<?xml version="1.0"?>
<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="nl">
	<id>http://wiki.atlasleuven.be/api.php?action=feedcontributions&amp;feedformat=atom&amp;user=Gaelle+Fronhoffs</id>
	<title>Atlas Examenwiki - Gebruikersbijdragen [nl]</title>
	<link rel="self" type="application/atom+xml" href="http://wiki.atlasleuven.be/api.php?action=feedcontributions&amp;feedformat=atom&amp;user=Gaelle+Fronhoffs"/>
	<link rel="alternate" type="text/html" href="http://wiki.atlasleuven.be/index.php?title=Speciaal:Bijdragen/Gaelle_Fronhoffs"/>
	<updated>2026-05-05T16:16:08Z</updated>
	<subtitle>Gebruikersbijdragen</subtitle>
	<generator>MediaWiki 1.43.6</generator>
	<entry>
		<id>http://wiki.atlasleuven.be/index.php?title=Advanced_Earth_Observation_Techniques&amp;diff=917</id>
		<title>Advanced Earth Observation Techniques</title>
		<link rel="alternate" type="text/html" href="http://wiki.atlasleuven.be/index.php?title=Advanced_Earth_Observation_Techniques&amp;diff=917"/>
		<updated>2026-01-24T21:03:28Z</updated>

		<summary type="html">&lt;p&gt;Gaelle Fronhoffs: &lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;{{Infobox|data2=Canters Frank|data3=Lectures|data4=Oral exam and PRAC report|data6=3|header1=Courses and exams|header5=Background|headerstyle=background:lightgrey|label2=Prof|label3=Courses|label4=Examination|label6=Credits|label7=When?|data7=1st semester|label8=ECTS|data8=[https://onderwijsaanbod.kuleuven.be/syllabi/e/G0I91BE.htm KU Leuven]&amp;lt;br&amp;gt;[https://caliweb.vub.be/index.php?page=course-offer&amp;amp;id=011568&amp;amp;anchor=1&amp;amp;target=pr&amp;amp;year=2324&amp;amp;language=en&amp;amp;output=html VUB]|title=Course Information}}&lt;br /&gt;
&lt;br /&gt;
&#039;&#039;[ORAL] Prof. Canters is very friendly during the exam. He lets you explain everything and doesn&#039;t really look at your notes. He asks many additional questions until you get stuck.&#039;&#039;&lt;br /&gt;
&lt;br /&gt;
== 2026 ==&lt;br /&gt;
&lt;br /&gt;
=== January ===&lt;br /&gt;
20/01/2026&lt;br /&gt;
&lt;br /&gt;
# Regression trees. &lt;br /&gt;
## Explain how a regression tree is built. &lt;br /&gt;
## Explain why it is different to Stepwise regression trees and how do they make decisions?&lt;br /&gt;
## Explain Priem et al. (2019). How did they use map-based and library-based for training data? Give advantages and disadvantages of both approaches.&lt;br /&gt;
# Texture &lt;br /&gt;
## Explain how a GLCM is constructed with a numerical example. &lt;br /&gt;
## Two second order texture meaures given (entropy and contrast). What texture measures do they represent?&lt;br /&gt;
## How can we use these measures to differentiate agricultural from urban land use?&lt;br /&gt;
# Region based approaches&lt;br /&gt;
## Explain what metrics you can use. &lt;br /&gt;
## Give an example of a metric in each category and explain how it can help in discerning different types of LU. &lt;br /&gt;
## What are the advantages of a region-based approach when compared to a kernel-based approach?&lt;br /&gt;
&lt;br /&gt;
== 2025 ==&lt;br /&gt;
Written exam due to miscommunications at the faculties&lt;br /&gt;
&lt;br /&gt;
=== January ===&lt;br /&gt;
11/01/2025&lt;br /&gt;
&lt;br /&gt;
# LSMA&lt;br /&gt;
## Explain linear spectral unmixing and the principles behind it.&lt;br /&gt;
## What is MESMA and why does it improve on LSMA?&lt;br /&gt;
## How does MESME select the most appropriate model to unmix a given pixel?&lt;br /&gt;
# Semivariogram&lt;br /&gt;
## Explain in detail how a semi-variogram is constructed and how you can use it in spectral mixture analysis.&lt;br /&gt;
## How can you use a semivariogram to construct GLCMs?&lt;br /&gt;
# Metrics used in LU classification from a LC classification. (Vanderhaegen en Canters, Walde)&lt;br /&gt;
## Explain, with a drawing, the principles of patch-based metrics, profile-based metrics and graph-based metrics in LU classification from LC within given regions.&lt;br /&gt;
## Give an example of a metric in each category and explain how it can help in discerning different types of LU.&lt;br /&gt;
## What are the advantages of a region-based approach when compared to a kernel-based approach?&lt;br /&gt;
&lt;br /&gt;
== 2023 ==&lt;br /&gt;
&#039;&#039;(oral again, 2 questions per person)&#039;&#039;&lt;br /&gt;
&lt;br /&gt;
=== Januari ===&lt;br /&gt;
&lt;br /&gt;
==== 16 januari ====&lt;br /&gt;
&lt;br /&gt;
# MESMA&lt;br /&gt;
#* Explain MESMA. Explain why this is better than linear SMA.&lt;br /&gt;
#* Explain the two approaches how Degerickx et al. (2019) used LiDAR data to improve the performance of MESMA.&lt;br /&gt;
#* Which one did improve MESMA the most?&lt;br /&gt;
# SPARK&lt;br /&gt;
#* Explain SPARK.&lt;br /&gt;
#* Explain the disadvantages and advantages towards region based.&lt;br /&gt;
&lt;br /&gt;
# Textures:&lt;br /&gt;
#* What is the difference between first order and second order texture measures?&lt;br /&gt;
#* Explain how a GLCM is constructed with a numerical example.&lt;br /&gt;
#* Two second order texture meaures given (entropy and contrast). What texture measures do they represent? How can we use these measures to differentiate agricultural from urban land use?&lt;br /&gt;
# Regression&lt;br /&gt;
#* Explain Priem et al. (2019). How did they use map-based and library-based for training data?&lt;br /&gt;
#* Give the advantages and disadvantages of both approaches.&lt;br /&gt;
&lt;br /&gt;
== 2022 ==&lt;br /&gt;
&lt;br /&gt;
# MESMA&lt;br /&gt;
#* Explain MESMA in detail.&lt;br /&gt;
#* Explain the two approaches how Degerickx et al. (2019) used LiDAR data to improve the performance of MESMA. (WASMA should not be explained) How does the accuracy change?&lt;br /&gt;
#* Degerickx et al. (2019) first performed their analysis on a simulated APEX image before doing this on the actual APEX image. Why did they do this? What are the advantages of first performing the analysis on a simulated APEX image?&lt;br /&gt;
# Textures&lt;br /&gt;
#* Work out a simple numerical example to explain how a grey-level co-occurence matrix is created.&lt;br /&gt;
#* Two second order texture measures formulas are given. What texture measures do they represent? How can we use these measures to differentiate agricultural from urban land use? (contrast &amp;amp; entropy)&lt;br /&gt;
