Skip to content

Python script to automate the alignment of vector data to target, high-resolution images.

Notifications You must be signed in to change notification settings

jjmckee/featureshift

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 

Repository files navigation

FeatureShift

Python code to automate the alignment of vector data to target, high-resolution images. Details regarding the impetus for this project can be found in the publication Automated Registration of Vector Data to Overhead Imagery.

Getting Started

Clone the Repository

git clone [email protected]:ChuckDoug/featureshift.git

Build the Docker Image

cd featureshift
docker build -t featureshift .

Run the Docker Image as a Container

docker run -v /my/data/images/:/mnt/images -v /my/data/vectors/:/mnt/vectors featureshift -i /mnt/vectors/input.shp -t /mnt/images/image_1.tif -o /mnt/vectors/output.shp -x 5

Parameters

-i (required): Path to input Featureclass (GDB) or shapefile (.shp).
-t (required): List of target image/s (.jpg, .jp2, .tif). Image/s must be in a projected coordinate system.
-o (required): Path to output shapefile (.shp).
-x (optional): Integer specifying the search distance in units associated with the target image/s. Default is 5 units.
-lv (optional): Integer specifying the number of nieghbors used for local validation. Value must be greater than or equal to 5.
-gv (optional): Boolean flag to invoke global validation.

*If both -lv and -gv are used, global validation will supersede local validation. If neither -lv or -gv are used, no validation will be implemented.

About

Python script to automate the alignment of vector data to target, high-resolution images.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published