Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision 		Previous revision
Last revision Both sides next revision
interimage:operators_documentation [2010/05/11 14:37]
tkorting 		interimage:operators_documentation [2014/06/04 15:13]
rsilva
Line 1: Line 1:
 [[interimage:​|InterIMAGE wiki]] ​ [[interimage:​|InterIMAGE wiki]] ​
- 
  
 ====== TerraAIDA Operators Documentation ====== ====== TerraAIDA Operators Documentation ======
 +Operators reference version: 1.0.6
 +
 +InterIMAGE is a multi-platform framework, written in C++, currently with implementations for LINUX and Windows operational systems. Moreover, InterIMAGE provides support for the integration of image processing operators in the interpretation process and, as such operators are treated as external programs by its control mechanism, they can be coded in any computer language, and even in proprietary programs. The InterIMAGE framework offers, nonetheless,​ a repository of operators, called TerraAIDA ([[http://​www.dpi.inpe.br/​terraaida]]),​ assembled with software classes and functions supplied by the [[http://​www.terralib.org/​|TerraLib]] library.
 +
 +
  
-===== TerraAIDA ​Arithmetic =====+===== TA Arithmetic =====
  
 **Authors** ​ **Authors** ​
Line 13: Line 17:
 **Description**  ​ **Description**  ​
  
-Generate segments based on the threshold image resultant from an arithmetic operation from the given input images.+Generate segments based on the threshold image. It is the result of an arithmetic operation from the given input images.
  
 **Type** **Type**
Line 25: Line 29:
 **Multi-Class support** **Multi-Class support**
  
-Yes. If you select //true// in the "Top Down Multi-Class"​ option, you must create another node in the same level with a corresponding opposite name, with prefix "​n-"​. For example, if this class name is "​MyClass"​ the opposite class name will be "​n-MyClass"​. Hypothesis discarded by this operator will be classified as "​n-MyClass"​. ​+Yes. If you select //true// in the "Top Down Multi-Class"​ option, you must create another node in the same level with a corresponding opposite name, with prefix "​n-"​. For example, if this class name is "​MyClass"​ the opposite class name will be "​n-MyClass"​. Hypothesis discarded by this operator will be classified as "​n-MyClass"​. Alternatively,​ you can define a new node name in the input parameter named **Non Class Name**.
  
 [[interimage:​example_supervised_c45|Example of using Multi-Class support.]] [[interimage:​example_supervised_c45|Example of using Multi-Class support.]]
Line 47: Line 51:
 | Polygons Min Area     | Integer | Generated polygons minimum allowed area (pixels). ​ |  | Only polygons with area greater than the supplied values will generate hypothesis. | | Polygons Min Area     | Integer | Generated polygons minimum allowed area (pixels). ​ |  | Only polygons with area greater than the supplied values will generate hypothesis. |
 | Dummy Value (no data)     | Floating point | The dummy value from input images. |  | If not present, all image data will be processed. | | Dummy Value (no data)     | Floating point | The dummy value from input images. |  | If not present, all image data will be processed. |
-| Arithmetic Expression ​    | String | One valid arithmetic expression, formed by a combination of the following elements, separated by spaces. | Operators: +, -, *, /, Real Numbers, Raster indexes and bands R0:1, R1:2 | Example: Quickbird-2 image with bands (0=B,​1=G,​2=R,​3=NIR),​ the NDVI is calculated by ( R0:3 - R0:2 ) / ( R0:3 + R0:2 ). |+| Arithmetic Expression ​    | String | One valid arithmetic expression, formed by a combination of the following elements, separated by spaces. | Operators: +, -, *, /, Real Numbers, Raster indexes and bands R0:1, R1:2 | Example: Quickbird-2 image with bands (0=B,​1=G,​2=R,​3=NIR),​ the NDVI is calculated by ( R0:3 - R0:2 ) / ( R0:3 + R0:2 ). **The blank space around the mathematical operators +, -, *, / are mandatory.** ​|
 | Morphological Filter Iterations | Integer | Number of morphological (mode) iterations applied to the result. | Greater or equal to 0. | The use of a value greater than or equal to 1 is advised to avoid the creation of to small hypothesis | | Morphological Filter Iterations | Integer | Number of morphological (mode) iterations applied to the result. | Greater or equal to 0. | The use of a value greater than or equal to 1 is advised to avoid the creation of to small hypothesis |
-| Training Set File | *.shp | A file with training samples for supervised classification. | The file must be in the InterIMAGE ​regions ​format. | |+| Training Set File | *.shp | A file with training samples for supervised classification. | The file must be in the InterIMAGE ​region ​format. | |
 | Decision Rule | Decision Rule | Decision rule applied to the generated hypothesis. | | Leave blank to accept all generated hypothesis. | | Decision Rule | Decision Rule | Decision rule applied to the generated hypothesis. | | Leave blank to accept all generated hypothesis. |
-| Node Weight ​    | Floating point | This node weight ​(higher priority will be given to nodes with higher weights in cases where there are geographic overlays). ​ | [0.0, 1.0] |  |+| Reliability ​    | Floating point | The reliability ​(higher priority will be given to nodes with higher weights in cases where there are geographic overlays). ​ | [0.0, 1.0] |  ​| 
 +| Non Class Name  | String | If Multi-Class support is active, the discarded hypothesis will fall in the node named by this parameter. | One string with the name of some node in the tree, in the same level. | |
  