#* Explain how we can determine the optimal window size when we want to classify our image based on second-order texture measures.&lt;br /&gt;
&lt;br /&gt;
== 2021 ==&lt;br /&gt;
&lt;br /&gt;
* Explain SPARK and OSPARK&lt;br /&gt;
* Explain how Degerickx et al. used Lidar in 2 ways fro improving the performance of MESMA (explanation of WASMA not needed)&lt;br /&gt;
* Explain regression trees. When do you use this?&lt;br /&gt;
&lt;br /&gt;
== 2019 ==&lt;br /&gt;
&lt;br /&gt;
* Explain LSMA, what are the assumptions? What is the differences with MESMA? What are the advantages?&lt;br /&gt;
* How did Canters and Priemer (2016) use LIDAR to improve their classification. What shadow masks were used?&lt;br /&gt;
* Explain the concept of regression trees (Example of the powerpoint is given). When do you expect this to work better than a normal regression approach?&lt;br /&gt;
* How are graphs used to infer Land Use from Land Cover? Explain how Walde et al. used graphs in their approach. Explain their case study, methodology and the most important conclusions.&lt;br /&gt;
&lt;br /&gt;
== 2017 ==&lt;br /&gt;
&lt;br /&gt;
* Song (given figure of Ikonos and Landsat ETM+), explain formulas and explain influence of the background reflectance of non-vegetation&lt;br /&gt;
* How can you account for uncertainty in the ground truth data? (expand diagonal OR fuzzy error matrix).&lt;br /&gt;
&lt;br /&gt;
== 2016 ==&lt;br /&gt;
&lt;br /&gt;
* Discuss the semi-variogram (with the use of the figure in the course). Wherefore is this used?&lt;br /&gt;
* What difficulties do you experience when using Landsat images to generate land cover classes (impervious, soil, vegetation). What does Wu (2004) uses? Discuss LMSA. How is the accuracy assessed  (Extra questions:  the difference between MAE and RMSE, what metric is highest?(RMSE looks at more outliers, What is the spatial resolution of the orthopotos? (3 cells)).&lt;br /&gt;
* Discuss the fuzzy error matrix. Why is it used. OR: How can you account for uncertainty in the ground trhuth data? (--&amp;gt; fuzzy matrices)&lt;br /&gt;
* Explain Song.  (dat mag adhv figuur slide 1.16) en leg uit hoe Song verklaart waarom de achtergrond reflectance een invloed heeft bij dit model&lt;br /&gt;
* Explain LSMA. Which assumptions are there made for LSMA.&lt;br /&gt;
* Explain the technique used by Van de Voorde et Al.. What are the main strengths and weaknesses of this technique.&lt;br /&gt;
* GLCM, explain it. Give an numerical example. There are formulas given of entropy and contrast (only formulas, no explanation), explain the formulas.&lt;br /&gt;
* Discuss paper of Canters. What method did he use?&lt;br /&gt;
&lt;br /&gt;
== 2015 ==&lt;br /&gt;
&lt;br /&gt;
* Song: bespreek (dat mag adhv figuur slide 1.16) en leg uit hoe Song verklaart waarom de achtergrond reflectance een invloed heeft bij dit model (of zoiets).&lt;br /&gt;
* Gegeven: 2 texture formules (het waren de &#039;contrast&#039; en &#039;entropy&#039; formules, maar dat stond er niet bij...) vraag: Wat is een GLCM en hoe wordt deze geconstrueerd? Toon met een numerisch voorbeeld. Wat is het voordeel van deze measures tov first order texture measures? Hoe werken de gegeven texture measures (leg uit mbv de formule) en hoe kun je ze gebruiken om agriculture van urban te gaan onderscheiden. Wat zijn de moeilijkheden bij het werken met texture?&lt;br /&gt;
* Bespreek de verschillende manieren om een medium resolution land cover map om te vormen naar een land use map. Wat zijn de voordelen en nadelen van kernel-based en region-based approaches?&lt;br /&gt;
&lt;br /&gt;
== 2014 ==&lt;br /&gt;
&lt;br /&gt;
* Leg SMA volledig uit: hoe werkt het, wat zijn de voordelen, wat zijn de veronderstellingen. Welke problemen kan je hebben met SMA als je werkt met Landsat? Wat is het VIS-model? Bespreek de methode van Lu en Weng (2004)&lt;br /&gt;
* Gegeven: 2 texture formules (het waren de &#039;contrast&#039; en &#039;entropy&#039; formules, maar dat stond er niet bij...) vraag: Wat is een GLCM en hoe wordt deze geconstrueerd? Toon met een numerisch voorbeeld. Hoe werken de gegeven texture measures en hoe kun je ze gebruiken om agriculture van urban te gaan onderscheiden. wat zijn de voordelen van het werken met texture, en wat zijn de moeilijkheden&lt;br /&gt;
** bijvraag: wanneer zou je opteren om directioneel i.p.v. omnidirectioneel te werken?&lt;br /&gt;
&lt;br /&gt;
== 2008 ==&lt;br /&gt;
&lt;br /&gt;
* Bespreek de opbouw van een GLCM? Waarvoor wordt deze textuurmaat gebruikt? Wat is het voordeel van 2e orde textuurmaten ten opzichte van eerste orde textuurmaten? Hoe verklaar je de nauwkeurigheid die bekomen wordt bij het toepassen van textuurmaten?&lt;br /&gt;
* Bespreek het VIS -model. Wat zijn de problemen die gerelateerd zijn met het gebruik van het VIS model en hoe zou je die problemen oplossen?&lt;br /&gt;
* Verklaar de werking van MLP. Wat zijn de voordelen t.o.v. maximum likelihood? Wat zijn de nadelen van MLP?&lt;br /&gt;
* Leg uit wat een semi-variogram komt doen bij remote sensing.&lt;br /&gt;
* Postclassificatie change detection.&lt;br /&gt;
* Emperical line calibration + vb.&lt;br /&gt;
* Leg het principe van lineaire unmixing uit. wat zijn de voorwaarden voor deze methode?&lt;br /&gt;
* Beschrijf de voor en nadelen van pixelgebaseerde classificatie tov object-oriented classificatie&lt;/div&gt;</summary>
		<author><name>Gaelle Fronhoffs</name></author>
	</entry>
	<entry>
		<id>http://wiki.atlasleuven.be/index.php?title=Advanced_Earth_Observation_Techniques&amp;diff=916</id>
		<title>Advanced Earth Observation Techniques</title>
		<link rel="alternate" type="text/html" href="http://wiki.atlasleuven.be/index.php?title=Advanced_Earth_Observation_Techniques&amp;diff=916"/>
		<updated>2026-01-24T21:03:18Z</updated>

		<summary type="html">&lt;p&gt;Gaelle Fronhoffs: /* Januay */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;{{Infobox|data2=Canters Frank|data3=Lectures|data4=Oral exam and PRAC report|data6=3|header1=Courses and exams|header5=Background|headerstyle=background:lightgrey|label2=Prof|label3=Courses|label4=Examination|label6=Credits|label7=When?|data7=1st semester|label8=ECTS|data8=[https://onderwijsaanbod.kuleuven.be/syllabi/e/G0I91BE.htm KU Leuven]&amp;lt;br&amp;gt;[https://caliweb.vub.be/index.php?page=course-offer&amp;amp;id=011568&amp;amp;anchor=1&amp;amp;target=pr&amp;amp;year=2324&amp;amp;language=en&amp;amp;output=html VUB]|title=Course Information}}&lt;br /&gt;
