SlideShare una empresa de Scribd logo
1 de 22
Descargar para leer sin conexión
Team 3. Open Land Use 4 Africa
2
Background

Land use maps help authorities and planners to create spatial
plans in order to manage land and natural resources sustainably

Open Land Use map database is a vector, seamless harmonized
dataset that covers the whole Europe. It is based on open data
and provides land use map in most detailed possible scale for
each country

Due to the fact that in Europe there are lots of vector open data
available it is possible to create such map just based on this data
3
Background
Example of how open land use map looks for Europe:
4
Background

In Africa on the other side there is almost no vector open data available
related to land use

From the research that was done in 2017 during Inspire hackathon in Kehl
just few datasources were identified:
➔Open Street Map
➔Africover dataset

The datasets cover just small part of the Africa, also Africover dataset was
collected in the end of 90s – beginning of 2000s so it is outdatated

Another important motivation for the work is lots of negative proccesses
around in Africa (deforestation, soil erosion, uncontrolled urban growth etc.),
that could be solved with land use plans and measures helping sustainable
development
5
Background
Example of coverage of Africa with open vector data sources
from which Land Use could be derived:
6
Background
●
The absense of open data together with the fact that negative
processes that were mentioned before are quite rapid and need
to be monitored , taking into account, easy availability of
satellite data nowadays (i.e. Sentinel-2, Landsat-8) it was
decided to use it to derive land use
●
The creation of the map should have been done with the help of
Tensorflow library (one of the most powerful libraries for
machine learning)
7
Background
With the help of this library it is possible to do following
operations:
➔
Classify image (i.e. to tell there is an object X on the image)
➔
Detect object on the image (draw bounding box around the
detected object)
➔
Do semantic segmentation of image (segmentize image into
different objects that appear on it)
➔
Segmentize image into instances of objects
8
Background
Examples of aforementioned operations:
9
Background
In general, from all AI algorithms, convolution neural networks
(CNN) seem to be the most usable for the abovementioned tasks.
Here is the diagram that explains how these CNN models for
image classification are being created:
10
Tensorflow library
From the user utile perspective the process of creating the model
creates of the following steps:
➔
Collecting big (thousands of images) collection of samples of each
land use classes
➔
Dividing the collected samples into two almost equal parts: training
and evaluation
➔
Selecting the base type of CNN model that will be trained
➔
Running training
➔
Running evaluation
➔
Using model
11
Image sample collection
●
There needs to be a lot of sample imagery (a few thousand samples for
each land use class)
●
The images need to be pre-processed (contrast adjustment, central
alignment)
●
Imagees for each class need to be divided into two groups (one for
training the model, another for model evaluation)
●
Tensorflow record file needs to be created for each of these two groups.
The file could be automatically generated from csv file that has the
number of rows corresponding to the number of objects in images and
looks like:
filename width height class xmin ymin xmax ymax
airport1.jpg 200 300 airport 1 1 200 300
12
Image sample collection
●
The tf record file then is easily generated from such csv file using
script generate_tfrecord.py that is provided by Tensorflow
developers
●
python generate_tfrecord.py --csv_input=data/train_labels.csv
–output_path=data/train.record –image_dir=images
●
The images of different land use classes could be downloaded
from Sentinel-2 , the classes of the image could be derived from
Open Street Map database
●
So in the beginning osm data for Eastern Africa (Kenya,
Tanzania, Southern Sudan, Rwanda, Burundi and Uganda) was
downloaded and loaded into PostgreSQL database
13
Image sample collection
●
After this for each land use class the script was run. For instance
taking airports as an example:
➔
initialize database connection
➔
query all airports
➔
for each airport find Sentinel-2 image with the least cloud
coverage (with sentinelsat api)
➔ download and save the sample image for this date from Mundi WCS service
14
Image sample collection
15
Model training and evaluation
●
After samples were collected the training of the object
detection model based on Mobilenet base model was trained:
python train.py --logtostderr --train_dir=training/ --
pipeline_config_path=training/ssd_mobilenet_v1_coco.config
●
After evaluation on another part of the images was run:
python eval.py --logtostderr
--pipeline_config_path=training/ssd_mobilenet_v1_coco.config
--checkpoint_dir=training/ --eval_dir=eval/
16
Using model
●
Eventually the model was exported to the graph:
python export_inference_graph.py --input_type image_tensor
--pipeline_config_path training/ssd_mobilenet_v1_coco.config
--trained_checkpoint_prefix training/model.ckpt-1454 --
output_directory airport_inference_graph2
●
After the models (concretely for residential land use and
airports) were tested on real cloudless images from Sentinel-2
for different areas
17
Expected results
Correct identification as in example identification of objects in
image below:
18
Real results
In our case unfortunately the model for the airports
identification wasn‘t able to find any airport and the model that
tried to identify residential land use was marking as residential
land use most part of the image.
The reason behind it is probably that in case with airports in
Eastern Africa – it wasn‘t enough samples for training the model.
From the whole Eastern Africa it is just 70 airports in Open Street
Map database and to train model one needs many more
samples.
19
Real results
In case with residential landuse the most samples were small
and looked like:
20
Real results
In the case with residential land use there were several
problems. The most residential areas in Open Street Map
database are very small features that with Sentinel-2 10 meters
spatial resolution become just like couple of brownish, grey
pixels. Taking into account that we have forgotten to improve
contrast of the samples before training model : almost all
Sentinel-2 images without improved contrast look very greyish
and brownish, so most of the images that we tested this model,
were evaluated as residential land use.
21
Things need to be done
●
Improve sample data collection process:
➔
Collect more samples
➔
Set minimum and maximum size of the sample
➔
Enhance contrast of samples
●
Select base CNN model and configure it with more care:
➔
This time Mobilenet CNN was selected since it is leightweight
and can be trained even on relatively simple notebook , possibly,
other models could be more useful for this prupose
22
Thank you for the attention!

