select training areas where he knows what is
on the ground and then digitize a polygon within that area…
Mean Spectral Signatures
Known Conifer Area
Known Water Area
Known Deciduous Area
Conifer
Deciduous
Water
![Page 31: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/31.jpg)
Multispectral ImageInformation
(Classified Image)
Mean Spectral Signatures
Spectral Signature of Next Pixel to be
Classified
Conifer
Deciduous
Water Unknown
Supervised ClassificationSupervised Classification
![Page 32: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/32.jpg)
Water
Conifer
Deciduous
Legend:
Land Cover Map
The Result: Image SignaturesThe Result: Image Signatures
![Page 33: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/33.jpg)
Unsupervised ClassificationUnsupervised Classification In unsupervised classification, the spectral data imposes constraints on our interpretation.
How? Rather than defining training sets and carving out pieces of n-Dimensional space, we define no classes beforehand and instead use statistical approaches to divide the n-Dimensional space into clusters with the best separation.
After the fact, we assign class names to those clusters.
![Page 34: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/34.jpg)
Unsupervised ClassificationUnsupervised Classification
Digital Image
The analyst requests the computer to examine the image and extract a number of spectrally distinct
clusters… Spectrally Distinct Clusters
Cluster 3
Cluster 5
Cluster 1
Cluster 6
Cluster 2
Cluster 4
![Page 35: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/35.jpg)
Saved Clusters
Cluster 3
Cluster 5
Cluster 1
Cluster 6
Cluster 2
Cluster 4
Unsupervised ClassificationUnsupervised ClassificationOutput Classified Image
Unknown
Next Pixel to be Classified
![Page 36: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/36.jpg)
Unsupervised ClassificationUnsupervised Classification
Conif.
Hardw.
Water
Land Cover Map Legend
Water
Water
Conifer
Conifer
Hardwood
Hardwood
Labels
It is a simple process to regroup (recode) the clusters into
meaningful information classes (the legend).
The result is essentially the same as that of the
supervised classification:
![Page 37: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/37.jpg)
MODEL FORMALISMMODEL FORMALISM
![Page 38: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/38.jpg)
Multispectral ImagingMultispectral Imaging Is a technology originally developed for space-based imaging.
Multispectral images are the main type of images acquired by remote sensing radiometers.
Usually, remote sensing systems have from 3 to 7 radiometers; each one acquires one digital image in a small band of visible spectra, ranging 450 to 690 nm, called red-green-blue (RGB) regions: Blue -> 450-520 nm. Green -> 520-600 nm. Red -> 600-690 nm.
The combination of the RGB spectral bands generates the so-called True-Color RS images.
![Page 39: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/39.jpg)
Statistical Approach.
Assume normal distributions of pixels within classes.
For each class, build a discriminant function For each pixel in the image, this function calculates the
probability that the pixel is a member of that class. Takes into account mean and variance of training set.
Each pixel is assigned to the class for which it has the highest probability of membership.
Weighted Pixel Statistics MethodWeighted Pixel Statistics Method
![Page 40: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/40.jpg)
Blue Green Red Near-IR Mid-IR
Mean Signature 1
Candidate Pixel
Mean Signature 2
It appears that the candidate pixel is closest to Signature 1. However, when
we consider the variance around the signatures…
Rel
ativ
e R
efle
ctan
ce
Weighted Pixel Statistics MethodWeighted Pixel Statistics Method
![Page 41: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/41.jpg)
Blue Green Red Near-IR Mid-IR
Mean Signature 1
Candidate Pixel
Mean Signature 2
The candidate pixel clearly belongs to the signature 2 group.
Rel
ativ
e R
efle
ctan
ce
Weighted Pixel Statistics MethodWeighted Pixel Statistics Method
![Page 42: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/42.jpg)
Weighted Pixel Statistics MethodWeighted Pixel Statistics Method
![Page 43: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/43.jpg)
Weighted Pixel Statistics MethodWeighted Pixel Statistics Method
![Page 44: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/44.jpg)
VERIFICATION PROTOCOLSVERIFICATION PROTOCOLS
![Page 45: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/45.jpg)
Verification ProtocolsVerification ProtocolsA set of three synthesized images are used as verification protocols.
All synthesized images are True-Color (RGB), presented in 1024-by-1024 pixels (TIFF format).
Each synthesized image contains three different regions (in yellow, blue and black colors) with a different pattern.
The developed Weighted Pixel Statistics (WPS) algorithm is compared with the most traditional Weighted Order Statistics (WOS) method [S.W. Perry, H.S. Wong, 2002].