&lt;br /&gt;
&#039;&#039;[ORAL] Prof. Canters is very friendly during the exam. He lets you explain everything and doesn&#039;t really look at your notes. He asks many additional questions until you get stuck.&#039;&#039;&lt;br /&gt;
&lt;br /&gt;
== 2026 ==&lt;br /&gt;
&lt;br /&gt;
=== Januay ===&lt;br /&gt;
20/01/2026&lt;br /&gt;
&lt;br /&gt;
# Regression trees. &lt;br /&gt;
## Explain how a regression tree is built. &lt;br /&gt;
## Explain why it is different to Stepwise regression trees and how do they make decisions?&lt;br /&gt;
## Explain Priem et al. (2019). How did they use map-based and library-based for training data? Give advantages and disadvantages of both approaches.&lt;br /&gt;
# Texture &lt;br /&gt;
## Explain how a GLCM is constructed with a numerical example. &lt;br /&gt;
## Two second order texture meaures given (entropy and contrast). What texture measures do they represent?&lt;br /&gt;
## How can we use these measures to differentiate agricultural from urban land use?&lt;br /&gt;
# Region based approaches&lt;br /&gt;
## Explain what metrics you can use. &lt;br /&gt;
## Give an example of a metric in each category and explain how it can help in discerning different types of LU. &lt;br /&gt;
## What are the advantages of a region-based approach when compared to a kernel-based approach?&lt;br /&gt;
&lt;br /&gt;
== 2025 ==&lt;br /&gt;
Written exam due to miscommunications at the faculties&lt;br /&gt;
&lt;br /&gt;
=== January ===&lt;br /&gt;
11/01/2025&lt;br /&gt;
&lt;br /&gt;
# LSMA&lt;br /&gt;
## Explain linear spectral unmixing and the principles behind it.&lt;br /&gt;
## What is MESMA and why does it improve on LSMA?&lt;br /&gt;
## How does MESME select the most appropriate model to unmix a given pixel?&lt;br /&gt;
# Semivariogram&lt;br /&gt;
## Explain in detail how a semi-variogram is constructed and how you can use it in spectral mixture analysis.&lt;br /&gt;
## How can you use a semivariogram to construct GLCMs?&lt;br /&gt;
# Metrics used in LU classification from a LC classification. (Vanderhaegen en Canters, Walde)&lt;br /&gt;
## Explain, with a drawing, the principles of patch-based metrics, profile-based metrics and graph-based metrics in LU classification from LC within given regions.&lt;br /&gt;
## Give an example of a metric in each category and explain how it can help in discerning different types of LU.&lt;br /&gt;
## What are the advantages of a region-based approach when compared to a kernel-based approach?&lt;br /&gt;
&lt;br /&gt;
== 2023 ==&lt;br /&gt;
&#039;&#039;(oral again, 2 questions per person)&#039;&#039;&lt;br /&gt;
&lt;br /&gt;
=== Januari ===&lt;br /&gt;
&lt;br /&gt;
==== 16 januari ====&lt;br /&gt;
&lt;br /&gt;
# MESMA&lt;br /&gt;
#* Explain MESMA. Explain why this is better than linear SMA.&lt;br /&gt;
#* Explain the two approaches how Degerickx et al. (2019) used LiDAR data to improve the performance of MESMA.&lt;br /&gt;
#* Which one did improve MESMA the most?&lt;br /&gt;
# SPARK&lt;br /&gt;
#* Explain SPARK.&lt;br /&gt;
#* Explain the disadvantages and advantages towards region based.&lt;br /&gt;
&lt;br /&gt;
# Textures:&lt;br /&gt;
#* What is the difference between first order and second order texture measures?&lt;br /&gt;
#* Explain how a GLCM is constructed with a numerical example.&lt;br /&gt;
#* Two second order texture meaures given (entropy and contrast). What texture measures do they represent? How can we use these measures to differentiate agricultural from urban land use?&lt;br /&gt;
# Regression&lt;br /&gt;
#* Explain Priem et al. (2019). How did they use map-based and library-based for training data?&lt;br /&gt;
#* Give the advantages and disadvantages of both approaches.&lt;br /&gt;
&lt;br /&gt;
== 2022 ==&lt;br /&gt;
&lt;br /&gt;
# MESMA&lt;br /&gt;
#* Explain MESMA in detail.&lt;br /&gt;
#* Explain the two approaches how Degerickx et al. (2019) used LiDAR data to improve the performance of MESMA. (WASMA should not be explained) How does the accuracy change?&lt;br /&gt;
#* Degerickx et al. (2019) first performed their analysis on a simulated APEX image before doing this on the actual APEX image. Why did they do this? What are the advantages of first performing the analysis on a simulated APEX image?&lt;br /&gt;
# Textures&lt;br /&gt;
#* Work out a simple numerical example to explain how a grey-level co-occurence matrix is created.&lt;br /&gt;
#* Two second order texture measures formulas are given. What texture measures do they represent? How can we use these measures to differentiate agricultural from urban land use? (contrast &amp;amp; entropy)&lt;br /&gt;
#* Explain how we can determine the optimal window size when we want to classify our image based on second-order texture measures.&lt;br /&gt;
&lt;br /&gt;
== 2021 ==&lt;br /&gt;
&lt;br /&gt;
* Explain SPARK and OSPARK&lt;br /&gt;
* Explain how Degerickx et al. used Lidar in 2 ways fro improving the performance of MESMA (explanation of WASMA not needed)&lt;br /&gt;
* Explain regression trees. When do you use this?&lt;br /&gt;
&lt;br /&gt;
== 2019 ==&lt;br /&gt;
&lt;br /&gt;
* Explain LSMA, what are the assumptions? What is the differences with MESMA? What are the advantages?&lt;br /&gt;
* How did Canters and Priemer (2016) use LIDAR to improve their classification. What shadow masks were used?&lt;br /&gt;
* Explain the concept of regression trees (Example of the powerpoint is given). When do you expect this to work better than a normal regression approach?&lt;br /&gt;
* How are graphs used to infer Land Use from Land Cover? Explain how Walde et al. used graphs in their approach. Explain their case study, methodology and the most important conclusions.&lt;br /&gt;
&lt;br /&gt;
== 2017 ==&lt;br /&gt;
&lt;br /&gt;
* Song (given figure of Ikonos and Landsat ETM+), explain formulas and explain influence of the background reflectance of non-vegetation&lt;br /&gt;
* How can you account for uncertainty in the ground truth data? (expand diagonal OR fuzzy error matrix).&lt;br /&gt;
