20

Ideally there would be some way to convert EE image objects to sklearn-readable NumPy arrays directly using the EE Python API. ee.Image.sampleRectangle() does this. However, there is a limit of 262144 pixels that can be transferred. The interactive data transfer limit is in place to protect your system from hanging (it is easy to request terabytes of data ...


16

Generating LiDAR DEMs from unclassified point clouds with: MCC-LIDAR - Multiscale Curvature Classification (MCC) algorithm. (supports LAS versions 1.1 to 1.3) MCC-LIDAR is a command-line tool for processing discrete-return LIDAR data in forested environments (Evans & Hudak, 2007). Workflow: a) unclassified point cloud. b) ground returns ...


15

As far as pixel-based classification is concerned, you are spot on. Each pixel is an n-dimensional vector and will be assigned to some class according to some metric, whether using Support Vector Machines, MLE, some kind of knn classifier, etc. As far as region based classifiers are concerned, though, there have been huge developments in the last few years, ...


12

Equal_Interval "the range is then divided by the number of classes" http://wiki.gis.com/wiki/index.php/Equal_Interval_classification Quantiles " for visualizing continuous data that is not distributed normally" http://wiki.gis.com/wiki/index.php/Geometric_Interval_Classification Natural Breaks "method designed to optimize the arrangement of a ...


12

You need to use Rule based style to set the scale for primary, secondary and tertiary network, as you can see below (but with different data): You can double-click each styled label to get more details:


11

There is a considerable body of literature on individual crown detection in spectral and lidar data. Methods wise, perhaps start with: Falkowski, M.J., A.M.S. Smith, P.E. Gessler, A.T. Hudak, L.A. Vierling and J.S. Evans. (2008). The influence of conifer forest canopy cover on the accuracy of two individual tree measurement algorithms using lidar data. ...


11

Your understanding is generally correct, however, there are dangers in your description of the object based classification - the term 'object' refers to the group of pixels, not whether or not it contains a given object. Furthermore, the central goal in a object-based classification is not to have segments of equal size, but to have "chopped"/segmented the ...


10

One giant Multipolygon per class isn't going to scale very well, but it's not hard to produce that. var geometry = ee.Geometry.Rectangle([29.1796875, 32.02670629333615, 32.607421875, 29.993002284551075]); var landcover = ee.Image('MCD12Q1/MCD12Q1_005_2001_01_01').select('Land_Cover_Type_1'); // Run reduceToVectors per class by masking all other classes. ...


9

The term spectral signature refers to the relationship between the wavelength (or frequency) of electromagnetic radiation and the reflectance of the surface. The signature is affected by several things including the material composition and structure. Some parts of the EMR spectrum, such as the microwave region, are more sensitive to surface structure than ...


9

The intensity image should be used for calibration and subsequent classification of geophysical features. To radiometrically calibrate the intensity, use the Calibrate tool in the Sentinel-1 Toolbox (SAR Processing > Radiometric > Calibrate). The S-1 Level 1 GRD product includes several Look-Up Tables (LUTs) to convert intensity values into sigma or gamma ...


9

You may apply a reclassification by right-clicking on the layer in the Layers Panel and then clicking on Properties: from the dialog that appears, go to Style and then set these parameters (you can adapt them following your specific needs): Please note that in step No.5 you set Equal interval as Mode, but you only do this for the possibility of editing the ...


9

sample() uses 1 region (either points or polygons) and does exhaustive sampling in that region (all pixels) unless you specify a smaller number of points. But the random sampling it does isn't optimal. sampleRegions uses multiple regions (either points or polygons) and does exhaustive sampling in each region (all pixels). There are no options for ...


9

Looking at the code, QGIS will take the exact values if there are up to 3000 features. Otherwise, it will take the largest between 3000 random features or a random 10% of the data.


8

I think that LasTools might suit your needs, see LASGround. The license is a bit funny depending on what tools. The tools can be downloaded and evaluated prior to purchase; also the product is relatively inexpensive.


8

Classification algorithms such as Maximum Liklihood, random forests, and SVM are statistical methods for grouping data. These data may be words, colors, sounds or anything you can imagine. In a remote sensing context, these algorithms are used to group pixels or image objects (segments) based on statistical properties, or spectral profiles. To answer ...


