Comments (2)
10m buffer: "fclass" in ("motorway", "primary", "secondary")
4m buffer: "fclass" in ( 'footway' , 'track', 'service' , 'steps' , 'track_grade1' , 'track_grade2' , 'track_grade3' , 'track_grade4' , 'track_grade5' , 'track', 'bridleway' )
6m buffer: remaining.
from sentinel_traj_nn.
Preperation of Montreal Data
-
Extract required data interval from osh.pbf file into osm.pbf.
osmium time-filter quebec-internal.osh.pbf 2018-12-31T23:59:59Z -o quebec-internal_2018.osm.pbf
-
Extract Montreal area from osm.pbf file.
osmium extract -b -75.0473,45.0678,-72.2555,46.0163 quebec-internal_2018.osm.pbf -o montreal-internal_2018.osm.pbf
-
Read montreal-internal_2018.osm.pbf with "QuickOSM" plugin. Only "QuickOSM" converts tag names to attribute fields.
-
Filter "highway" != '' and export into shp - exclude unnecessary fields especially the ones having inconsistent name with shape format.Output shapefile name is montreal-internal_2018_roads.shp.
-
Query for excluded roads. Output files are named with "reduced". This shape files are also projected to raster epsg codes.
"highway" = 'bridleway' or
"highway" = 'bus_guideway' or
"highway" = 'bus_stop' or
"highway" = 'corridor' or
"highway" = 'cycleway' or
"highway" = 'disused' or
"highway" = 'elevator' or
"highway" = 'footway' or
"highway" = 'path' or
"highway" = 'proposed' or
"highway" = 'raceway' or
"highway" = 'services' or
"highway" = 'steps' or
"highway" = 'track' or
"highway" = 'yes'
-
Following queries run and buffer_dis field updated with respective buffer value.
- Query for 12m buffer roads
"highway" = 'motorway' or "highway" = 'motorway_link' or "highway" = 'primary' or "highway" = 'primary_link' or "highway" = 'secondary' or "highway" = 'secondary_link'
- Query for 7m buffer roads
"highway" = 'tertiary' or "highway" = 'tertiary_link' or "highway" = 'trunk' or "highway" = 'trunk_link'
- Query for 5m buffer roads
"highway" = 'living_street' or "highway" = 'residential' or "highway" = 'rest_area' or "highway" = 'road' or "highway" = 'service'
- Query for 4m buffer roads
"buffer_dis" is null
-
"_buf" files are created using "buffer_dis" field using QGIS.
-
"_label" raster files created with using QGIS rasterize tool. Cell size is 2.5 x 2.5m and compression chosen as "DEFLATE"
from sentinel_traj_nn.
Related Issues (20)
- Create custom convolution filter HOT 1
- Add requirements.txt for python libraries
- Resolve filename typo in constract_loss.py HOT 1
- Implement layer wise normalization boundaries.
- Implement ignored images functionality.
- Implement data generator with multiple input sets.
- Run available models on Montreal data
- Run available models on Istanbul data
- Migrate to tensorflow 2.2
- Test new input/output file paths with remote and linux
- Examine the effect of shuffling HOT 1
- Comparison of different loss functions on Montreal and Istanbul with different models
- Add standard deviation for mIoU metric in jupyter notebook
- Create caching mechanism for train, test, validation splits HOT 1
- Run available models on Istanbul+Montreal together
- Create batch experiment running scripts
- Create label coverage % filter
- Run label coverage filtered experiments on all datasets variations
- Create test on different datasets functionality
- Implement swin-unet and transunet
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from sentinel_traj_nn.