&lt;br /&gt;
== 2016 ==&lt;br /&gt;
&lt;br /&gt;
* Discuss the semi-variogram (with the use of the figure in the course). Wherefore is this used?&lt;br /&gt;
* What difficulties do you experience when using Landsat images to generate land cover classes (impervious, soil, vegetation). What does Wu (2004) uses? Discuss LMSA. How is the accuracy assessed  (Extra questions:  the difference between MAE and RMSE, what metric is highest?(RMSE looks at more outliers, What is the spatial resolution of the orthopotos? (3 cells)).&lt;br /&gt;
* Discuss the fuzzy error matrix. Why is it used. OR: How can you account for uncertainty in the ground trhuth data? (--&amp;gt; fuzzy matrices)&lt;br /&gt;
* Explain Song.  (dat mag adhv figuur slide 1.16) en leg uit hoe Song verklaart waarom de achtergrond reflectance een invloed heeft bij dit model&lt;br /&gt;
* Explain LSMA. Which assumptions are there made for LSMA.&lt;br /&gt;
* Explain the technique used by Van de Voorde et Al.. What are the main strengths and weaknesses of this technique.&lt;br /&gt;
* GLCM, explain it. Give an numerical example. There are formulas given of entropy and contrast (only formulas, no explanation), explain the formulas.&lt;br /&gt;
* Discuss paper of Canters. What method did he use?&lt;br /&gt;
&lt;br /&gt;
== 2015 ==&lt;br /&gt;
&lt;br /&gt;
* Song: bespreek (dat mag adhv figuur slide 1.16) en leg uit hoe Song verklaart waarom de achtergrond reflectance een invloed heeft bij dit model (of zoiets).&lt;br /&gt;
* Gegeven: 2 texture formules (het waren de &#039;contrast&#039; en &#039;entropy&#039; formules, maar dat stond er niet bij...) vraag: Wat is een GLCM en hoe wordt deze geconstrueerd? Toon met een numerisch voorbeeld. Wat is het voordeel van deze measures tov first order texture measures? Hoe werken de gegeven texture measures (leg uit mbv de formule) en hoe kun je ze gebruiken om agriculture van urban te gaan onderscheiden. Wat zijn de moeilijkheden bij het werken met texture?&lt;br /&gt;
* Bespreek de verschillende manieren om een medium resolution land cover map om te vormen naar een land use map. Wat zijn de voordelen en nadelen van kernel-based en region-based approaches?&lt;br /&gt;
&lt;br /&gt;
== 2014 ==&lt;br /&gt;
&lt;br /&gt;
* Leg SMA volledig uit: hoe werkt het, wat zijn de voordelen, wat zijn de veronderstellingen. Welke problemen kan je hebben met SMA als je werkt met Landsat? Wat is het VIS-model? Bespreek de methode van Lu en Weng (2004)&lt;br /&gt;
* Gegeven: 2 texture formules (het waren de &#039;contrast&#039; en &#039;entropy&#039; formules, maar dat stond er niet bij...) vraag: Wat is een GLCM en hoe wordt deze geconstrueerd? Toon met een numerisch voorbeeld. Hoe werken de gegeven texture measures en hoe kun je ze gebruiken om agriculture van urban te gaan onderscheiden. wat zijn de voordelen van het werken met texture, en wat zijn de moeilijkheden&lt;br /&gt;
** bijvraag: wanneer zou je opteren om directioneel i.p.v. omnidirectioneel te werken?&lt;br /&gt;
&lt;br /&gt;
== 2008 ==&lt;br /&gt;
&lt;br /&gt;
* Bespreek de opbouw van een GLCM? Waarvoor wordt deze textuurmaat gebruikt? Wat is het voordeel van 2e orde textuurmaten ten opzichte van eerste orde textuurmaten? Hoe verklaar je de nauwkeurigheid die bekomen wordt bij het toepassen van textuurmaten?&lt;br /&gt;
* Bespreek het VIS -model. Wat zijn de problemen die gerelateerd zijn met het gebruik van het VIS model en hoe zou je die problemen oplossen?&lt;br /&gt;
* Verklaar de werking van MLP. Wat zijn de voordelen t.o.v. maximum likelihood? Wat zijn de nadelen van MLP?&lt;br /&gt;
* Leg uit wat een semi-variogram komt doen bij remote sensing.&lt;br /&gt;
* Postclassificatie change detection.&lt;br /&gt;
* Emperical line calibration + vb.&lt;br /&gt;
* Leg het principe van lineaire unmixing uit. wat zijn de voorwaarden voor deze methode?&lt;br /&gt;
* Beschrijf de voor en nadelen van pixelgebaseerde classificatie tov object-oriented classificatie&lt;/div&gt;</summary>
		<author><name>Gaelle Fronhoffs</name></author>
	</entry>
	<entry>
		<id>http://wiki.atlasleuven.be/index.php?title=Advanced_Earth_Observation_Techniques&amp;diff=915</id>
		<title>Advanced Earth Observation Techniques</title>
		<link rel="alternate" type="text/html" href="http://wiki.atlasleuven.be/index.php?title=Advanced_Earth_Observation_Techniques&amp;diff=915"/>
		<updated>2026-01-24T21:01:02Z</updated>

		<summary type="html">&lt;p&gt;Gaelle Fronhoffs: &lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;{{Infobox|data2=Canters Frank|data3=Lectures|data4=Oral exam and PRAC report|data6=3|header1=Courses and exams|header5=Background|headerstyle=background:lightgrey|label2=Prof|label3=Courses|label4=Examination|label6=Credits|label7=When?|data7=1st semester|label8=ECTS|data8=[https://onderwijsaanbod.kuleuven.be/syllabi/e/G0I91BE.htm KU Leuven]&amp;lt;br&amp;gt;[https://caliweb.vub.be/index.php?page=course-offer&amp;amp;id=011568&amp;amp;anchor=1&amp;amp;target=pr&amp;amp;year=2324&amp;amp;language=en&amp;amp;output=html VUB]|title=Course Information}}&lt;br /&gt;
&lt;br /&gt;
&#039;&#039;[ORAL] Prof. Canters is very friendly during the exam. He lets you explain everything and doesn&#039;t really look at your notes. He asks many additional questions until you get stuck.&#039;&#039;&lt;br /&gt;
&lt;br /&gt;
== 2026 ==&lt;br /&gt;
&lt;br /&gt;
=== Januay ===&lt;br /&gt;
20/01/2026&lt;br /&gt;
&lt;br /&gt;
# Regression trees. explain why it is different to Stepwise regression trees and how do they make decisions? Explain Priem et al. (2019). How did they use map-based and library-based for training data? Give advantages and disadvantages of both approaches.&lt;br /&gt;
# Explain how a GLCM is constructed with a numerical example. Two second order texture meaures given (entropy and contrast). What texture measures do they represent? How can we use these measures to differentiate agricultural from urban land use?&lt;br /&gt;
# Region based approaches, explain. Give an example of a metric in each category and explain how it can help in discerning different types of LU. What are the advantages of a region-based approach when compared to a kernel-based approach?&lt;br /&gt;
&lt;br /&gt;
== 2025 ==&lt;br /&gt;
