• Semi-automatic classification plugin v. 5: watch the trailer

    Semi-automatic classification plugin v. 5: watch the trailer

    It is assumed that you have a basic knowledge of QGIS. This tutorial aims to analyze land cover change using SCP Postprocessing tools. Basically, we are going to assess land cover change from two 1947 ford wiring diagram classifications, and relate the changes to a land use vector file.

    An overview of several postprocessing tools is also provided. Of course, this tutorial is designed for demonstration purposes and it is not endorsed by the European Union. The Copernicus High Resolution Layers are raster classifications with 20m spatial resolution.

    Several land cover classes are available, but in this tutorial we are going to use the Imperviousness Density for and The Imperviousness Density was produced using automatic derivation based on calibrated Normalized Difference Vegetation Index.

    You can find the detailed product specifications here.

    semi-automatic classification plugin v. 5: watch the trailer

    The vector is classified in 44 classes divided in 3 hierarchical levels with minimum mapping unit of 25 hectares. In this tutorial we are considering only the first level of Corine Land Coverdivided in these classes:.

    You can download the data for this tutorial from this archiveor use your own data two classification rasters and a land use vector. For this tutorial, the original Copernicus data were modified by clipping the rasters to a small area over Florence Italy.

    As you can see, the rasters have values from 0 torepresenting the degree of imperviousness. It is useful to refine the classification by photo-interpretation, especially for data produced by semi-automatic processing.

    We can use high resolution images or other services such as OpenStreetMap. For example you can follow this tutorial Download the Data to download satellite images, or you can download a subset of a Landsat 8 image, already converted to reflectance, from this link about 27 MB, data available from the U.

    First, we need to define a Band set containing a classification raster this is required for drawing ROIs. Band set definition. Optionally, we can create a band set for the satellite image to display a color composite; open the tab Band set and select all the Landsat bands in the list; click to add a new band set, then click to add selected rasters to the Band set 2.Post a comment.

    Version 5. It provides several tools for the download of free images, the preprocessing, the postprocessing, and the raster calculation please see What can I do with the SCP?

    The overall objective of SCP is to provide a set of intertwined tools for raster processing in order to make an automatic workflow and ease the land cover classification, which could be performed also by people whose main field is not remote sensing. The first version of the SCP was written by Luca Congedo in for the ACC Dar Project in order to create a tool for the classification of land cover in an affordable and automatic fashion read this working paper.

    Following versions of SCP were developed as personal commitment to the remote sensing field and open source software. In addition, the Brief Introduction to Remote Sensing page illustrates the basic concepts and definitions which are required for using the SCP. Basic Tutorials page are available for learning the main functions of SCP and Thematic Tutorials page illustrate specific tools.

    How to cite : Congedo Luca Semi-Automatic Classification Plugin Documentation. No comments:. Newer Post Older Post Home. Subscribe to: Post Comments Atom. Subscribe Posts Atom. Comments Atom. Follow by Email. Follow us on Facebook and YouTube.It provides several tools for the download of free images, the preprocessing, the postprocessing, and the raster calculation please see What can I do with the SCP?

    The overall objective of SCP is to provide a set of intertwined tools for raster processing in order to make an automatic workflow and ease the land cover classification, which could be performed also by people whose main field is not remote sensing. The first version of the SCP was written by Luca Congedo in for the ACC Dar Project in order to create a tool for the classification of land cover in an affordable and automatic fashion read this working paper.

    Following versions of SCP were developed as personal commitment to the remote sensing field and open source software. In addition, the Brief Introduction to Remote Sensing illustrates the basic concepts and definitions which are required for using the SCP. Basic Tutorials are available for learning the main functions of SCP and Thematic Tutorials illustrate specific tools. Several thousand people have already joined and posted hundreds of questions and comments.

    Also, please read the Frequently Asked Questions. Congedo Luca Semi-Automatic Classification Plugin Documentation. Except where otherwise noted, content of this work is licensed under a Creative Commons Attribution-ShareAlike 4. Navigation next previous Semi-Automatic Classification Plugin 5.The Main Interface Window is composed of several tabs described in detail in the following paragraphs. Tabs can be selected through the menu at the left side.