Más contenido relacionado

La actualidad más candente

Dem analaysis and catchment delineation using GIS
Dem analaysis and catchment delineation using GISDem analaysis and catchment delineation using GIS
Dem analaysis and catchment delineation using GISHans van der Kwast
 
2017 ASPRS-RMR Big Data Track: A Geospatial Picture of 1959 Albuquerque, New ...
2017 ASPRS-RMR Big Data Track: A Geospatial Picture of 1959 Albuquerque, New ...2017 ASPRS-RMR Big Data Track: A Geospatial Picture of 1959 Albuquerque, New ...
2017 ASPRS-RMR Big Data Track: A Geospatial Picture of 1959 Albuquerque, New ...GIS in the Rockies
 
Using Very High Resolution Satellite Images for Planning Activities in Mining
Using Very High Resolution Satellite Images for Planning Activities in MiningUsing Very High Resolution Satellite Images for Planning Activities in Mining
Using Very High Resolution Satellite Images for Planning Activities in MiningArgongra Gis
 
Remotesensingandgisapplications
RemotesensingandgisapplicationsRemotesensingandgisapplications
Remotesensingandgisapplicationsimaduddin91
 
CNES activities on semantic search
CNES activities on semantic searchCNES activities on semantic search
CNES activities on semantic searchGasperi Jerome
 
NUMERICAL METHOD
NUMERICAL METHODNUMERICAL METHOD
NUMERICAL METHODmehedi15
 
5 pgp built environment library
5 pgp  built environment library5 pgp  built environment library
5 pgp built environment librarypvhead123
 
Intelligent video monitoring
Intelligent video monitoringIntelligent video monitoring
Intelligent video monitoringivangomezconde
 
Integrating the Campus to National NSF Cyberinfrastructure such as OSG and XSEDE
Integrating the Campus to National NSF Cyberinfrastructure such as OSG and XSEDEIntegrating the Campus to National NSF Cyberinfrastructure such as OSG and XSEDE
Integrating the Campus to National NSF Cyberinfrastructure such as OSG and XSEDERob Gardner
 
Ahmad Mauliddin Vol Of Water In Bili Bili
Ahmad Mauliddin Vol Of Water In Bili BiliAhmad Mauliddin Vol Of Water In Bili Bili
Ahmad Mauliddin Vol Of Water In Bili BiliHartanto Sanjaya
 
Mobile mapping: Wuppertal, Germany
Mobile mapping: Wuppertal, GermanyMobile mapping: Wuppertal, Germany
Mobile mapping: Wuppertal, GermanyTijana Susnjar
 
Lupws session 1 progress NGD FINNMAP_short_oct2012_eng only
Lupws session 1 progress NGD FINNMAP_short_oct2012_eng onlyLupws session 1 progress NGD FINNMAP_short_oct2012_eng only
Lupws session 1 progress NGD FINNMAP_short_oct2012_eng onlyLUP_Lao
 
ePOM - Intro to Ocean Data Science - Raster and Vector Data Formats
ePOM - Intro to Ocean Data Science - Raster and Vector Data FormatsePOM - Intro to Ocean Data Science - Raster and Vector Data Formats
ePOM - Intro to Ocean Data Science - Raster and Vector Data FormatsGiuseppe Masetti
 

La actualidad más candente (20)

Dem analaysis and catchment delineation using GIS
Dem analaysis and catchment delineation using GISDem analaysis and catchment delineation using GIS
Dem analaysis and catchment delineation using GIS
 
2017 ASPRS-RMR Big Data Track: A Geospatial Picture of 1959 Albuquerque, New ...
2017 ASPRS-RMR Big Data Track: A Geospatial Picture of 1959 Albuquerque, New ...2017 ASPRS-RMR Big Data Track: A Geospatial Picture of 1959 Albuquerque, New ...
2017 ASPRS-RMR Big Data Track: A Geospatial Picture of 1959 Albuquerque, New ...
 
Workshop two
Workshop twoWorkshop two
Workshop two
 
Using Very High Resolution Satellite Images for Planning Activities in Mining
Using Very High Resolution Satellite Images for Planning Activities in MiningUsing Very High Resolution Satellite Images for Planning Activities in Mining
Using Very High Resolution Satellite Images for Planning Activities in Mining
 
Diaz Collect Earth remote sensing activity data Nov 10 2014
Diaz Collect Earth remote sensing activity data Nov 10 2014Diaz Collect Earth remote sensing activity data Nov 10 2014
Diaz Collect Earth remote sensing activity data Nov 10 2014
 
Remotesensingandgisapplications
RemotesensingandgisapplicationsRemotesensingandgisapplications
Remotesensingandgisapplications
 
CNES activities on semantic search
CNES activities on semantic searchCNES activities on semantic search
CNES activities on semantic search
 
NUMERICAL METHOD
NUMERICAL METHODNUMERICAL METHOD
NUMERICAL METHOD
 
5 pgp built environment library
5 pgp  built environment library5 pgp  built environment library
5 pgp built environment library
 