Written exam due to miscommunications at the faculties&lt;br /&gt;
&lt;br /&gt;
=== January ===&lt;br /&gt;
11/01/2025&lt;br /&gt;
&lt;br /&gt;
# LSMA&lt;br /&gt;
## Explain linear spectral unmixing and the principles behind it.&lt;br /&gt;
## What is MESMA and why does it improve on LSMA?&lt;br /&gt;
## How does MESME select the most appropriate model to unmix a given pixel?&lt;br /&gt;
# Semivariogram&lt;br /&gt;
## Explain in detail how a semi-variogram is constructed and how you can use it in spectral mixture analysis.&lt;br /&gt;
## How can you use a semivariogram to construct GLCMs?&lt;br /&gt;
# Metrics used in LU classification from a LC classification. (Vanderhaegen en Canters, Walde)&lt;br /&gt;
## Explain, with a drawing, the principles of patch-based metrics, profile-based metrics and graph-based metrics in LU classification from LC within given regions.&lt;br /&gt;
## Give an example of a metric in each category and explain how it can help in discerning different types of LU.&lt;br /&gt;
## What are the advantages of a region-based approach when compared to a kernel-based approach?&lt;br /&gt;
&lt;br /&gt;
== 2023 ==&lt;br /&gt;
&#039;&#039;(oral again, 2 questions per person)&#039;&#039;&lt;br /&gt;
&lt;br /&gt;
=== Januari ===&lt;br /&gt;
&lt;br /&gt;
==== 16 januari ====&lt;br /&gt;
&lt;br /&gt;
# MESMA&lt;br /&gt;
#* Explain MESMA. Explain why this is better than linear SMA.&lt;br /&gt;
#* Explain the two approaches how Degerickx et al. (2019) used LiDAR data to improve the performance of MESMA.&lt;br /&gt;
#* Which one did improve MESMA the most?&lt;br /&gt;
# SPARK&lt;br /&gt;
#* Explain SPARK.&lt;br /&gt;
#* Explain the disadvantages and advantages towards region based.&lt;br /&gt;
&lt;br /&gt;
# Textures:&lt;br /&gt;
#* What is the difference between first order and second order texture measures?&lt;br /&gt;
#* Explain how a GLCM is constructed with a numerical example.&lt;br /&gt;
#* Two second order texture meaures given (entropy and contrast). What texture measures do they represent? How can we use these measures to differentiate agricultural from urban land use?&lt;br /&gt;
# Regression&lt;br /&gt;
#* Explain Priem et al. (2019). How did they use map-based and library-based for training data?&lt;br /&gt;
#* Give the advantages and disadvantages of both approaches.&lt;br /&gt;
&lt;br /&gt;
== 2022 ==&lt;br /&gt;
&lt;br /&gt;
# MESMA&lt;br /&gt;
#* Explain MESMA in detail.&lt;br /&gt;
#* Explain the two approaches how Degerickx et al. (2019) used LiDAR data to improve the performance of MESMA. (WASMA should not be explained) How does the accuracy change?&lt;br /&gt;
#* Degerickx et al. (2019) first performed their analysis on a simulated APEX image before doing this on the actual APEX image. Why did they do this? What are the advantages of first performing the analysis on a simulated APEX image?&lt;br /&gt;
# Textures&lt;br /&gt;
#* Work out a simple numerical example to explain how a grey-level co-occurence matrix is created.&lt;br /&gt;
#* Two second order texture measures formulas are given. What texture measures do they represent? How can we use these measures to differentiate agricultural from urban land use? (contrast &amp;amp; entropy)&lt;br /&gt;
#* Explain how we can determine the optimal window size when we want to classify our image based on second-order texture measures.&lt;br /&gt;
&lt;br /&gt;
== 2021 ==&lt;br /&gt;
&lt;br /&gt;
* Explain SPARK and OSPARK&lt;br /&gt;
* Explain how Degerickx et al. used Lidar in 2 ways fro improving the performance of MESMA (explanation of WASMA not needed)&lt;br /&gt;
* Explain regression trees. When do you use this?&lt;br /&gt;
&lt;br /&gt;
== 2019 ==&lt;br /&gt;
&lt;br /&gt;
* Explain LSMA, what are the assumptions? What is the differences with MESMA? What are the advantages?&lt;br /&gt;
* How did Canters and Priemer (2016) use LIDAR to improve their classification. What shadow masks were used?&lt;br /&gt;
* Explain the concept of regression trees (Example of the powerpoint is given). When do you expect this to work better than a normal regression approach?&lt;br /&gt;
* How are graphs used to infer Land Use from Land Cover? Explain how Walde et al. used graphs in their approach. Explain their case study, methodology and the most important conclusions.&lt;br /&gt;
&lt;br /&gt;
== 2017 ==&lt;br /&gt;
&lt;br /&gt;
* Song (given figure of Ikonos and Landsat ETM+), explain formulas and explain influence of the background reflectance of non-vegetation&lt;br /&gt;
* How can you account for uncertainty in the ground truth data? (expand diagonal OR fuzzy error matrix).&lt;br /&gt;
&lt;br /&gt;
== 2016 ==&lt;br /&gt;
&lt;br /&gt;
* Discuss the semi-variogram (with the use of the figure in the course). Wherefore is this used?&lt;br /&gt;
* What difficulties do you experience when using Landsat images to generate land cover classes (impervious, soil, vegetation). What does Wu (2004) uses? Discuss LMSA. How is the accuracy assessed  (Extra questions:  the difference between MAE and RMSE, what metric is highest?(RMSE looks at more outliers, What is the spatial resolution of the orthopotos? (3 cells)).&lt;br /&gt;
* Discuss the fuzzy error matrix. Why is it used. OR: How can you account for uncertainty in the ground trhuth data? (--&amp;gt; fuzzy matrices)&lt;br /&gt;
* Explain Song.  (dat mag adhv figuur slide 1.16) en leg uit hoe Song verklaart waarom de achtergrond reflectance een invloed heeft bij dit model&lt;br /&gt;
* Explain LSMA. Which assumptions are there made for LSMA.&lt;br /&gt;
* Explain the technique used by Van de Voorde et Al.. What are the main strengths and weaknesses of this technique.&lt;br /&gt;
* GLCM, explain it. Give an numerical example. There are formulas given of entropy and contrast (only formulas, no explanation), explain the formulas.&lt;br /&gt;
* Discuss paper of Canters. What method did he use?&lt;br /&gt;
&lt;br /&gt;
== 2015 ==&lt;br /&gt;
&lt;br /&gt;
* Song: bespreek (dat mag adhv figuur slide 1.16) en leg uit hoe Song verklaart waarom de achtergrond reflectance een invloed heeft bij dit model (of zoiets).&lt;br /&gt;