8

The Supplementary Materials (SM) for the Science article provides references to a number of different journal-articles that outline various parts of the methodology. The SM can be found here Extending the time-series to include Landsat-5 (and potentially Landsat-8 to make the methodology something that can be rerun "easily") data will be a challenging task,...


8

In terms of something akin to a spectral signature, the only way would be through the return intensity values, which are rarely calibrated. Unfortunately, there is really nothing expected in the characteristics of the return intensity that would separate rock and soil, the answer really is that this is not a likely outcome. Now, if you used surface texture ...


7

As troubleshot by @Paul, the error message is being triggered because you have placed your *.gsg file inside of a file geodatabase folder (*.gdb). It seems like the Maximum Likelihood Classification tool is getting confused by this. However, the error can be easily avoided by ensuring that your *.gsg file is NOT inside of a file geodatabase folder (*.gdb). ...


7

those are different things. Image classification is the process of creating a thematic image where each pixel is assigned a number representing a class (can include the class 'unclassified'). In an aerial image the classes can be soil, vegetation, water etc. image classification algorithms examples are k-means or ISO-DATA. Pattern recognition is the ...


7

I have had good luck with FUSION's (manual here) GroundFilter command. I've had no problem handling 40 million points (unclassified), so wouldn't expect an issue with 100 million.


7

A spectral signature is some measurable quantity (e.g., reflectivity, emissivity), which varies as a function of wavelength and can be used to identify a material. To obtain a signature, the quantity must be measured at a sufficient number of wavelengths (and at fine enough spectral resolution) such that the material can be discriminated from other materials....


7

Scikit-learn has some excellent unsupervised classification/clustering algorithms. The batched K-means algorithm works quickly with large datasets. Here is an example using the KEA file format. You will have to modify this slightly to work with whatever raster format you use. import rsgislib from rsgislib import imageutils from osgeo import gdal import ...


7

The general name for the operation that will allow you to compare two classified images is cross tabulation or what is sometimes called a contingency table. This will allow you to calculate change in class values. In the SAGA toolbox of QGIS there is a tool called Cross-classification and tabulation that will perform this operation.


7

I am the main developer of MGET. The first step in your problem is to obtain values of the covariates that you will use to fit the model to your 90 GPS points. It sounds like you want to use the 8 bands as your covariates. You need to add 8 fields to your shapefile (one for each band) and populate them using a tool such as Extract Multi Values to Points ...


7

The problem is you need to be escaping the pathnames. In Python (and many other programming languages) the single backslash \ is an escape character. See this page for an explanation. in the path "C:\Project\GIS\Grayscale\aug1951_clip_bw.gsg", the \a is an ascii Bell. You can see all the string literals here. You can properly format your pathnames many ...


7

First, for the answers proposed here, you probably do not want to use the ferry filter to push HeightAboveGround to Z, at least not prior to segmentation, as the act of normalizing heights involves subtracting an interpolated estimate of the ground elevation from each return. Something planar in the original X, Y, Z space may no longer be planar in the ...


7

Try using just the stratifiedSample algorithm: https://code.earthengine.google.com/e061f92736d8261f812db1dc2bfa8934 var ROI = ee.Geometry.Rectangle(-82.56277, 35.58935,-82.53436, 35.59996); // define area var features = ee.FeatureCollection([ ee.Feature(ee.Geometry.Rectangle(-82.56123, 35.59053,-82.55213, 35.59674),{class: 0}), ee.Feature(ee....


7

You can use graduted stylings for color and also size when using point or line features. In case of lines the size is used to classify the width. There you find also the options for natural breaks and other classifications.


6

By default, ArcGIS samples for classification by taking the first 10,000 records. This can be changed in the classification dialog by increasing the number of records used. For information on the implementation, I'd recommend seeing this mapping center post (and read Charlie Frye's comments since he worked on the original implementation)


6

Yes, image classification is generally improved when you remove topographic illumination effects (same goes with atmospheric effects). However, as with anything like this, there exists a wide range of techniques for accomplishing this task and the effectiveness of it will depend both on the sophistication of the technique (its ability to model the physical ...


Only top voted, non community-wiki answers of a minimum length are eligible