Intelligent video monitoring
Intelligent video monitoringIntelligent video monitoring
Intelligent video monitoring
 
Integrating the Campus to National NSF Cyberinfrastructure such as OSG and XSEDE
Integrating the Campus to National NSF Cyberinfrastructure such as OSG and XSEDEIntegrating the Campus to National NSF Cyberinfrastructure such as OSG and XSEDE
Integrating the Campus to National NSF Cyberinfrastructure such as OSG and XSEDE
 
Map design in GIS
Map design in GISMap design in GIS
Map design in GIS
 
RJW CCAE Course 1977-79
RJW CCAE Course 1977-79RJW CCAE Course 1977-79
RJW CCAE Course 1977-79
 
Ahmad Mauliddin Vol Of Water In Bili Bili
Ahmad Mauliddin Vol Of Water In Bili BiliAhmad Mauliddin Vol Of Water In Bili Bili
Ahmad Mauliddin Vol Of Water In Bili Bili
 
Introduction to GIS
Introduction to GISIntroduction to GIS
Introduction to GIS
 
Keeping It Simple
Keeping It SimpleKeeping It Simple
Keeping It Simple
 
Mobile mapping: Wuppertal, Germany
Mobile mapping: Wuppertal, GermanyMobile mapping: Wuppertal, Germany
Mobile mapping: Wuppertal, Germany
 
Lupws session 1 progress NGD FINNMAP_short_oct2012_eng only
Lupws session 1 progress NGD FINNMAP_short_oct2012_eng onlyLupws session 1 progress NGD FINNMAP_short_oct2012_eng only
Lupws session 1 progress NGD FINNMAP_short_oct2012_eng only
 
Casos de uso do FME no IBGE
Casos de uso do FME no IBGECasos de uso do FME no IBGE
Casos de uso do FME no IBGE
 
ePOM - Intro to Ocean Data Science - Raster and Vector Data Formats
ePOM - Intro to Ocean Data Science - Raster and Vector Data FormatsePOM - Intro to Ocean Data Science - Raster and Vector Data Formats
ePOM - Intro to Ocean Data Science - Raster and Vector Data Formats
 

Similar a TEAM 3: Open Land Use for Africa (OLU4Africa)

CrowdMap: Accurate Reconstruction of Indoor Floor Plan from Crowdsourced Sens...
CrowdMap: Accurate Reconstruction of Indoor Floor Plan from Crowdsourced Sens...CrowdMap: Accurate Reconstruction of Indoor Floor Plan from Crowdsourced Sens...
CrowdMap: Accurate Reconstruction of Indoor Floor Plan from Crowdsourced Sens...Si Chen
 
12 SuperAI on Supercomputers
12 SuperAI on Supercomputers12 SuperAI on Supercomputers
12 SuperAI on SupercomputersRCCSRENKEI
 
Comparison of Various RCNN techniques for Classification of Object from Image
Comparison of Various RCNN techniques for Classification of Object from ImageComparison of Various RCNN techniques for Classification of Object from Image
Comparison of Various RCNN techniques for Classification of Object from ImageIRJET Journal
 
Open Land Use - the Current Status and Steps Forward
Open Land Use - the Current Status and Steps ForwardOpen Land Use - the Current Status and Steps Forward
Open Land Use - the Current Status and Steps Forwardplan4all
 
Assignment 9Assignment 9.docxGIS 5103 – Week 9 Assignment – R.docx
Assignment 9Assignment 9.docxGIS 5103 – Week 9 Assignment – R.docxAssignment 9Assignment 9.docxGIS 5103 – Week 9 Assignment – R.docx
Assignment 9Assignment 9.docxGIS 5103 – Week 9 Assignment – R.docxbraycarissa250
 
Real time video analytics with InfoSphere Streams, OpenCV and R
Real time video analytics with InfoSphere Streams, OpenCV and RReal time video analytics with InfoSphere Streams, OpenCV and R
Real time video analytics with InfoSphere Streams, OpenCV and RStephan Reimann
 
[DSC Europe 22] Land Boundary Delineation using U-net - Theophilus Aidoo
[DSC Europe 22] Land Boundary Delineation using U-net - Theophilus Aidoo[DSC Europe 22] Land Boundary Delineation using U-net - Theophilus Aidoo
[DSC Europe 22] Land Boundary Delineation using U-net - Theophilus AidooDataScienceConferenc1
 
Vol 9 No 1 - January 2014
Vol 9 No 1 - January 2014Vol 9 No 1 - January 2014
Vol 9 No 1 - January 2014ijcsbi
 
A Computer Model for Selecting Equipment for Earthmoving Operations Using Sim...
A Computer Model for Selecting Equipment for Earthmoving Operations Using Sim...A Computer Model for Selecting Equipment for Earthmoving Operations Using Sim...
A Computer Model for Selecting Equipment for Earthmoving Operations Using Sim...Hassan Eliwa
 
SD-miner System to Retrieve Probabilistic Neighborhood Points in Spatial Dat...
SD-miner System to Retrieve Probabilistic Neighborhood Points  in Spatial Dat...SD-miner System to Retrieve Probabilistic Neighborhood Points  in Spatial Dat...
SD-miner System to Retrieve Probabilistic Neighborhood Points in Spatial Dat...IOSR Journals
 
Machine learning for decentralized and flying radio devices
Machine learning for decentralized and flying radio devicesMachine learning for decentralized and flying radio devices
Machine learning for decentralized and flying radio devicesITU
 