![Page 46: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/46.jpg)
Results:Results:11stst Synthesized Scene Synthesized Scene
Synthesized SceneSynthesized Scene WOS ClassificationWOS Classification WPS ClassificationWPS Classification
![Page 47: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/47.jpg)
Quantitative ComparisonQuantitative Comparison11stst Synthesized Scene Synthesized Scene
![Page 48: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/48.jpg)
Results:Results:22ndnd Synthesized Scene Synthesized Scene
Synthesized SceneSynthesized Scene WOS ClassificationWOS Classification WPS ClassificationWPS Classification
![Page 49: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/49.jpg)
Qualitative ComparisonQualitative Comparison22ndnd Synthesized Scene Synthesized Scene
Synthesized SceneSynthesized Scene WOS ClassificationWOS Classification WPS ClassificationWPS Classification
![Page 50: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/50.jpg)
Quantitative ComparisonQuantitative Comparison22ndnd Synthesized Scene Synthesized Scene
![Page 51: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/51.jpg)
Results:Results:33rdrd Synthesized SceneSynthesized Scene
Synthesized SceneSynthesized Scene WOS ClassificationWOS Classification WPS ClassificationWPS Classification
![Page 52: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/52.jpg)
Qualitative ComparisonQualitative Comparison33rdrd Synthesized Scene Synthesized Scene
Synthesized SceneSynthesized Scene WOS ClassificationWOS Classification WPS ClassificationWPS Classification
![Page 53: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/53.jpg)
Quantitative ComparisonQuantitative Comparison33rdrd Synthesized Scene Synthesized Scene
![Page 54: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/54.jpg)
RemarksRemarksThe quantitative study is performed calculating the classified percentage obtained with the WOS and WPS methods, respectively.
The WOS method uses only 1 spectral band.
The WPS method uses the information from the three spectral bands to analyze the pixel-level neighborhood means and variances.
The results shows a more accurate and less smoothed identification of the classes.
![Page 55: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/55.jpg)
SIMULATION EXPERIMENTSSIMULATION EXPERIMENTS
![Page 56: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/56.jpg)
Archaeological Land UseArchaeological Land UseA Remote Sensing Signatures (RSS) electronic map is extracted from the multispectral image. Three level RSS are selected for this particular simulation process, defined as:
██ – Archaeological land use zones.
██ – Modern land use zones.
██ – Natural land cover zones.
██ – Unclassified zones.
![Page 57: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/57.jpg)
Archaeological SiteArchaeological Site"Guachimontones", Jalisco Mexico"Guachimontones", Jalisco Mexico
![Page 58: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/58.jpg)
Simulation ResultsSimulation ResultsScene from "Guachimontones"Scene from "Guachimontones"
Original SceneOriginal Scene WPS ClassificationWPS Classification
![Page 59: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/59.jpg)
Hidrological VariationsHidrological VariationsA Remote Sensing Signatures (RSS) electronic map is extracted from the multispectral image. Three level RSS are selected for this particular simulation process, defined as:
██ – Humid zones.
██ – Dry zones.
██ – Wet zones.
██ – Unclassified zones.
![Page 60: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/60.jpg)
Simulation ResultsSimulation ResultsScene from "La Vega" dam, Jalisco MexicoScene from "La Vega" dam, Jalisco Mexico
Original SceneOriginal Scene WPS ClassificationWPS Classification
![Page 61: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/61.jpg)
CONCLUDING REMARKSCONCLUDING REMARKS
![Page 62: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/62.jpg)
RemarksRemarksThe WOS classifier generates several unclassified zones because it uses only one spectral band in the classification process.
The WPS classifier provides a high-accurate classification without unclassified zones because it uses more robust information in the processing.
The qualitative and quantitative analysis probe the efficiency of the proposed approach.
![Page 63: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/63.jpg)
Future WorkFuture WorkComparison with several classification techniques.
A more extensive performance analysis of the proposed approach with different synthesized images.
Application to remote sensing imagery and the study of its performance.
Hardware implementation of the proposed approach.
![Page 64: IGARSS 2011.ppt](https://reader035.vdocuments.net/reader035/viewer/2022062308/559107981a28abc56f8b4756/html5/thumbnails/64.jpg)
Dr. Iván Esteban Villalón Turrubiates, Dr. Iván Esteban Villalón Turrubiates, Member,Member, IEEEIEEE
UNIVERSIDAD DE GUADALAJARAUNIVERSIDAD DE GUADALAJARACENTRO UNIVERSITARIO DE LOS VALLESCENTRO UNIVERSITARIO DE LOS VALLES
THANK YOU!THANK YOU!Questions?Questions?