| Label | Explanation | Data Type |
Input Raster | The input raster on which processing will be performed. If the Mode parameter is specified as Only Postprocess, a raster with binary classification is expected for this parameter. | Raster Layer; Raster Dataset; Mosaic Layer |
Mode | Specifies the mode that will be used for the processing of the input raster.
| String |
Output Location
| The file geodatabase where the intermediate output from the models and the final postprocessed output will be stored. | Workspace |
Output Prefix
| A prefix that will be added to the name of the outputs that will be saved to the output location. The prefix will also be used as the name of a group layer that will be used to display all outputs. | String |
Area of Interest
(Optional) | The geographical extent that will be used to extract features. Only features within the area of interest will be extracted. | Feature Set |
Pretrained Models (Optional) | The ArcGIS pretrained models from ArcGIS Living Atlas of the World that can be used on the provided input raster. This parameter requires internet connection to download the pretrained models. | String |
Additional Models
(Optional) | The deep learning models that can be used on the provided input raster and the postprocessing workflow that will be used for additional model files (.dlpk and .emd). Available postprocessing workflow are as follows:
| Value Table |
Confidence Threshold
(Optional) | The minimum confidence of deep learning model that will be used when detecting objects. The value must be between 0 and 1. | Double |
Save Intermediate
Output (Optional) | Specifies whether the intermediate outputs will be saved to the output location. The term intermediate outputs refers to the results generated after the model has been inferenced.
| Boolean |
Test Time Augmentation (Optional) | Specifies whether predictions of flipped and rotated variants of the input image will be merged into the final output.
| Boolean |
Buffer Distance
(Optional) | The distance that will be used to buffer polyline features before they are used in postprocessing. The default is 15 meters. | Linear Unit |
Extend Length (Optional) | The maximum distance a line segment will be extended to an intersecting feature. The default is 25 meters. | Linear Unit |
Smoothing Tolerance (Optional) | The tolerance used by the Polynomial Approximation with Exponential Kernel (PAEK) algorithm. The default is 30 meters. | Linear Unit |
Dangle Length (Optional) | The length at which line segments that do not touch another line at both endpoints (dangles) will be trimmed. The default is 5 meters. | Linear Unit |
Input Road Features (Optional) | A road feature class that will be used for refining the parcels. The input can be a polygon or polyline feature class. | Feature Layer; Feature Class |
Road Buffer Width
(Optional) | The buffer distance that will be used for the Input Road Features value. The default value is 5 meters for polyline features and 0 meters for polygon features. | Linear Unit |
Regularize Parcels
(Optional) | Specifies whether extracted parcels will be normalized by eliminating undesirable artifacts in their geometry.
| Boolean |
Post Processing Workflow (Optional) | Specifies the postprocessing workflow that will be used.
| String |
Output Features (Optional) | The feature class containing the postprocessed output. | Feature Class |
Tolerance Between Adjacent Parcels
(Optional) | The minimum distance between coordinates before they are considered equal. This parameter is used to reduce slivers between extracted parcels. The default is 3 meters. | Linear Unit |
Regularization Method (Optional) | Specifies the regularization method that will be used in postprocessing.
| String |
Tolerance
(Optional) | The maximum distance that the regularized footprint can deviate from the boundary of its originating feature. The default is 1 meter. | Linear Unit |
Available with Image Analyst license.
Summary
Runs one or more pretrained deep learning models on an input raster to extract features and automate the postprocessing of the inferenced outputs.
Usage
This tool requires ArcGIS pretrained models from ArcGIS Living Atlas of the World or custom deep learning model packages (.dlpk file).
You must install the proper deep learning framework for Python in ArcGIS Pro.
The time it takes for the tool to produce the outputs depends on the following:
- The area of interest used for inference
- The number of models selected
To run this tool, a GPU-equipped machine is required. If you have more than one GPU, specify the GPU ID instead.
Potential use cases for the tool include creating a basemap using multiple models and postprocessing model outputs using algorithms to clean extracted features.
For information about requirements for running this tool and issues you may encounter, see Deep Learning frequently asked questions.
Parameters
ExtractFeaturesUsingAIModels(in_raster, mode, out_location, out_prefix, {area_of_interest}, {pretrained_models}, {additional_models}, {confidence_threshold}, {save_intermediate_output}, {test_time_augmentation}, {buffer_distance}, {extend_length}, {smoothing_tolerance}, {dangle_length}, {in_road_features}, {road_buffer_width}, {regularize_parcels}, {post_processing_workflow}, {out_features}, {parcel_tolerance}, {regularization_method}, {poly_tolerance})| Name | Explanation | Data Type |
in_raster | The input raster on which processing will be performed. If the mode parameter is specified as Only Postprocess, a raster with binary classification is expected for this parameter. | Raster Layer; Raster Dataset; Mosaic Layer |
mode | Specifies the mode that will be used for the processing of the input raster.