Path Finding In Hazad Terrain
Path Finding In Hazad TerrainPath Finding In Hazad Terrain
Path Finding In Hazad TerrainOren Koler
 
Vehicle detection in Aerial Images
Vehicle detection in Aerial ImagesVehicle detection in Aerial Images
Vehicle detection in Aerial ImagesKoshy Geoji
 
Project on nypd accident analysis using hadoop environment
Project on nypd accident analysis using hadoop environmentProject on nypd accident analysis using hadoop environment
Project on nypd accident analysis using hadoop environmentSiddharth Chaudhary
 
AI IN VEHICLE COUNTING (1).pptx
AI IN VEHICLE COUNTING (1).pptxAI IN VEHICLE COUNTING (1).pptx
AI IN VEHICLE COUNTING (1).pptxYash670955
 
Qualità dei dati OpenStreetMap: sperimentazioni sulla città di Milano e risul...
Qualità dei dati OpenStreetMap: sperimentazioni sulla città di Milano e risul...Qualità dei dati OpenStreetMap: sperimentazioni sulla città di Milano e risul...
Qualità dei dati OpenStreetMap: sperimentazioni sulla città di Milano e risul...Marco Minghini
 

Similar a TEAM 3: Open Land Use for Africa (OLU4Africa) (20)

CrowdMap: Accurate Reconstruction of Indoor Floor Plan from Crowdsourced Sens...
CrowdMap: Accurate Reconstruction of Indoor Floor Plan from Crowdsourced Sens...CrowdMap: Accurate Reconstruction of Indoor Floor Plan from Crowdsourced Sens...
CrowdMap: Accurate Reconstruction of Indoor Floor Plan from Crowdsourced Sens...
 
Lesson2 esa summer_school_brovelli
Lesson2 esa summer_school_brovelliLesson2 esa summer_school_brovelli
Lesson2 esa summer_school_brovelli
 
12 SuperAI on Supercomputers
12 SuperAI on Supercomputers12 SuperAI on Supercomputers
12 SuperAI on Supercomputers
 
Comparison of Various RCNN techniques for Classification of Object from Image
Comparison of Various RCNN techniques for Classification of Object from ImageComparison of Various RCNN techniques for Classification of Object from Image
Comparison of Various RCNN techniques for Classification of Object from Image
 
Open Land Use - the Current Status and Steps Forward
Open Land Use - the Current Status and Steps ForwardOpen Land Use - the Current Status and Steps Forward
Open Land Use - the Current Status and Steps Forward
 
Assignment 9Assignment 9.docxGIS 5103 – Week 9 Assignment – R.docx
Assignment 9Assignment 9.docxGIS 5103 – Week 9 Assignment – R.docxAssignment 9Assignment 9.docxGIS 5103 – Week 9 Assignment – R.docx
Assignment 9Assignment 9.docxGIS 5103 – Week 9 Assignment – R.docx
 
Real time video analytics with InfoSphere Streams, OpenCV and R
Real time video analytics with InfoSphere Streams, OpenCV and RReal time video analytics with InfoSphere Streams, OpenCV and R
Real time video analytics with InfoSphere Streams, OpenCV and R
 
[DSC Europe 22] Land Boundary Delineation using U-net - Theophilus Aidoo
[DSC Europe 22] Land Boundary Delineation using U-net - Theophilus Aidoo[DSC Europe 22] Land Boundary Delineation using U-net - Theophilus Aidoo
[DSC Europe 22] Land Boundary Delineation using U-net - Theophilus Aidoo
 
Vol 9 No 1 - January 2014
Vol 9 No 1 - January 2014Vol 9 No 1 - January 2014
Vol 9 No 1 - January 2014
 
Multimedia Mining
Multimedia Mining Multimedia Mining
Multimedia Mining
 
A Computer Model for Selecting Equipment for Earthmoving Operations Using Sim...
A Computer Model for Selecting Equipment for Earthmoving Operations Using Sim...A Computer Model for Selecting Equipment for Earthmoving Operations Using Sim...
A Computer Model for Selecting Equipment for Earthmoving Operations Using Sim...
 
Real Time Parking Information Provider System on Android Phones
Real Time Parking Information Provider System on Android PhonesReal Time Parking Information Provider System on Android Phones
Real Time Parking Information Provider System on Android Phones
 
SD-miner System to Retrieve Probabilistic Neighborhood Points in Spatial Dat...
SD-miner System to Retrieve Probabilistic Neighborhood Points  in Spatial Dat...SD-miner System to Retrieve Probabilistic Neighborhood Points  in Spatial Dat...
SD-miner System to Retrieve Probabilistic Neighborhood Points in Spatial Dat...
 
Machine learning for decentralized and flying radio devices
Machine learning for decentralized and flying radio devicesMachine learning for decentralized and flying radio devices
Machine learning for decentralized and flying radio devices
 
A step towards interactive displays of digital elevation models
A step towards interactive displays of digital elevation modelsA step towards interactive displays of digital elevation models
A step towards interactive displays of digital elevation models
 
Path Finding In Hazad Terrain
Path Finding In Hazad TerrainPath Finding In Hazad Terrain
Path Finding In Hazad Terrain
 
Vehicle detection in Aerial Images
Vehicle detection in Aerial ImagesVehicle detection in Aerial Images
Vehicle detection in Aerial Images
 
Project on nypd accident analysis using hadoop environment
Project on nypd accident analysis using hadoop environmentProject on nypd accident analysis using hadoop environment
Project on nypd accident analysis using hadoop environment
 
AI IN VEHICLE COUNTING (1).pptx
AI IN VEHICLE COUNTING (1).pptxAI IN VEHICLE COUNTING (1).pptx
AI IN VEHICLE COUNTING (1).pptx
 
Qualità dei dati OpenStreetMap: sperimentazioni sulla città di Milano e risul...
Qualità dei dati OpenStreetMap: sperimentazioni sulla città di Milano e risul...Qualità dei dati OpenStreetMap: sperimentazioni sulla città di Milano e risul...
Qualità dei dati OpenStreetMap: sperimentazioni sulla città di Milano e risul...
 