* Gegeven: 2 texture formules (het waren de &#039;contrast&#039; en &#039;entropy&#039; formules, maar dat stond er niet bij...) vraag: Wat is een GLCM en hoe wordt deze geconstrueerd? Toon met een numerisch voorbeeld. Wat is het voordeel van deze measures tov first order texture measures? Hoe werken de gegeven texture measures (leg uit mbv de formule) en hoe kun je ze gebruiken om agriculture van urban te gaan onderscheiden. Wat zijn de moeilijkheden bij het werken met texture?&lt;br /&gt;
* Bespreek de verschillende manieren om een medium resolution land cover map om te vormen naar een land use map. Wat zijn de voordelen en nadelen van kernel-based en region-based approaches?&lt;br /&gt;
&lt;br /&gt;
== 2014 ==&lt;br /&gt;
&lt;br /&gt;
* Leg SMA volledig uit: hoe werkt het, wat zijn de voordelen, wat zijn de veronderstellingen. Welke problemen kan je hebben met SMA als je werkt met Landsat? Wat is het VIS-model? Bespreek de methode van Lu en Weng (2004)&lt;br /&gt;
* Gegeven: 2 texture formules (het waren de &#039;contrast&#039; en &#039;entropy&#039; formules, maar dat stond er niet bij...) vraag: Wat is een GLCM en hoe wordt deze geconstrueerd? Toon met een numerisch voorbeeld. Hoe werken de gegeven texture measures en hoe kun je ze gebruiken om agriculture van urban te gaan onderscheiden. wat zijn de voordelen van het werken met texture, en wat zijn de moeilijkheden&lt;br /&gt;
** bijvraag: wanneer zou je opteren om directioneel i.p.v. omnidirectioneel te werken?&lt;br /&gt;
&lt;br /&gt;
== 2008 ==&lt;br /&gt;
&lt;br /&gt;
* Bespreek de opbouw van een GLCM? Waarvoor wordt deze textuurmaat gebruikt? Wat is het voordeel van 2e orde textuurmaten ten opzichte van eerste orde textuurmaten? Hoe verklaar je de nauwkeurigheid die bekomen wordt bij het toepassen van textuurmaten?&lt;br /&gt;
* Bespreek het VIS -model. Wat zijn de problemen die gerelateerd zijn met het gebruik van het VIS model en hoe zou je die problemen oplossen?&lt;br /&gt;
* Verklaar de werking van MLP. Wat zijn de voordelen t.o.v. maximum likelihood? Wat zijn de nadelen van MLP?&lt;br /&gt;
* Leg uit wat een semi-variogram komt doen bij remote sensing.&lt;br /&gt;
* Postclassificatie change detection.&lt;br /&gt;
* Emperical line calibration + vb.&lt;br /&gt;
* Leg het principe van lineaire unmixing uit. wat zijn de voorwaarden voor deze methode?&lt;br /&gt;
* Beschrijf de voor en nadelen van pixelgebaseerde classificatie tov object-oriented classificatie&lt;/div&gt;</summary>
		<author><name>Gaelle Fronhoffs</name></author>
	</entry>
	<entry>
		<id>http://wiki.atlasleuven.be/index.php?title=Introduction_to_Remote_Sensing&amp;diff=891</id>
		<title>Introduction to Remote Sensing</title>
		<link rel="alternate" type="text/html" href="http://wiki.atlasleuven.be/index.php?title=Introduction_to_Remote_Sensing&amp;diff=891"/>
		<updated>2026-01-09T08:06:10Z</updated>

		<summary type="html">&lt;p&gt;Gaelle Fronhoffs: /* 2026 */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;== 2026 ==&lt;br /&gt;
&lt;br /&gt;
=== January ===&lt;br /&gt;
&lt;br /&gt;
# Explain NDVI. Why can it be used to map biomes. Which sensors can be used to map this biomes (spectral + spatial characteristics)? What is off-nadir viewing. What are the advantages and the disadvantages?&lt;br /&gt;
# Explain descision trees. Explain the principle of inductive learning and how automation via inductive learning improves descision trees. Explain different criteria to split nodes. How are these criteria defined?&lt;br /&gt;
# What is Multidate composite image change detection? Explain the difference between supervised and unsupervised.&lt;br /&gt;
{{Infobox|data2=Canters Frank|data3=Lectures|data4=50% on written exam; 50% on reports|data6=3|header1=Courses and exams|header5=Background|headerstyle=background:lightgrey|label2=Prof|label3=Courses|label4=Examination|label6=Credits|label7=When?|data7=1st semester|label8=ECTS|data8=[https://caliweb.vub.be/?page=course-offer&amp;amp;id=006507&amp;amp;anchor=1&amp;amp;target=pr&amp;amp;year=2324&amp;amp;language=en&amp;amp;output=html Link]|title=Course Information}}&lt;br /&gt;
&lt;br /&gt;
== 2025 ==&lt;br /&gt;
&lt;br /&gt;
=== January ===&lt;br /&gt;
&lt;br /&gt;
# Radiometric calibration&lt;br /&gt;
## What is a spectralon, and how is it used to perform in-field measurements?&lt;br /&gt;
## Empirical line method: explain the principle in image calibration&lt;br /&gt;
## What are Pseudo-Invariant Features (PIFs)? What kind of characteristics should they have?&lt;br /&gt;
# MLP&lt;br /&gt;
## Explain the structure of and training mechanisms in MLP, in detail&lt;br /&gt;
## What are some advantages and disadvantages in using MLP when compared to ML classification?&lt;br /&gt;
## What is &amp;quot;overtraining&amp;quot;? Explain how you can counter this in MLP classification&lt;br /&gt;
# Post-classification change detection&lt;br /&gt;
## Explain the three methods of post-classification change detection&lt;br /&gt;
## Advantages/disadvantages of each&lt;br /&gt;
## Explain what influences the accuracies of each method&lt;br /&gt;
# No how are you :(&lt;br /&gt;
&lt;br /&gt;
== 2024 ==&lt;br /&gt;
=== January ===&lt;br /&gt;
&lt;br /&gt;
# Explain NDVI. Why can it be used to map biomes. Which sensors can be used to map this biomes (spectral + spatial characteristics)? &lt;br /&gt;
# What is off-nadir viewing. What are the advantages and the disadvantages?&lt;br /&gt;
# Explain Multiple Layer Perceptron in detail. What are the (dis)advantages compared to Maximum Likelihood? What is &#039;overtraining&#039; and how would you solve this for a MLP?&lt;br /&gt;
# What is Multidate composite image change detection? Explain the difference between supervised and unsupervised.&lt;br /&gt;
# How are you?&lt;br /&gt;
&lt;br /&gt;
== 2023 ==&lt;br /&gt;
&lt;br /&gt;
=== January ===&lt;br /&gt;
&lt;br /&gt;
==== 12/01/2023 ====&lt;br /&gt;
&lt;br /&gt;
# Explain the Radiometric Empirical line calibration method. When is this method used and when not? Explain the importance of PIFs (Pseudo-Invariant Features) in this method.&lt;br /&gt;
# Explain Maximum Likelihood classification. (Principles, when to use, ...) Use these figures from a case study to explain the pitfalls of the methods (see Figure from 2018-2019).&lt;br /&gt;
# Explain all post-classification change detection methods. What are the assumptions you make for each method?&lt;br /&gt;
&lt;br /&gt;