-===== TerraAIDA ​Baatz Segmenter =====+===== TA Baatz Segmenter =====
  
 **Authors** ​ **Authors** ​
Line 62: Line 67:
 **Description**  ​ **Description**  ​
  
-This operator performs a Baatz based segmentation (see the reference article for more information). Each generated segment represents an hypothesis to be analyzed by the next semantic network node.+This operator performs a segmentation ​based on Baatz (see the reference article for more information). Each generated segment represents an hypothesis to be analyzed by the next semantic network node.
  
 **Type** **Type**
Line 78: Line 83:
 ** Reference** ** Reference**
  
-  * Baatz, M.; Schape, A. Multiresolution segmentation:​ an optimization approach for high quality multi-scale image segmentation. In: XII Angewandte Geographische Informationsverarbeitung,​ Wichmann-Verlag, Heidelberg, 2000.+  * Baatz, M.; Schäpe, A. Multiresolution segmentation:​ an optimization approach for high quality multi-scale image segmentation. In: XII Angewandte Geographische Informationsverarbeitung,​ Wichmann Verlag, Heidelberg, 2000.
  
 **Processing sequence** **Processing sequence**
Line 99: Line 104:
 | Training Set File | *.shp | A file with training samples for supervised classification. | The file must be in the InterIMAGE regions format. | | | Training Set File | *.shp | A file with training samples for supervised classification. | The file must be in the InterIMAGE regions format. | |
 | Decision Rule | Decision Rule | Decision rule applied to the generated hypothesis. ​ |  | Leave blank to accept all generated hypothesis. | | Decision Rule | Decision Rule | Decision rule applied to the generated hypothesis. ​ |  | Leave blank to accept all generated hypothesis. |
-| Node Weight ​    | Floating point | This node weight ​(higher priority will be given to nodes with higher weights in cases where there are geographic overlays). ​ | [0.0, 1.0] |  | +| Reliability ​    | Floating point | The reliability ​(higher priority will be given to nodes with higher weights in cases where there are geographic overlays). ​ | [0.0, 1.0] |  | 
-| Euclidean Distance Threshold | Floating point   | The minimum ​euclidean distance ​between each segment feature. | Greater than 0.  | This parameter is required to merge adjacent ​blocks ​segments when the optimization option is enabled |+| Euclidean Distance Threshold | Floating point   | The minimum ​Euclidean Distance ​between each segment feature. | Greater than 0.  | This parameter is required to merge adjacent ​block segments when the optimization option is enabled |
  