Más de plan4all

Agrihub INSPIRE HAckathon 2021: Extreme weather
Agrihub INSPIRE HAckathon 2021: Extreme weather Agrihub INSPIRE HAckathon 2021: Extreme weather
Agrihub INSPIRE HAckathon 2021: Extreme weather plan4all
 
Agrihub INSPIRE Hackathon 2021: Challenge #7: Analysis, processing and standa...
Agrihub INSPIRE Hackathon 2021: Challenge #7: Analysis, processing and standa...Agrihub INSPIRE Hackathon 2021: Challenge #7: Analysis, processing and standa...
Agrihub INSPIRE Hackathon 2021: Challenge #7: Analysis, processing and standa...plan4all
 
Agrihub INSPIRE Hackathon 2021: Challenge #6 Drones Utilization for Crop Prot...
Agrihub INSPIRE Hackathon 2021: Challenge #6 Drones Utilization for Crop Prot...Agrihub INSPIRE Hackathon 2021: Challenge #6 Drones Utilization for Crop Prot...
Agrihub INSPIRE Hackathon 2021: Challenge #6 Drones Utilization for Crop Prot...plan4all
 
Agrihub INSPIRE Hackathon 2021: Challenge #4 Irrigation Management
Agrihub INSPIRE Hackathon 2021: Challenge #4 Irrigation ManagementAgrihub INSPIRE Hackathon 2021: Challenge #4 Irrigation Management
Agrihub INSPIRE Hackathon 2021: Challenge #4 Irrigation Managementplan4all
 
Agrihub INSPIRE Hackathon 2021: Challenge #2 Crop status monitoring
Agrihub INSPIRE Hackathon 2021: Challenge #2 Crop status monitoringAgrihub INSPIRE Hackathon 2021: Challenge #2 Crop status monitoring
Agrihub INSPIRE Hackathon 2021: Challenge #2 Crop status monitoringplan4all
 
Agrihub INSPIRE Hackathon 2021: Challenge #1 Crop detection
Agrihub INSPIRE Hackathon 2021: Challenge #1 Crop detectionAgrihub INSPIRE Hackathon 2021: Challenge #1 Crop detection
Agrihub INSPIRE Hackathon 2021: Challenge #1 Crop detectionplan4all
 
Challenge #3 agro environmental services final presentation
Challenge #3 agro environmental services final presentationChallenge #3 agro environmental services final presentation
Challenge #3 agro environmental services final presentationplan4all
 
Sieusoil e-brochure (Feb 2021)
Sieusoil e-brochure (Feb 2021)Sieusoil e-brochure (Feb 2021)
Sieusoil e-brochure (Feb 2021)plan4all
 
Webinar 4 Agronode - autonomni telemetricka io t stanice
Webinar 4  Agronode - autonomni telemetricka io t staniceWebinar 4  Agronode - autonomni telemetricka io t stanice
Webinar 4 Agronode - autonomni telemetricka io t staniceplan4all
 
Webinar 3 senslog-otevrene reseni pro integraci senzoru a spravu senzorovyc...
Webinar 3   senslog-otevrene reseni pro integraci senzoru a spravu senzorovyc...Webinar 3   senslog-otevrene reseni pro integraci senzoru a spravu senzorovyc...
Webinar 3 senslog-otevrene reseni pro integraci senzoru a spravu senzorovyc...plan4all
 
Webinar 2 sdileni prostorovych dat
Webinar 2 sdileni prostorovych datWebinar 2 sdileni prostorovych dat
Webinar 2 sdileni prostorovych datplan4all
 
Calculation of agro climatic factors from global climatic data
Calculation of agro climatic factors from global climatic dataCalculation of agro climatic factors from global climatic data
Calculation of agro climatic factors from global climatic dataplan4all
 
Digitalization of indigenous knowledge in African agriculture for fostering f...
Digitalization of indigenous knowledge in African agriculture for fostering f...Digitalization of indigenous knowledge in African agriculture for fostering f...
Digitalization of indigenous knowledge in African agriculture for fostering f...plan4all
 
Atlas of Best Practice
Atlas of Best PracticeAtlas of Best Practice
Atlas of Best Practiceplan4all
 
Euxdat newsletter 10_2020
Euxdat newsletter 10_2020Euxdat newsletter 10_2020
Euxdat newsletter 10_2020plan4all
 
Karel charvat map-compositions-format-intro-presentation-by-karel (1)
Karel charvat map-compositions-format-intro-presentation-by-karel (1)Karel charvat map-compositions-format-intro-presentation-by-karel (1)
Karel charvat map-compositions-format-intro-presentation-by-karel (1)plan4all
 
Karel charvat map-whiteboard-collaborative-map-making-breakout-session
Karel charvat map-whiteboard-collaborative-map-making-breakout-sessionKarel charvat map-whiteboard-collaborative-map-making-breakout-session
Karel charvat map-whiteboard-collaborative-map-making-breakout-sessionplan4all
 