    Band set. Image input in SCP is named band set. This tab allows for the definition of one or more band sets used as input for classification and other tools. Band sets are identified by numbers. The active band set i. Other SCP tools allow for the selection of band set numbers.

    This section allows for the selection of a multiband raster. If selected, raster bands are listed in the active band set. List of single band rasters already loaded in QGIS. It is possible to select one or more bands to be added to the active band set.

    semi-automatic classification plugin v. 5: watch the trailer

    Definition of bands composing the band sets. The active band set is the tab selected with bold green name. It is possible to add new band sets clicking the following button:. Click the in the tab to remove the corresponding band set.

    semi-automatic classification plugin v. 5: watch the trailer

    Band sets can be reordered dragging the tabs. The Center wavelength of bands should be defined in order to use several functions of SCP.

    If the Center wavelength of bands is not defined, the band number is used and some SCP tools will be disabled. It is possible to define a multiplicative rescaling factor and additive rescaling factor for each band for instance using the values in Landsat metadatawhich are used on the fly i.

    It is possible to perform several processes directly on active band set.

    The tab Basic tools includes several tools for manipulating input data. RGB list. Algorithm band weight. This tab allows for the definition of band weights that are useful for improving the spectral separability of materials at certain wavelengths bands.

    During the classification process, band values and spectral signature values are multiplied by the corresponding band weights, thus modifying the spectral distances. A tab is displayed for every Band set. Multiple ROI Creation. This tab allows for the automatic creation of ROIs, useful for the rapid classification of multi-temporal images, or for accuracy assessment. Created ROIs are automatically saved to the Training input. The active band set in Band set is used for calculations.This tutorial is about the Land Cover Signature Classification.

    Open the tab Band setclick the button and select the bands of the downloaded Sentinel-2 image. In the table Band set definition order the band names in ascending order click to sort bands by name automaticallythen highlight band 8A i. Finally, select Sentinel-2 from the list Quick wavelength settingsin order to set automatically the Center wavelength of each band and the Wavelength unit required for spectral signature calculation.

    Band set definition. In the SCP dock click the button and define a file name for the Training input. Now create some ROIs. The Land Cover Signature Classification can use additional classification algorithms for pixels falling inside overlapping regions or outside any spectral region in this tutorial we are going to use Minimum Distancetherefore it is important that ROIs are homogeneous in order to train correctly the additional algorithm.

    Spectral signatures are displayed with the respective colors; also, the semi-transparent area represents the spectral range of each ROI. The minimum and maximum values of these spectral range are displayed in the Plot Signature list. You can manually edit these ranges or use the tools Automatic thresholds.

    It is worth noticing the same spectral ranges of spectral signatures in ROI Signature list are displayed in the Signature threshold. Now create a classification preview over the lake see Create a Classification Preview. Classification preview. You can see that several pixels are unclassified black because they are outside any spectral range.

    In the Plot Signature list highlight a signature of macroclass Water and click the button From pixel. This tool allows you to extend the spectral range to include a pixel signature.

    Click an unclassified pixel in the map over the lake; you should see that the spectral range of highlighted signature is larger now. Click the button in the Working toolbar.

    Now the area classified as water is larger and should include the pixel that was clicked before. Signature plot: the spectral range is extended. This way, the spectral range is extended to include the minimum and maximum value of this ROI for each band. Creating another classification preview we can see that the classified area is extended according to the temporary ROI.

    Particular attention should be posed on the spectral similarity of classes. For instance soil and built-up can have very similar spectral signatures.It is assumed that you have a basic knowledge of QGIS. This is a basic tutorial about the use of SCP for the classification of a multi-spectral image. It is recommended to read the Brief Introduction to Remote Sensing before this tutorial.