==== 13/01/2023 ====&lt;br /&gt;
&lt;br /&gt;
# Explain MLP. What are the (dis)advantages in comparison with a maximum likelihood classifier? How can you avoid overtraining? + advantages and disadvanteges.&lt;br /&gt;
# Explain NDVI and how this measure can be used to map biomes on a global scale. Give examples of sensors that can be used to measure the NDVI globally on a daily basis (give spatial and spectral characteristics).&lt;br /&gt;
# Explain all post-classification change detection methods. What are the assumptions you make for each method? Is atmospheric/radiometric correction required for these methods? Why (not)?&lt;br /&gt;
&lt;br /&gt;
== 2022 ==&lt;br /&gt;
&lt;br /&gt;
# Explain the Radiometric Empirical line calibration method. When is this method used and when not? Explain the importance of PIFs (Pseudo-Invariant Features) in this method.&lt;br /&gt;
# Explain descision trees. Explain the principle of inductive learning and how automation via inductive learning improves descision trees. Explain different criteria to split nodes. How are these criteria defined?&lt;br /&gt;
# Explain the Random Forest algorithm. Why is RF usually better than a single descision tree?&lt;br /&gt;
# Explain all post-classification change detection methods. What are the assumptions you make for each method? Is atmospheric/radiometric correction required for these methods? Why (not)?&lt;br /&gt;
&lt;br /&gt;
== 2021 ==&lt;br /&gt;
&lt;br /&gt;
# Explain Maximum Likelihood classification. (Principles, when to use, ...) Use these figures from a case study to explain the pitfalls of the methods (see Figure from 2018-2019).&lt;br /&gt;
# Explain NDVI and how this measure can be used to map biomes on a global scale. Give examples of sensors that can be used to measure the NDVI globally on a daily basis (give spatial and spectral characteristics).&lt;br /&gt;
# Explain all post-classification change detection methods. What are the assumptions you make for each method? Is atmospheric/radiometric correction required for these methods? Why (not)?&lt;br /&gt;
&lt;br /&gt;
== 2019 ==&lt;br /&gt;
&amp;lt;u&amp;gt;Series 3:&amp;lt;/u&amp;gt;&lt;br /&gt;
&lt;br /&gt;
# Explain Maximum Likelihood classification. (Principles, when to use, ...) Use these figures from a case study to explain the pitfalls of the methods.&lt;br /&gt;
# What are along-track off-nadir and off-track off-nadir image acquisition? Give applications and (dis)advantages for both.&lt;br /&gt;
&lt;br /&gt;
== 2018 ==&lt;br /&gt;
&amp;lt;u&amp;gt;Series 2:&amp;lt;/u&amp;gt;&lt;br /&gt;
&lt;br /&gt;
# Explain the different methods of post-classification. Compare the techniques and give their advantages/disadvantages.&lt;br /&gt;
# Explain how a confusion matrix is constucted. Give all the validations that you can calculate based on this confusion matrix. An image is classified by two different classifiers. How can I whether one classifier is significantly better than the other one?&lt;br /&gt;
&lt;br /&gt;
Additional questions:&lt;br /&gt;
&lt;br /&gt;
* Does your data require radiometric correction for image differencing? Why haven&#039;t we done that in the practicals? What would be the influence on the Gaussian shape of these values?&lt;br /&gt;
* What is the assumption you need to make for the cross correlation change detection method to work well?&lt;br /&gt;
* What is the range of values for the Kappa index, what does a Kappa of 0 mean?&lt;br /&gt;
* When will there be a large difference between PCC and Kappa?&lt;br /&gt;
&lt;br /&gt;
== 2017 ==&lt;br /&gt;
&lt;br /&gt;
# How monitor vegetation on global scale.&lt;br /&gt;
# Explain decision tree&lt;br /&gt;
&lt;br /&gt;
# MLP&lt;br /&gt;
# Emperical line calibration&lt;br /&gt;
&lt;br /&gt;
== 2016 ==&lt;br /&gt;
&amp;lt;u&amp;gt;Series 2:&amp;lt;/u&amp;gt;&lt;br /&gt;
&lt;br /&gt;
# Explain the different methods of post-classification. Compare the techniques and give their advantages/disadvantages.&lt;br /&gt;
# Explain how a confusion matrix is constucted. Give all the validations that you can calculate based on this confusion matrix. An image is classified by two different classifiers. How can I whether one classifier is significantly better than the other one?&lt;br /&gt;
&lt;br /&gt;
== 2015 ==&lt;br /&gt;
&lt;br /&gt;
=== January ===&lt;br /&gt;
&lt;br /&gt;
==== 26/01/2015 ====&lt;br /&gt;
&lt;br /&gt;
# Wat zijn off-track en along-track image acquisition? Geef aan bij welke toepassingen deze best gebruikt worden. Wat zijn de nadelen van off-nadir image acquisition?&lt;br /&gt;
# Beschrijf de werking van een MLP? Wat zijn de voordelen en nadelen vergeleken met een maxlike classifier? Hoe kan je overtraining vermijden?&lt;br /&gt;
# Geef alle methoden van postclassificatie change detection en hun voor- en nadelen.&lt;br /&gt;
&lt;br /&gt;
== 2014 ==&lt;br /&gt;
&lt;br /&gt;
=== January ===&lt;br /&gt;
&lt;br /&gt;
==== 20/01/2014 ====&lt;br /&gt;
&amp;lt;u&amp;gt;Reeks 1:&amp;lt;/u&amp;gt;&lt;br /&gt;
&lt;br /&gt;
# Maximumlikelihood classificatie en de a priori probabilities uitleggen + 2 figuren (slide 2.16 en 2.17) onderaan gegeven waar hij dan wat bijvragen over stelde&lt;br /&gt;
# Wat zijn &amp;quot;pointable&amp;quot; sensors? Geef voorbeelden van deze sensoren. Voordelen en nadelen? Wat is het meest efficiënte gebruik hiervan?&lt;br /&gt;
&lt;br /&gt;
&amp;lt;u&amp;gt;Reeks 2:&amp;lt;/u&amp;gt;&lt;br /&gt;
&lt;br /&gt;
# Bespreek alle mogelijke methoden van post-classificatie change detection&lt;br /&gt;
# Leg alle soorten resolutie uit en mogelijke trade-offs.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;u&amp;gt;Reeks 3:&amp;lt;/u&amp;gt;&lt;br /&gt;
&lt;br /&gt;
# Beschrijf de werking van een MLP? Wat zijn de voordelen en nadelen vergeleken met een maxlike classifier? Hoe kan je overtraining vermijden?&lt;br /&gt;
# Leg empirical line calibration uit. Hoe zou je dit uitvoeren, wat voor data heb je hier voor nodig? Is dit noodzakelijk voor elke analyse van een satelliet beeld? (bonus: toepassing uitleggen bij land cover CHANGE detection)&lt;br /&gt;
&lt;br /&gt;
== 2013 ==&lt;br /&gt;
&lt;br /&gt;