Bridging the Digital Divide Through Consumer Driven Agricultural FarmHub Data...
Bridging the Digital Divide Through Consumer Driven Agricultural FarmHub Data...Bridging the Digital Divide Through Consumer Driven Agricultural FarmHub Data...
Bridging the Digital Divide Through Consumer Driven Agricultural FarmHub Data...plan4all
 
Codes of conduct for farm data sharing
Codes of conduct for farm data sharing Codes of conduct for farm data sharing
Codes of conduct for farm data sharing plan4all
 
Mobilizing Capacity Development in Agriculture for Smallholder Farmers - How ...
Mobilizing Capacity Development in Agriculture for Smallholder Farmers - How ...Mobilizing Capacity Development in Agriculture for Smallholder Farmers - How ...
Mobilizing Capacity Development in Agriculture for Smallholder Farmers - How ...plan4all
 

Más de plan4all (20)

Agrihub INSPIRE HAckathon 2021: Extreme weather
Agrihub INSPIRE HAckathon 2021: Extreme weather Agrihub INSPIRE HAckathon 2021: Extreme weather
Agrihub INSPIRE HAckathon 2021: Extreme weather
 
Agrihub INSPIRE Hackathon 2021: Challenge #7: Analysis, processing and standa...
Agrihub INSPIRE Hackathon 2021: Challenge #7: Analysis, processing and standa...Agrihub INSPIRE Hackathon 2021: Challenge #7: Analysis, processing and standa...
Agrihub INSPIRE Hackathon 2021: Challenge #7: Analysis, processing and standa...
 
Agrihub INSPIRE Hackathon 2021: Challenge #6 Drones Utilization for Crop Prot...
Agrihub INSPIRE Hackathon 2021: Challenge #6 Drones Utilization for Crop Prot...Agrihub INSPIRE Hackathon 2021: Challenge #6 Drones Utilization for Crop Prot...
Agrihub INSPIRE Hackathon 2021: Challenge #6 Drones Utilization for Crop Prot...
 
Agrihub INSPIRE Hackathon 2021: Challenge #4 Irrigation Management
Agrihub INSPIRE Hackathon 2021: Challenge #4 Irrigation ManagementAgrihub INSPIRE Hackathon 2021: Challenge #4 Irrigation Management
Agrihub INSPIRE Hackathon 2021: Challenge #4 Irrigation Management
 
Agrihub INSPIRE Hackathon 2021: Challenge #2 Crop status monitoring
Agrihub INSPIRE Hackathon 2021: Challenge #2 Crop status monitoringAgrihub INSPIRE Hackathon 2021: Challenge #2 Crop status monitoring
Agrihub INSPIRE Hackathon 2021: Challenge #2 Crop status monitoring
 
Agrihub INSPIRE Hackathon 2021: Challenge #1 Crop detection
Agrihub INSPIRE Hackathon 2021: Challenge #1 Crop detectionAgrihub INSPIRE Hackathon 2021: Challenge #1 Crop detection
Agrihub INSPIRE Hackathon 2021: Challenge #1 Crop detection
 
Challenge #3 agro environmental services final presentation
Challenge #3 agro environmental services final presentationChallenge #3 agro environmental services final presentation
Challenge #3 agro environmental services final presentation
 
Sieusoil e-brochure (Feb 2021)
Sieusoil e-brochure (Feb 2021)Sieusoil e-brochure (Feb 2021)
Sieusoil e-brochure (Feb 2021)
 
Webinar 4 Agronode - autonomni telemetricka io t stanice
Webinar 4  Agronode - autonomni telemetricka io t staniceWebinar 4  Agronode - autonomni telemetricka io t stanice
Webinar 4 Agronode - autonomni telemetricka io t stanice
 
Webinar 3 senslog-otevrene reseni pro integraci senzoru a spravu senzorovyc...
Webinar 3   senslog-otevrene reseni pro integraci senzoru a spravu senzorovyc...Webinar 3   senslog-otevrene reseni pro integraci senzoru a spravu senzorovyc...
Webinar 3 senslog-otevrene reseni pro integraci senzoru a spravu senzorovyc...
 
Webinar 2 sdileni prostorovych dat
Webinar 2 sdileni prostorovych datWebinar 2 sdileni prostorovych dat
Webinar 2 sdileni prostorovych dat
 
Calculation of agro climatic factors from global climatic data
Calculation of agro climatic factors from global climatic dataCalculation of agro climatic factors from global climatic data
Calculation of agro climatic factors from global climatic data
 
Digitalization of indigenous knowledge in African agriculture for fostering f...
Digitalization of indigenous knowledge in African agriculture for fostering f...Digitalization of indigenous knowledge in African agriculture for fostering f...
Digitalization of indigenous knowledge in African agriculture for fostering f...
 