    Download the image from this archive data available from the U. Geological Survey and unzip the downloaded file. The downloaded file is actually a Landsat Satellite image pan-sharpened including the following bands:. In this tutorial we pretend this dataset is a generic multi-spectral raster in order to focus on the classification process in the next tutorial we are going to use an image whose bands are single rasters.

    Start QGIS. You can see that image colors in the map change according to the selected bands, and vegetation is highlighted in red if the item was selected, natural colors would be displayed. Now we need to create the Training input in order to collect Training Areas ROIs and calculate the Spectral Signature thereof which are used in classification.

    In the SCP dock click the button and define a name e. The path of the file is displayed in Training input. Definition of Training input in SCP. Zoom in the map over the dark area it is a lake in the lower right region of the image. In order to create manually a ROI inside the dark area, click the button in the Working toolbar you can ignore a message about wavelength unit not provided.

    Left click on the map to define the ROI vertices and right click to define the last vertex closing the polygon. An orange semi-transparent polygon is displayed over the image, which is a temporary polygon i.

    A temporary ROI created manually. If the shape of the temporary polygon is good we can save it to the Training input. Open the Classification dock to define the Classes and Macroclasses. Now click to save the ROI in the Training input. The ROI saved in the Training input. Now we are going to create a second ROI for the built-up class using the automatic region growing algorithm. Zoom in the map over the blue area in the upper left region of the image.

    In Working toolbar set the Dist value to 0. Click the button in the Working toolbar and click over the blue area of the map. After a while the orange semi-transparent polygon is displayed over the image.

    A temporary ROI created with the automatic region growing algorithm.The following is a basic tutorial about the use of the Semi-Automatic Classification Plugin.

    Using a semi-automatic approach we are going to rapidly classify a Landsat 8 image and estimate land cover area, in only six phases. Download the sample datasetwhich is a subset of a Landsat 8 image acquired over Rome, Italy on June 12, data available from the U. Geological Survey. The zip file can be extracted with any file archiver software for instance the open source 7-zip.

    The dataset includes the metadata file MTL. The pre processing phase is required before the actual image processing in order to improve the classification results. In addition, we are going to create a color composite of the image. We need to define the input image i. Now we are ready to collect the ROIs. ROIs are polygons drawn over homogeneous areas of the image that represent land cover classes.

    ROIs can be drawn manually or with a region growing process i. SCP calculates the spectral signatures which are used by classification algorithms considering the pixel values under each ROI.

    A Macroclass is a group of ROIs having different Class ID, which is useful when one needs to classify materials that have different spectral signatures in the same land cover class. For instance we could classify grass e. Macroclass example. Vegetation: trees. Vegetation: grass. After the collection of several ROIs, it is useful to display the spectral signatures thereof, in order to assess the spectral similarity:.

    You can download the final training shapefile and spectral signature listwhere 11 spectral signatures were collected. SCP allows for classification previewsin order to assess very rapidly the classification results. Classifications previews are useful during the collection of ROIs, and for the selection of the more accurate spectral signatures.

    If the preview results are considered good i. Otherwise, it is possible to remove one or more spectral signatures, or add new spectral signatures creating other ROIs as described in Collection of ROIs and Spectral Signatures. The final land cover classification can be downloaded from here. The accuracy assessment of land cover classification is useful for identifying map errors. SCP allows for the calculation of accuracy comparing the classification raster to a reference shapefile.

    Usually, accuracy assessment requires ancillary data and field survey. In this tutorial we are are going to compare the land cover classification to the training ROIs.

    The following error matrix represents the number of pixels classified correctly in the major diagonal. As you can see, most of the errors are between class 3 built-up and 4 bare soil.

    From the error matrix file, we have also calculated the accuracy of user and producer; the results show that class 4 bare soil has high commission error - user accuracy and low omission error - producer accuracy.

    In order to improve the results, we should collect more ROIs and spectral signatures for the bare soil class, paying attention to the spectral similarity with the built-up class.


    Comments

    Leave a Reply

    Your email address will not be published. Required fields are marked *