| String |
out_location | The file geodatabase where the intermediate output from the models and the final postprocessed output will be stored. | Workspace |
out_prefix | A prefix that will be added to the name of the outputs that will be saved to the output location. The prefix will also be used as the name of a group layer that will be used to display all outputs. | String |
area_of_interest (Optional) | The geographical extent that will be used to extract features. Only features within the area of interest will be extracted. | Feature Set |
pretrained_models [pretrained_models,...] (Optional) | The ArcGIS pretrained models from ArcGIS Living Atlas of the World that can be used on the provided input raster. This parameter requires internet connection to download the pretrained models. | String |
additional_models [additional_models,...] (Optional) | The deep learning models that can be used on the provided input raster and the postprocessing workflow that will be used for additional model files (.dlpk and .emd). Available postprocessing workflow are as follows:
| Value Table |
confidence_threshold (Optional) | The minimum confidence of deep learning model that will be used when detecting objects. The value must be between 0 and 1. | Double |
save_intermediate_output (Optional) | Specifies whether the intermediate outputs will be saved to the output location. The term intermediate outputs refers to the results generated after the model has been inferenced.
| Boolean |
test_time_augmentation (Optional) | Specifies whether predictions of flipped and rotated variants of the input image will be merged into the final output.
| Boolean |
buffer_distance (Optional) | The distance that will be used to buffer polyline features before they are used in postprocessing. The default is 15 meters. | Linear Unit |
extend_length (Optional) | The maximum distance a line segment will be extended to an intersecting feature. The default is 25 meters. | Linear Unit |
smoothing_tolerance (Optional) | The tolerance used by the Polynomial Approximation with Exponential Kernel (PAEK) algorithm. The default is 30 meters. | Linear Unit |
dangle_length (Optional) | The length at which line segments that do not touch another line at both endpoints (dangles) will be trimmed. The default is 5 meters. | Linear Unit |
in_road_features (Optional) | A road feature class that will be used for refining the parcels. The input can be a polygon or polyline feature class. | Feature Layer; Feature Class |
road_buffer_width (Optional) | The buffer distance that will be used for the Input Road Features value. The default value is 5 meters for polyline features and 0 meters for polygon features. | Linear Unit |
regularize_parcels (Optional) | Specifies whether extracted parcels will be normalized by eliminating undesirable artifacts in their geometry.
| Boolean |
post_processing_workflow (Optional) | Specifies the postprocessing workflow that will be used.
| String |
out_features (Optional) | The feature class containing the postprocessed output. | Feature Class |
parcel_tolerance (Optional) | The minimum distance between coordinates before they are considered equal. This parameter is used to reduce slivers between extracted parcels. The default is 3 meters. | Linear Unit |
regularization_method (Optional) | Specifies the regularization method that will be used in postprocessing.
| String |
poly_tolerance (Optional) | The maximum distance that the regularized footprint can deviate from the boundary of its originating feature. The default is 1 meter. | Linear Unit |
Code sample
This example shows how to use the ExtractFeaturesUsingAIModels function.
# Name: ExtractFeaturesUsingAIModels.py
# Description: Extract features using pretrained deep learning models on imagery data.
# Import system modules
import arcpy
# Check out the ArcGIS Image Analyst extension license
arcpy.CheckOutExtension("ImageAnalyst")
# Set local variables
datapath = "path_to_training_data"
out_gdb = "path_to_gdb"
predictions = "output_prefix"
# Run Extract Features Using AI Models
arcpy.geoai.ExtractFeaturesUsingAIModels(in_raster=datapath,
mode="Infer and Postprocess",
out_location=out_gdb,
out_prefix=predictions,
area_of_interest=None,
pretrained_models="'Building Footprint Extraction - USA'",
additional_models=None,
confidence_threshold=None,
save_intermediate_output="TRUE",
test_time_augmentation=None,
buffer_distance="15 Meters",
extend_length="25 Meters",
smoothing_tolerance="30 Meters",
dangle_length="5 Meters",
in_road_features=None,
road_buffer_width=None,
regularize_parcels=None,
post_processing_workflow="",
out_features=None,
parcel_tolerance=None,
regularization_method="Right Angles",
poly_tolerance="1 Meters")This example shows how to use the ExtractFeaturesUsingAIModels function using Image Analyst.
# Name: ExtractFeaturesUsingAIModels.py
# Description: Extract features using pretrained deep learning models on imagery data.
# Import system modules
import arcpy
# Check out the ArcGIS Image Analyst extension license
arcpy.CheckOutExtension("ImageAnalyst")
# Set local variables
datapath = "path_to_training_data"
out_gdb = "path_to_gdb"
predictions = "output_prefix"
# Run Extract Features Using AI Models
arcpy.ia.ExtractFeaturesUsingAIModelsin_raster=datapath,
mode="Infer and Postprocess",
out_location=out_gdb,
out_prefix=predictions,
area_of_interest=None,
pretrained_models="'Building Footprint Extraction - USA'",
additional_models=None,
confidence_threshold=None,
save_intermediate_output="TRUE",
test_time_augmentation=None,
buffer_distance="15 Meters",
extend_length="25 Meters",
smoothing_tolerance="30 Meters",
dangle_length="5 Meters",
in_road_features=None,
road_buffer_width=None,
regularize_parcels=None,
post_processing_workflow="",
out_features=None,
parcel_tolerance=None,
regularization_method="Right Angles",
poly_tolerance="1 Meters")Environments
Licensing information
- Basic: No
- Standard: No
- Advanced: Requires Image Analyst