-===== TerraAIDA ​Checkerboard Segmenter =====+===== TA Bottom-Up Export ===== 
 + 
 +**Author**  
 + 
 +Emiliano Castejon, [[castejon@dpi.inpe.br]]\\ 
 + 
 +**Description** ​  
 + 
 +Allows to export the bottom-up hypothesis (including its attributes) to a shape file. This operator acts like the generic bottom-up operator, making a copy of every hypothesis to the shape file. No spatial conflict resolution is performed when there is no decision rule. 
 + 
 +**Type** 
 + 
 +Bottom-Up operator. 
 + 
 +**Applies to** 
 + 
 +Root (scene) and internal nodes. 
 + 
 +**Multi-Class support** 
 + 
 +No. 
 + 
 +**Processing sequence** 
 + 
 +  -Read input hypothesis 
 +  -Apply the user decision rule using the supplied training set. 
 +  -Generate the output hypothesis 
 +  -Generate the output shape file 
 + 
 +**Input parameters** 
 +  
 +^ Parameter Name  ^ Type            ^ Description ​              ​^ ​  Valid Values ​     ^   ​Note ​  ​^ ​   
 +| Shape File Name | * .shp | Shape file name.   | A valid shape file name.  | The shapefile will be composed only by polygons and their respective attributes. ​ | 
 +| Decision Rule | Decision Rule | Decision rule applied to the input hypothesis. | | At least the spatial resolve rule must be present. | 
 + 
 +{{ interimage:​buexport.png }} 
 + 
 +===== TA C4.5 Classifier ===== 
 + 
 +**Author**  
 + 
 +Thales Sehn Korting, [[tkorting@dpi.inpe.br]]\\ 
 + 
 +**Description** ​  
 + 
 +Use C4.5 Decision Tree Algorithm to perform supervised classification into shapefiles with attributes and class description. 
 + 
 +**Type** 
 + 
 +Top-Down operator. 
 + 
 +**Applies to** 
 + 
 +Any node. 
 + 
 +**Multi-Class support** 
 + 
 +Yes. You must create the same number of classes as the training file. The classes must have also the same name of the training file. One of the nodes must have this operator, and all others should have "No Operator"​ for Top-Down and Bottom-Up options, and must have the option "​Multi-Class"​ selected as well. 
 + 
 +**Input parameters** 
 +  
 +^ Parameter Name  ^ Type            ^ Description ​              ​^ ​  Valid Values ​     ^   ​Note ​  ​^ ​   
 +| a) Training Set File | * .shp | Training shape file name.   | A valid shape file name.  | The shapefile must be composed by polygons, their respective attributes and particularly one attribute called "​class"​. ​ | 
 +| b) Input Shape File | *.shp | Shape file name of the file to be classified. | A valid shape file name. | The shapefile must be composed by polygons, and the **same set of attributes** in the training shape file. | 
 + 
 +Note: The generated decision tree will be placed in a //.txt// file, located in the **same place as your input shape file**, with the same name as your input file. 
 + 
 +One example of this operator can be found [[interimage:​examples:​supervised_c45|here]]. 
 + 
 + 
 + 
 + 
 +===== TA Checkerboard Segmenter =====
  
 **Author** ​ **Author** ​
Line 111: Line 188:
  
 This operator creates a rectangular grid according to user defined resolution. ​ This operator creates a rectangular grid according to user defined resolution. ​
-Every rectangle will be a segment for the next nodes.+Every rectangle will be a segment for the child nodes.
  
 **Type** **Type**
Line 128: Line 205:
    
 ^ Parameter Name  ^ Type            ^ Description ​              ​^ ​  Valid Values ​     ^   ​Note ​  ​^ ​   ^ Parameter Name  ^ Type            ^ Description ​              ​^ ​  Valid Values ​     ^   ​Note ​  ​^ ​  
-| Size of Cells | Integer ​        ​| Size of cells in pixels.   | Greater than zero.  |          | +| Number ​of grid lines | Integer ​  ​| Number ​of lines to divide the image.   | Greater than zero.  |          | 
-| Training Set File | *.shp         | A file with training samples for supervised classification. | The file must be in the InterIMAGE regions format. ​|   | +| Number of grid columns ​| Integer | Number of columns to divide the image.   ​| Greater than zero.  |          | 
-| Decision Rule   | Decision rule   | Decision rule applied ​in the generated hypothesis. | | Leave blank to accept all generated hypothesis. | +| Amount of points ​in X | Integer | Number of pixels per cell in X dimension. ​  ​| Greater than zero.  |          ​| 
-| Node Weight ​    | Floating point | This node weight ​(higher priority will be given to nodes with higher weights in cases where there are geographic overlays). | [0.0, 1.0] |  |+| Amount of points in Y | Integer ​| Number of pixels per cell in Y dimension.     ​| Greater than zero.  ​| ​         ​| 
 +| Reliability ​    | Floating point | The reliability ​(higher priority will be given to nodes with higher weights in cases where there are geographic overlays). | [0.0, 1.0] |  | 
  
