Available with Image Server
The Classify Objects Using Deep Learning tool runs a deep learning model on an imagery layer to produce a feature layer or table in which each input object is classified.
The output is a hosted feature layer.
The Classify Objects Using Deep Learning tool can be used to assess damaged buildings after a natural disaster. With a feature layer of building footprints and an imagery layer showing the damaged areas, the tool can indicate whether the existing buildings have been damaged.
The Classify Objects Using Deep Learning tool can be used to indicate tree canopy health for existing trees. With a feature layer of tree canopies and an imagery layer showing the current tree canopy, the tool can indicate whether the existing trees are healthy or under stress.
The Classify Objects Using Deep Learning tool includes configurations for input imagery layers, input feature layers, deep learning model, and result layer.
The Input layer(s) group includes the following parameters:
- Input imagery layer or feature layer is used to select an imagery layer or layers used to classify objects. The imagery layer selected should be based on the requirements of the deep learning model that will be used to classify the objects. The imagery layer may be multidimensional or an image collection.
- Input feature layer is used to select features indicating the positions to be classified. Each row in the input feature layer represents a single object. If no input feature layer is specified, it is assumed that each input image contains a single object to be classified.
- Processing mode specifies how the raster items in the imagery layer will be processed. Processing mode includes the following options:
- Process as mosaicked image—All raster items in the mosaic dataset or image service will be mosaicked together and processed. This is the default.
- Process all raster items separately—All raster items in the mosaic dataset or image service will be processed as separate images.
The Model settings group includes the following parameters:
- Model for object classification specifies the deep learning model used to classify the objects. The deep learning model needs to be located on ArcGIS Online to be selected in the tool. You can select your own model, publicly available in ArcGIS Online, or from ArcGIS Living Atlas of the World.
- Model arguments specifies the function arguments defined in the Python raster function class. Additional deep learning parameters and arguments for experiments and refinement are listed, such as a confidence threshold for adjusting the sensitivity. The names of the arguments are populated from the Python module.
- Output class label field name specifies the field name that will contain the classification label in the output hosted feature layer or table.
The Result layer group includes the following parameters:
- Output name determines the name of the layer that is created and added to the map. The name must be unique. If a layer with the same name already exists in your organization, the tool will fail and you will be prompted to use a different name.
- Save in folder specifies the name of a folder in My Content where the result will be saved.
Analysis environment settings are additional parameters that affect a tool's results. You can access the tool's analysis environment settings from the Environment settings parameter group.
This tool honors the following analysis environments:
This tool includes the following outputs:
- A hosted feature layer with the objects or features labeled based on the classification determined by the deep learning model.
- A table with the locations labeled based on the classification determined by the deep learning model.
This tool requires the following licensing and configurations:
- Creator or GIS Professional user type
- Publisher or Administrator role, or an equivalent custom role
- ArcGIS Image Server configured for deep learning raster analytics
Use the following resources to learn more: