IOTA2: large scale land cover mapping operational chain
This is a modal window.
The media could not be loaded, either because the server or network failed or because the format is not supported.
Formal Metadata
Title |
| |
Title of Series | ||
Number of Parts | 351 | |
Author | ||
Contributors | ||
License | CC Attribution 3.0 Unported: You are free to use, adapt and copy, distribute and transmit the work or content in adapted or unchanged form for any legal purpose as long as the work is attributed to the author in the manner specified by the author or licensor. | |
Identifiers | 10.5446/69155 (DOI) | |
Publisher | ||
Release Date | ||
Language | ||
Production Year | 2022 |
Content Metadata
Subject Area | ||
Genre | ||
Abstract |
| |
Keywords |
FOSS4G Firenze 202289 / 351
1
7
13
22
25
31
33
36
39
41
43
44
46
52
53
55
58
59
60
76
80
93
98
104
108
127
128
133
135
141
142
143
150
151
168
173
176
178
190
196
200
201
202
204
211
219
225
226
236
242
251
258
263
270
284
285
292
00:00
Scale (map)Local GroupTexture mappingGroup actionSoftware engineeringPresentation of a groupGoodness of fitComputer animation
00:20
Local GroupPresentation of a groupStack (abstract data type)Open sourceProduct (business)Series (mathematics)OpticsAreaProcess (computing)SupercomputerLocal ringMultiplicationSocial classIntegrated development environmentData managementInterpolationAxonometric projectionUnified threat managementPoint cloudPixelContext awarenessComputer-generated imageryObject (grammar)Mathematical analysisSupport vector machineoutputRandom numberForestCovering spaceAreaMultiplicationOpticsOpen sourceNeuroinformatikAxiom of choiceMehrprozessorsystemVirtual machineInterpolationoutputPoint cloudProduct (business)Time seriesScaling (geometry)Social classBilderkennungForestMedical imagingProcess (computing)Software frameworkElectric generatorClosed setGoodness of fitReference dataWindowTesselationAddress spaceThread (computing)Projective planeCompilation albumCuboidTurm von HanoiDifferent (Kate Ryan album)Context awarenessObject (grammar)Support vector machineSoftware development kitComputer animation
Transcript: English(auto-generated)
00:01
Good afternoon, everyone. I am Julien Osman. I work as a software engineer at CS group company in France. Artur Vincent was not able to make it today, so he asked me to do the presentation for him. And I will present YoTattoo.
00:20
If you want to generate land cover maps on the large scale using machine learning, YoTattoo is a tool you need. It can take as input some optical images or SAR images.
00:41
It works with time series on very large areas and it's able to work with different geological areas. It's it relies on the Orpho toolbox,
01:02
multiprocessing and multithreading capabilities, and it can be distributed on multiple computing nodes through Dask. It's already used on production to produce the Ozo project, which is a land cover map of France
01:21
that's produced every year. It contains 23 classes. And also, it's an open source project, so you can check it out at this address. What do I mean when I say large scale? Well, first it works with
01:43
heterogeneous data, so you can work with multiple kind of sensors on multiple dates, and it will deal with the presence of clouds. It's able to work with multiple geological areas, as I said before, so for example in France,
02:03
you don't have the same climate close to the earth land or in the middle of France, so you can specify it as an input, and it will take it into account. Also, it will do some temporal interpolation to smooth the data, remove the clouds, and
02:23
also to homogenize the dates since you can put images of any date. So the temporal interpolation will deal with different dates. As I said, it's a framework for machine learning, so you will want to do some classification with it, and
02:45
you have multiple choice of classifier. I said earlier that it relies on the Orpho toolbox, so all the classifier in the Orpho toolbox are available, like the random forest or the SVM, but you can also use a classifier from the
03:05
Cyk-Hitteram or PyTorch if you want to do some deep learning. You can also do some object-based image analysis using some segmentation as input, and it also has a capability of auto-context to work with
03:24
SuperPixels and do some recurrent processing. So to conclude, Yota 2 will help you to do some long cover maps at large scale, so don't use it if you just have one tile. I mean, it's really large scale over countries, and
03:45
you will need to give as input some good quality reference data for your learning step. It doesn't work with Windows, only with Linux, but it's easy to install because we provide
04:01
a Conda package. You will find the documentation at this address, and you are welcome to contribute. Thank you.