-===== TerraAIDA ​NDVI Segmenter =====+===== TA NDVI Segmenter =====
  
 **Authors** ​ **Authors** ​
Line 158: Line 237:
 **Multi-Class support** **Multi-Class support**
  
-Yes. If you select //true// in the "Top Down Multi-Class"​ option, you must create another node in the same level with a corresponding opposite name, with prefix "​n-"​. For example, if this class name is "​MyClass"​ the opposite class name will be "​n-MyClass"​. Hypothesis discarded by this operator will be classified as "​n-MyClass"​. ​+Yes. If you select //true// in the "Top Down Multi-Class"​ option, you must create another node in the same level with a corresponding opposite name, with prefix "​n-"​. For example, if this class name is "​MyClass"​ the opposite class name will be "​n-MyClass"​. Hypothesis discarded by this operator will be classified as "​n-MyClass"​. Alternatively,​ you can define a new node name in the input parameter named **Non Class Name**.
  
 [[interimage:​example_supervised_c45|Example of using Multi-Class support.]] [[interimage:​example_supervised_c45|Example of using Multi-Class support.]]
Line 182: Line 261:
 | Training Set File | *.shp | A file with training samples for supervised classification. | The file must be in the InterIMAGE regions format. | | | Training Set File | *.shp | A file with training samples for supervised classification. | The file must be in the InterIMAGE regions format. | |
 | Decision Rule | Decision Rule | Decision rule applied to the generated hypothesis. | | Leave blank to accept all generated hypothesis. | | Decision Rule | Decision Rule | Decision rule applied to the generated hypothesis. | | Leave blank to accept all generated hypothesis. |
-| Node Weight ​| Floating point | This node weight ​(higher priority will be given to nodes with higher weights in cases where there are geographic overlays). | [0.0, 1.0] |  |+| Reliability ​    | Floating point | The reliability ​(higher priority will be given to nodes with higher weights in cases where there are geographic overlays). | [0.0, 1.0] |  ​| 
 +| Non Class Name  | String | If Multi-Class support is active, the discarded hypothesis will fall in the node named by this parameter. | One string with the name of some node in the tree, in the same level. | |
  
-===== TerraAIDA ​Region Growing Segmenter =====+===== TA Region Growing Segmenter =====
  
 **Authors** ​ **Authors** ​
Line 209: Line 289:
 ** Reference** ** Reference**
  
-  * [[http://​citeseerx.ist.psu.edu/​viewdoc/​download?​doi=10.1.1.93.4555&​rep=rep1&​type=pdf|Bins,​ L.S.; Fonseca, L.M.G.; Erthal, G.J.; Ii, F.M. Satellite imagery segmentation:​ a region growing approach. VIII Simpósio Brasileiro de Sensoriamento Remoto, Salvador, BA. Pages 677-680. 1996.]]+  * [[http://​citeseerx.ist.psu.edu/​viewdoc/​download?​doi=10.1.1.93.4555&​rep=rep1&​type=pdf|Bins,​ L.S.; Fonseca, L.M.G.; Erthal, G.J.; Ii, F.M. Satellite imagery segmentation:​ a region growing approach. VIII Simpósio Brasileiro de Sensoriamento Remoto, Salvador, BA. p. 677-680. 1996.]]
  
 **Processing sequence** **Processing sequence**
Line 222: Line 302:
 ^ Parameter Name  ^ Type            ^ Description ​              ​^ ​  Valid Values ​     ^   ​Note ​  ​^ ​   ^ Parameter Name  ^ Type            ^ Description ​              ​^ ​  Valid Values ​     ^   ​Note ​  ​^ ​  
 | Input Image | * .tif  | Input image file name.   | A valid image file name.  | The image type must be supported by TerraLib. | | Input Image | * .tif  | Input image file name.   | A valid image file name.  | The image type must be supported by TerraLib. |
-| Euclidean Distance Threshold | Floating point   | The minimum ​euclidean distance ​between each segment feature. | Greater than 0.  | |+| Euclidean Distance Threshold | Floating point   | The minimum ​Euclidean Distance ​between each segment feature. | Greater than 0.  | |
 | Polygons Min Area | Integer | The generated polygons minimum area.  | Greater than 0. |  | | Polygons Min Area | Integer | The generated polygons minimum area.  | Greater than 0. |  |
 | Use Optimization | Boolean | Divides, or not, the image into pieces and segment each piece individually. | yes/no | | | Use Optimization | Boolean | Divides, or not, the image into pieces and segment each piece individually. | yes/no | |
 | Training Set File | *.shp | A file with training samples for supervised classification. | The file must be in the InterIMAGE regions format. | | | Training Set File | *.shp | A file with training samples for supervised classification. | The file must be in the InterIMAGE regions format. | |
 | Decision Rule | Decision Rule | Decision rule applied to the generated hypothesis. ​ |  | Leave blank to accept all generated hypothesis. | | Decision Rule | Decision Rule | Decision rule applied to the generated hypothesis. ​ |  | Leave blank to accept all generated hypothesis. |
-| Node Weight ​| Floating point | This node weight ​(higher priority will be given to nodes with higher weights in cases where there are geographic overlays). ​ | [0.0, 1.0] |  |+| Reliability ​    | Floating point | The reliability ​(higher priority will be given to nodes with higher weights in cases where there are geographic overlays). ​ | [0.0, 1.0] |  |
  
 ** Segmentation Example** ** Segmentation Example**
Line 235: Line 315:
  
  
-===== TerraAIDA ​ShapeFile Import =====+===== TA ShapeFile Import =====
  
 **Authors** ​ **Authors** ​
Line 260: Line 340:
 **Notes** **Notes**
  
-Shape files attributes with the the folowing ​names will not be imported: REGION, CLASS, ID, GEOWEST, GEONORTH, GEOEAST, GEOSOUTH, FILE_GEOWEST,​ FILE_GEONORTH,​ FILE_GEOEAST,​ FILE_GEOSOUTH,​ P, FILE, LLX, LLY, URX, URY.+Shape file attributes with the the following ​names will not be imported: REGION, CLASS, ID, GEOWEST, GEONORTH, GEOEAST, GEOSOUTH, FILE_GEOWEST,​ FILE_GEONORTH,​ FILE_GEOEAST,​ FILE_GEOSOUTH,​ P, FILE, LLX, LLY, URX, URY. 
 + 
 +**Processing sequence** 
 + 
 +  -Read user input shape file. 
 +  -Generates the intersection between the loaded shape file polygons and the operator execution area. 
 +  -Apply the user decision rule (using the supplied training set) over the intersection ​ polygons. 
 +  -Generate the output hypothesis.
  