# Maximumlikelihood classificatie en de a priori probabilities uitleggen + 2 figuren (slide 2.16 en 2.17) onderaan gegeven waar hij dan wat bijvragen over stelde&lt;br /&gt;
# Wat zijn &amp;quot;pointable&amp;quot; sensors? Geef voorbeelden van deze sensoren. Voordelen en nadelen? Wat is het meest efficiënte gebruik hiervan?&lt;br /&gt;
&lt;br /&gt;
# verschillende soorten resolutie uitleggen&lt;br /&gt;
# post-classificatie methodes voor change detectie uitleggen&lt;br /&gt;
&lt;br /&gt;
# Geef alle methoden van postclassificatie change detection en hun voor- en nadelen.&lt;br /&gt;
# Bespreek spectrale, temporale, spatiale en radiometrische resolutie. Geef telkens voorbeelden van hoge en lage resolutie. Leg de trade-off tussen de verschillende resoluties uit en geef voorbeelden van wanneer welke combinaties nuttig zijn.&lt;br /&gt;
&lt;br /&gt;
# Bespreek de maximum likelihood classifier. Leg a priori probability uit en bespreek de figuren op slide 2.16 en 2.17.&lt;br /&gt;
# Wat zijn &#039;pointable sensors&#039;? Geef enkele voorbeelden van zulke sensoren? Wat zijn de voordelen en nadelen? Voor welke toepassingen kunnen ze gebruikt worden?&lt;br /&gt;
&lt;br /&gt;
# Bespreek Multi-Layer Perceptron. Hoe vermijd je overtraining. Vergelijk met maximum likelihood.&lt;br /&gt;
# Bespreek de empirische lijn methode. Is calibratie altijd noodzakelijk?&lt;br /&gt;
&lt;br /&gt;
# Het gebruik van de valse kleurencomposiet en de PCA bij kwalitatieve change detection uitleggen.&lt;br /&gt;
# Bespreek de Decision tree classifier. Wat zijn de voordelen ten opzichte van de maxlike? (Bespreek hierbij zeker uw inductive learning system uitgebreid!&lt;br /&gt;
&lt;br /&gt;
# Hoe bepaalt ge de top van uw piramide bij inductive learning? Wat is de evaluatiemethode/criteria van uw opsplitsing?&lt;br /&gt;
# Op welke basis wordt uw inductive learning getoetst?&lt;br /&gt;
&lt;br /&gt;
# Geef een eigen benaming voor de beelden van stable components en variable components (met verschilbeelden en veranderingbeelden ging hij wel akkoord)&lt;br /&gt;
# Op aangeven van eigen redenering: Wat is het specifieke voordeel en dus verschil tussen a-priori stratificatie bij maxlike en hierarchy inwerking door inductive learning?&lt;br /&gt;
&lt;br /&gt;
== 2012 ==&lt;br /&gt;
&lt;br /&gt;
# wat zijn &amp;quot;pointable&amp;quot; sensors? geeft voorbeelden van deze sensoren. voordelen en nadelen? wat is het meest efficiënte gebruik hiervan?&lt;br /&gt;
# werking MLP uitleggen. voordelen tov. MaxLike? wat is overtraining en hoe dit vermijden?&lt;br /&gt;
# geeft de verschillende soorten van post-classificatie om aan change detection te doen. Vermeld bij elke methode de voor-en nadelen.&lt;br /&gt;
&lt;br /&gt;
# Uitleggen wat spectrale,spatial,temporele en radiometrische resolutie is. En de trade-offs bij sensoren.&lt;br /&gt;
# Maximumlikelihood classifier gedetailleerd uitleggen. De a priori probabilities uitleggen. Plus de figuren op slde 2.16 en 2.17.&lt;br /&gt;
# Het gebruik van de valse kleurencomposiet en de PCA bij kwalitatieve change detection uitleggen.&lt;br /&gt;
&lt;br /&gt;
== 2011 ==&lt;br /&gt;
&amp;lt;u&amp;gt;Reeks 1:&amp;lt;/u&amp;gt;&lt;br /&gt;
&lt;br /&gt;
# Bespreek MLP. (werking, voor- en nadelen tov MLC, overtraining)&lt;br /&gt;
# Bespreek de empirical line method. Is die correctie altijd noodzakelijk?&lt;br /&gt;
&lt;br /&gt;
&amp;lt;u&amp;gt;Reeks 3:&amp;lt;/u&amp;gt;&lt;br /&gt;
&lt;br /&gt;
# Hoe werkt de Maximum Likelihood Classifier? Wat zijn de vereisten voor een Maximum Likelihood Classifier? Wat zijn a priori probabilities? Hoe moet je die bepalen? Wat zijn de voor- en nadelen ervan? En dan stonden er ook die figuurkes op slides 2.16 en 2.17 bij (er stond niet in de vraag dat ge die figuren moest uitleggen, maar tijdens het examen vroeg hij daar natuurlijk wel zeer uitgebreid achter).&lt;br /&gt;
# Wat zijn &#039;pointable sensors&#039;? Geef enkele voorbeelden van zulke sensoren? Wat zijn de voordelen en nadelen? Voor welke toepassingen kunnen ze gebruikt worden?&lt;br /&gt;
&lt;br /&gt;
&amp;lt;u&amp;gt;Reeks 4:&amp;lt;/u&amp;gt;&lt;br /&gt;
&lt;br /&gt;
# Bespreek alle types van postclassification change detection, geef ook telkens de voor en nadelen&lt;br /&gt;
# leg uit: spectrale, spatiale, temporele, radiometrische resolutie. geef telkens voordelen van hoge resoluties, leg trade-off uit en geef voorbeelden van wanneer welke combinaties nuttig zijn&lt;br /&gt;
&lt;br /&gt;
+ hele hoop bijvragen&lt;br /&gt;
&lt;br /&gt;
&amp;lt;u&amp;gt;Reeks 5:&amp;lt;/u&amp;gt;&lt;br /&gt;
&lt;br /&gt;
# Bespreek de Decision tree classifier. Wat zijn de voordelen ten opzichte van de maxlike? (Bespreek hierbij zeker uw inductive learning system uitgebreid!)&lt;br /&gt;
# Hoe dragen a) false colour composite images en b) PCA bij tot een qualitatieve change detection?&lt;br /&gt;
&lt;br /&gt;
4 bijvragen:&lt;br /&gt;
&lt;br /&gt;
* Hoe bepaalt ge de top van uw piramide bij inductive learning? Wat is de evaluatiemethode/criteria van uw opsplitsing?&lt;br /&gt;
* Op welke basis wordt uw inductive learning getoetst?&lt;br /&gt;
* Geef een eigen benaming voor de beelden van stable components en variable components (met verschilbeelden en veranderingbeelden ging hij wel akkoord)&lt;br /&gt;
* Op aangeven van eigen redenering: Wat is het specifieke voordeel en dus verschil tussen a-priori stratificatie bij maxlike en hierarchy inwerking door inductive learning?&lt;br /&gt;
&lt;br /&gt;
== 2010 ==&lt;br /&gt;
&amp;lt;u&amp;gt;Reeks 1&amp;lt;/u&amp;gt;&lt;br /&gt;
&lt;br /&gt;
# MLP: hoe werkt het, wat zijn de voordelen tov ML en wat zijn er nadelen? leg overtraining uit en hoe los je het op?&lt;br /&gt;
# keuzetekst uitleggen, idem zoals kasper: doelstelling, methodologie, resultaten, conclusie&lt;br /&gt;
&lt;br /&gt;
(examenvragen van persoon na mij):&lt;br /&gt;
&lt;br /&gt;
# pixelbased vs objectbased (voor - en nadelen)&lt;br /&gt;
&lt;br /&gt;
&amp;lt;u&amp;gt;Reeks 2&amp;lt;/u&amp;gt;&lt;br /&gt;
&lt;br /&gt;
# Semi-variogram uitleggen + verband met remote sensing (ook de figuur van no, low density en high density vegetation)&lt;br /&gt;
# Alles (doel, methodologie, resultaten en discussie) van keuzepaper uitleggen.&lt;/div&gt;</summary>
		<author><name>Gaelle Fronhoffs</name></author>
	</entry>
</feed>