Atlas of Best Practice
Atlas of Best PracticeAtlas of Best Practice
Atlas of Best Practice
 
Euxdat newsletter 10_2020
Euxdat newsletter 10_2020Euxdat newsletter 10_2020
Euxdat newsletter 10_2020
 
Karel charvat map-compositions-format-intro-presentation-by-karel (1)
Karel charvat map-compositions-format-intro-presentation-by-karel (1)Karel charvat map-compositions-format-intro-presentation-by-karel (1)
Karel charvat map-compositions-format-intro-presentation-by-karel (1)
 
Karel charvat map-whiteboard-collaborative-map-making-breakout-session
Karel charvat map-whiteboard-collaborative-map-making-breakout-sessionKarel charvat map-whiteboard-collaborative-map-making-breakout-session
Karel charvat map-whiteboard-collaborative-map-making-breakout-session
 
Bridging the Digital Divide Through Consumer Driven Agricultural FarmHub Data...
Bridging the Digital Divide Through Consumer Driven Agricultural FarmHub Data...Bridging the Digital Divide Through Consumer Driven Agricultural FarmHub Data...
Bridging the Digital Divide Through Consumer Driven Agricultural FarmHub Data...
 
Codes of conduct for farm data sharing
Codes of conduct for farm data sharing Codes of conduct for farm data sharing
Codes of conduct for farm data sharing
 
Mobilizing Capacity Development in Agriculture for Smallholder Farmers - How ...
Mobilizing Capacity Development in Agriculture for Smallholder Farmers - How ...Mobilizing Capacity Development in Agriculture for Smallholder Farmers - How ...
Mobilizing Capacity Development in Agriculture for Smallholder Farmers - How ...
 

Último

Ravak dropshipping via API with DroFx.pptx
Ravak dropshipping via API with DroFx.pptxRavak dropshipping via API with DroFx.pptx
Ravak dropshipping via API with DroFx.pptxolyaivanovalion
 
VidaXL dropshipping via API with DroFx.pptx
VidaXL dropshipping via API with DroFx.pptxVidaXL dropshipping via API with DroFx.pptx
VidaXL dropshipping via API with DroFx.pptxolyaivanovalion
 
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...amitlee9823
 
CebaBaby dropshipping via API with DroFX.pptx
CebaBaby dropshipping via API with DroFX.pptxCebaBaby dropshipping via API with DroFX.pptx
CebaBaby dropshipping via API with DroFX.pptxolyaivanovalion
 
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptxBPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptxMohammedJunaid861692
 
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 nightCheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 nightDelhi Call girls
 
Discover Why Less is More in B2B Research
Discover Why Less is More in B2B ResearchDiscover Why Less is More in B2B Research
Discover Why Less is More in B2B Researchmichael115558
 
Generative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and MilvusGenerative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and MilvusTimothy Spann
 
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...amitlee9823
 
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...Delhi Call girls
 
Edukaciniai dropshipping via API with DroFx
Edukaciniai dropshipping via API with DroFxEdukaciniai dropshipping via API with DroFx
Edukaciniai dropshipping via API with DroFxolyaivanovalion
 
Log Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptxLog Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptxJohnnyPlasten
 
Data-Analysis for Chicago Crime Data 2023
Data-Analysis for Chicago Crime Data  2023Data-Analysis for Chicago Crime Data  2023
Data-Analysis for Chicago Crime Data 2023ymrp368
 
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...amitlee9823
 
Determinants of health, dimensions of health, positive health and spectrum of...
Determinants of health, dimensions of health, positive health and spectrum of...Determinants of health, dimensions of health, positive health and spectrum of...
Determinants of health, dimensions of health, positive health and spectrum of...shambhavirathore45
 
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...SUHANI PANDEY
 
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779Delhi Call girls
 
BigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptxBigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptxolyaivanovalion
 

Último (20)

Ravak dropshipping via API with DroFx.pptx
Ravak dropshipping via API with DroFx.pptxRavak dropshipping via API with DroFx.pptx
Ravak dropshipping via API with DroFx.pptx
 
VidaXL dropshipping via API with DroFx.pptx
VidaXL dropshipping via API with DroFx.pptxVidaXL dropshipping via API with DroFx.pptx
VidaXL dropshipping via API with DroFx.pptx
 
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
 
CebaBaby dropshipping via API with DroFX.pptx
CebaBaby dropshipping via API with DroFX.pptxCebaBaby dropshipping via API with DroFX.pptx
CebaBaby dropshipping via API with DroFX.pptx
 
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get CytotecAbortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
 
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptxBPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
 
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 nightCheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
 
Discover Why Less is More in B2B Research
Discover Why Less is More in B2B ResearchDiscover Why Less is More in B2B Research
Discover Why Less is More in B2B Research
 
Generative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and MilvusGenerative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and Milvus
 
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
 
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
 
Edukaciniai dropshipping via API with DroFx
Edukaciniai dropshipping via API with DroFxEdukaciniai dropshipping via API with DroFx
Edukaciniai dropshipping via API with DroFx
 
Log Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptxLog Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptx
 
Data-Analysis for Chicago Crime Data 2023
Data-Analysis for Chicago Crime Data  2023Data-Analysis for Chicago Crime Data  2023
Data-Analysis for Chicago Crime Data 2023
 
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
 
Determinants of health, dimensions of health, positive health and spectrum of...
Determinants of health, dimensions of health, positive health and spectrum of...Determinants of health, dimensions of health, positive health and spectrum of...
Determinants of health, dimensions of health, positive health and spectrum of...
 