 **Input parameters** **Input parameters**
Line 267: Line 354:
 | Shape File Name | * .shp | Shape file name.   | A valid shape file name.  | The shapefile must be composed only by polygons, neither lines nor polylines. ​ | | Shape File Name | * .shp | Shape file name.   | A valid shape file name.  | The shapefile must be composed only by polygons, neither lines nor polylines. ​ |
 | Shape File Attributes | String | A comma-separated list of shape file attributes names to be imported. | A valid attribute ID or empty field. ​ | Leave blank to use all shape file attributes. | | Shape File Attributes | String | A comma-separated list of shape file attributes names to be imported. | A valid attribute ID or empty field. ​ | Leave blank to use all shape file attributes. |
-| Label Image Resolution | Floating point | The output label image resolution. | Positive real numbers or zero for automatic. | Choose a value good enough matching the resolution of the best used image. Leave blank and the system will automatically choose the resolution. The automatic method ​only can be used if the operator ​are not in the semantic network node right above the "​scene"​ node. | +| Label Image Resolution | Floating point | The output label image resolution. | Positive real numbers or zero for automatic. | Choose a value good enough matching the resolution of the best used image. Leave blank and the system will automatically choose the resolution. The automatic method can be used only if the operator ​is not in the semantic network node right above the "​scene"​ node. | 
-| Training Set File | *.shp | A file with training samples for supervised classification. | The file must be in the InterIMAGE ​regions ​format. | |+| Training Set File | *.shp | A file with training samples for supervised classification. | The file must be in the InterIMAGE ​region ​format. | |
 | Decision Rule     | Decision rule | Decision rule applied to the generated hypothesis. ​ |  | Leave blank to accept all generated hypothesis. | | Decision Rule     | Decision rule | Decision rule applied to the generated hypothesis. ​ |  | Leave blank to accept all generated hypothesis. |
-| Node Weight ​    | Floating point | This node weight ​(higher priority will be given to nodes with higher weights in cases where there are geographic overlays). ​ | [0.0, 1.0] |  |+| Reliability ​    | Floating point | The reliability ​(higher priority will be given to nodes with higher weights in cases where there are geographic overlays). ​ | [0.0, 1.0] |  |
  
 {{ :​interimage:​shape_file_import_example.png }} {{ :​interimage:​shape_file_import_example.png }}
  
-===== TerraAIDA ​ShapeFile Intersection =====+===== TA ShapeFile Intersection =====
  
 **Authors** ​ **Authors** ​
Line 295: Line 382:
 **Multi-Class support** **Multi-Class support**
  
-Yes. If you select //true// in the "Top Down Multi-Class"​ option, you must create another node in the same level with a corresponding opposite name, with prefix "​n-"​. For example, if this class name is "​MyClass"​ the opposite class name will be "​n-MyClass"​. Hypothesis discarded by this operator will be classified as "​n-MyClass"​. ​+Yes. If you select //true// in the "Top Down Multi-Class"​ option, you must create another node in the same level with a corresponding opposite name, with prefix "​n-"​. For example, if this class name is "​MyClass"​ the opposite class name will be "​n-MyClass"​. Hypothesis discarded by this operator will be classified as "​n-MyClass"​. Alternatively,​ you can define a new node name in the input parameter named **Non Class Name**.
  
 [[interimage:​example_supervised_c45|Example of using Multi-Class support.]] [[interimage:​example_supervised_c45|Example of using Multi-Class support.]]
 +
 +**Processing sequence**
 +
 +  -Read user input shape file.
 +  -Generates the intersection between the loaded shape file polygons and the operator execution area.
 +  -Using the intersection result generates a set of intermediate hypothesis of "​MyClass"​ and the opposite class "​n-MyClass",​ as describe above.
 +  -Apply the user decision rule (using the supplied training set) over the intermediate hypothesis set.
 +  -Generate the output hypothesis from the decision rule result.
  
 **Input parameters** **Input parameters**
Line 305: Line 400:
 | Shape Target Attribute ID | String | The name of the shape file attribute column used to filter what shape files polygons will be used. | A valid attribute ID. | Leave blank to use all shape file polygons. | | Shape Target Attribute ID | String | The name of the shape file attribute column used to filter what shape files polygons will be used. | A valid attribute ID. | Leave blank to use all shape file polygons. |
 | Shape Target Attribute Value | String | The value, from the shape target attribute ID, which will define what polygons will be selected. |  | Leave blank to use all shape file polygons. | | Shape Target Attribute Value | String | The value, from the shape target attribute ID, which will define what polygons will be selected. |  | Leave blank to use all shape file polygons. |
-| Label Image Resolution | Floating point | The output label image resolution. | Positive real numbers or zero for automatic. | Choose a value good enough matching the the resolution of the best used image. Leave blank and the system will automatically choose the resolution. The automatic method ​only can be used if the operator ​are not in the semantic network node right above the "​scene"​ node. |+| Label Image Resolution | Floating point | The output label image resolution. | Positive real numbers or zero for automatic. | Choose a value good enough matching the the resolution of the best used image. Leave blank and the system will automatically choose the resolution. The automatic method can be used only if the operator ​is not in the semantic network node right above the "​scene"​ node. |
 | Training Set File | *.shp | A file with training samples for supervised classification. | The file must be in the InterIMAGE regions format. | | | Training Set File | *.shp | A file with training samples for supervised classification. | The file must be in the InterIMAGE regions format. | |
 | Decision Rule | Decision Rule | Decision rule applied to the generated hypothesis. | | Leave blank to accept all generated hypothesis. | | Decision Rule | Decision Rule | Decision rule applied to the generated hypothesis. | | Leave blank to accept all generated hypothesis. |
-| Node Weight ​| Floating point | This node weight ​(higher priority will be given to nodes with higher weights in cases where there are geographic overlays). ​ | [0.0, 1.0] |  |+| Reliability ​    | Floating point | The reliability ​(higher priority will be given to nodes with higher weights in cases where there are geographic overlays). ​ | [0.0, 1.0] |  ​| 
 +| Non Class Name  | String | If Multi-Class support is active, the discarded hypothesis will fall in the node named by this parameter. | One string with the name of some node in the tree, in the same level. | |
  