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
 
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
 
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts ServiceCall Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
 
BigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptxBigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptx
 

TEAM 3: Open Land Use for Africa (OLU4Africa)

  • 1. Team 3. Open Land Use 4 Africa
  • 2. 2 Background  Land use maps help authorities and planners to create spatial plans in order to manage land and natural resources sustainably  Open Land Use map database is a vector, seamless harmonized dataset that covers the whole Europe. It is based on open data and provides land use map in most detailed possible scale for each country  Due to the fact that in Europe there are lots of vector open data available it is possible to create such map just based on this data
  • 3. 3 Background Example of how open land use map looks for Europe:
  • 4. 4 Background  In Africa on the other side there is almost no vector open data available related to land use  From the research that was done in 2017 during Inspire hackathon in Kehl just few datasources were identified: ➔Open Street Map ➔Africover dataset  The datasets cover just small part of the Africa, also Africover dataset was collected in the end of 90s – beginning of 2000s so it is outdatated  Another important motivation for the work is lots of negative proccesses around in Africa (deforestation, soil erosion, uncontrolled urban growth etc.), that could be solved with land use plans and measures helping sustainable development
  • 5. 5 Background Example of coverage of Africa with open vector data sources from which Land Use could be derived:
  • 6. 6 Background ● The absense of open data together with the fact that negative processes that were mentioned before are quite rapid and need to be monitored , taking into account, easy availability of satellite data nowadays (i.e. Sentinel-2, Landsat-8) it was decided to use it to derive land use ● The creation of the map should have been done with the help of Tensorflow library (one of the most powerful libraries for machine learning)
  • 7. 7 Background With the help of this library it is possible to do following operations: ➔ Classify image (i.e. to tell there is an object X on the image) ➔ Detect object on the image (draw bounding box around the detected object) ➔ Do semantic segmentation of image (segmentize image into different objects that appear on it) ➔ Segmentize image into instances of objects
  • 9. 9 Background In general, from all AI algorithms, convolution neural networks (CNN) seem to be the most usable for the abovementioned tasks. Here is the diagram that explains how these CNN models for image classification are being created:
  • 10. 10 Tensorflow library From the user utile perspective the process of creating the model creates of the following steps: ➔ Collecting big (thousands of images) collection of samples of each land use classes ➔ Dividing the collected samples into two almost equal parts: training and evaluation ➔ Selecting the base type of CNN model that will be trained ➔ Running training ➔ Running evaluation ➔ Using model
  • 11. 11 Image sample collection ● There needs to be a lot of sample imagery (a few thousand samples for each land use class) ● The images need to be pre-processed (contrast adjustment, central alignment) ● Imagees for each class need to be divided into two groups (one for training the model, another for model evaluation) ● Tensorflow record file needs to be created for each of these two groups. The file could be automatically generated from csv file that has the number of rows corresponding to the number of objects in images and looks like: filename width height class xmin ymin xmax ymax airport1.jpg 200 300 airport 1 1 200 300
  • 12. 12 Image sample collection ● The tf record file then is easily generated from such csv file using script generate_tfrecord.py that is provided by Tensorflow developers ● python generate_tfrecord.py --csv_input=data/train_labels.csv –output_path=data/train.record –image_dir=images ● The images of different land use classes could be downloaded from Sentinel-2 , the classes of the image could be derived from Open Street Map database ● So in the beginning osm data for Eastern Africa (Kenya, Tanzania, Southern Sudan, Rwanda, Burundi and Uganda) was downloaded and loaded into PostgreSQL database
  • 13. 13 Image sample collection ● After this for each land use class the script was run. For instance taking airports as an example: ➔ initialize database connection ➔ query all airports ➔ for each airport find Sentinel-2 image with the least cloud coverage (with sentinelsat api) ➔ download and save the sample image for this date from Mundi WCS service
  • 15. 15 Model training and evaluation ● After samples were collected the training of the object detection model based on Mobilenet base model was trained: python train.py --logtostderr --train_dir=training/ -- pipeline_config_path=training/ssd_mobilenet_v1_coco.config ● After evaluation on another part of the images was run: python eval.py --logtostderr --pipeline_config_path=training/ssd_mobilenet_v1_coco.config --checkpoint_dir=training/ --eval_dir=eval/
  • 16. 16 Using model ● Eventually the model was exported to the graph: python export_inference_graph.py --input_type image_tensor --pipeline_config_path training/ssd_mobilenet_v1_coco.config --trained_checkpoint_prefix training/model.ckpt-1454 -- output_directory airport_inference_graph2 ● After the models (concretely for residential land use and airports) were tested on real cloudless images from Sentinel-2 for different areas
  • 17. 17 Expected results Correct identification as in example identification of objects in image below:
  • 18. 18 Real results In our case unfortunately the model for the airports identification wasn‘t able to find any airport and the model that tried to identify residential land use was marking as residential land use most part of the image. The reason behind it is probably that in case with airports in Eastern Africa – it wasn‘t enough samples for training the model. From the whole Eastern Africa it is just 70 airports in Open Street Map database and to train model one needs many more samples.
  • 19. 19 Real results In case with residential landuse the most samples were small and looked like:
  • 20. 20 Real results In the case with residential land use there were several problems. The most residential areas in Open Street Map database are very small features that with Sentinel-2 10 meters spatial resolution become just like couple of brownish, grey pixels. Taking into account that we have forgotten to improve contrast of the samples before training model : almost all Sentinel-2 images without improved contrast look very greyish and brownish, so most of the images that we tested this model, were evaluated as residential land use.
  • 21. 21 Things need to be done ● Improve sample data collection process: ➔ Collect more samples ➔ Set minimum and maximum size of the sample ➔ Enhance contrast of samples ● Select base CNN model and configure it with more care: ➔ This time Mobilenet CNN was selected since it is leightweight and can be trained even on relatively simple notebook , possibly, other models could be more useful for this prupose
  • 22. 22 Thank you for the attention!