 {{ :​interimage:​shape_file_intersection_example.png }} {{ :​interimage:​shape_file_intersection_example.png }}
- 
- 
- 
- 
-===== TerraAIDA Bottom-Up Export ===== 
- 
-**Authors** ​ 
- 
-Emiliano Castejon, [[castejon@dpi.inpe.br]]\\ 
- 
-**Description**  ​ 
- 
-Allows to export the bottom-up hypothesis (including their attributes) to a shape file. This operator acts like the generic bottom-up operator by making a copy of every hypothesis to the shape file. No spatial conflict resolution is performed when there is no decision rule. 
- 
-**Type** 
- 
-Bottom-Up operator. 
- 
-**Applies to** 
- 
-Root (scene) and internal nodes. 
- 
-**Multi-Class support** 
- 
-No. 
- 
-**Processing sequence** 
- 
-  -Read input hypothesis 
-  -Apply the user decision rule using the supplied training set. 
-  -Generate the output hypothesis 
-  -Generate the output shape file 
- 
-**Input parameters** 
-  
-^ Parameter Name  ^ Type            ^ Description ​              ​^ ​  Valid Values ​     ^   ​Note ​  ​^ ​   
-| Shape File Name | * .shp | Shape file name.   | A valid shape file name.  | The shapefile will be composed only by polygons and their respective attributes. ​ | 
-| Decision Rule | Decision Rule | Decision rule applied to the input hypothesis. | | At least the spatial resolve rule must be present. | 
- 
-{{ interimage:​buexport.png }} 
- 
-===== TerraAIDA C4.5 Classifier ===== 
- 
-**Authors** ​ 
- 
-Thales Sehn Korting, [[tkorting@dpi.inpe.br]]\\ 
- 
-**Description**  ​ 
- 
-Use C4.5 Decision Tree Algorithm to perform supervised classification into shapefiles with attributes and classes description. 
- 
-**Type** 
- 
-Top-Down operator. 
- 
-**Applies to** 
- 
-Any node. 
- 
-**Multi-Class support** 
- 
-Yes. You must create the same number of classes as the training file. The classes must have the same name of the training file also. One of the nodes must have this operator, and all others should have "No Operator"​ for Top-Down and Bottom-Up options, and must have the option "​Multi-Class"​ selected as well. 
- 
-**Input parameters** 
-  
-^ Parameter Name  ^ Type            ^ Description ​              ​^ ​  Valid Values ​     ^   ​Note ​  ​^ ​   
-| a) Training Set File | * .shp | Training shape file name.   | A valid shape file name.  | The shapefile must be composed by polygons, their respective attributes and particularly one attribute called "​class"​. ​ | 
-| b) Input Shape File | *.shp | Shape file name of the file to be classified. | A valid shape file name. | The shapefile must be composed by polygons, and the *same set of attributes* in the training shape file. | 
- 
-One example of this operator can be found [[interimage:​example_supervised_c45|here]]. 

Trace:

Navigation

Wiki start

DPI