Episode #125 of the Stack Overflow podcast is here. We talk Tilde Club and mechanical keyboards. Listen now

Questions tagged [land-classification]

A cartographic delineation of distinct land areas, identified by their geology, topography, soils, vegetation, climate conditions, living species, habitats, water resources, as well as anthropic factors.

Filter by
Sorted by
Tagged with
37
votes
7answers
8k views

Machine Learning Algorithms for Land Cover Classification

I am interested in learning what software exists for land classification using machine learning algorithms (e.g. k-NN, Random Forest, decision trees, etc.) I am aware of the randomForest package in R ...
32
votes
4answers
14k views

How to perform Random Forest land cover classification?

This is a follow-up to a previous post: Machine Learning Algorithms for Land Cover Classification. It seems that the Random Forest (RF) classification method is gaining much momentum in the remote ...
12
votes
2answers
321 views

Ice type differentiation using satellite data

I would like to classify glacial area by categories of snow (if there is) and ice, but what's most important: between old ice and fresh ice. They have different properties that are possible to ...
9
votes
1answer
420 views

Confidence in pan-sharpened classification?

I pan-sharpened one Landsat Image on ERDAS using the resolution merge resource, with brovey transform and nearest neighbor techniques. But I was told that in terms of land-use classification, it would ...
9
votes
1answer
3k views

Is machine learning used much in GIS?

I'm new to GIS. Is machine learning used much in this field, and where? I'm investigating a job opportunity with a mapping company working on traffic awareness. My background is in supervised machine ...
7
votes
1answer
2k views

How to Remove Topographic Effects Like Shadows from Landsat Image

I am using QGIS 2.4.0 Chugiak on my windows 8.1, for classification of landsat 5-7 image that contains hilly mountains with dense forest and 60% area are plains. I am classifying through Semi-...
5
votes
3answers
3k views

Pixel-based and object-based classification!

I would like to understand if pixel-based classification algorithm (e.g. Maximum Likelihood classification ) can be used for object-based classification (i.e. after a segmentation procedure). On the ...
5
votes
7answers
8k views

Failed to create signature file

I've no clue how to solve this issue in the exercise that I'm trying to perform. The point where I'm stuck is 4. "Create signature file as LandsatCompS.sgs". I've done what it says in the exercise. I ...
5
votes
1answer
432 views

Land Use classification and canopy cover using LT8 imagery and ground truth points in QGIS

I am trying to run a land use classification with QGIS on LANDSAT8 imagery to classify the various land uses within an area of northern Vietnam. I want to distinguish between primary forest, ...
5
votes
1answer
378 views

Using original Landsat multispectral image or pan-sharpened image in land cover classification?

I am currently creating land cover maps of a number of national parks across Asia from Landsat 8 imagery and also later from SPOT imagery. I plan to use supervised classifications in ERDAS IMAGINE and ...
5
votes
3answers
1k views

Differentiating bare soil and urban areas in Landsat 4-5 land cover classification?

I am trying to classify a Landsat 4-5 image using the semi automatic classification plugin (QGIS). I always get misclassifications between bare soil and urban areas as they have similar spectral ...
4
votes
1answer
254 views

Finding high-resolution land cover data for Taiwan?

So far, the best data I've found is from Globeland 30 (30 m), but the data for Taiwan is not very discriminant in partitioning the landscape. Does anyone know of better resolution data?
4
votes
1answer
1k views

Looking for example of a Random Forest tutorial to estimate spatial distribution

Could anyone point me to a Random Forest tutorial for predicting a spatial random variable? Or an easy dataset to try to work through. For Decision Trees and Random Forests, I found some very good ...
4
votes
1answer
772 views

How to extract impervious areas from Landsat data?

I'm working with multi-temporal datasets from Landsat (Landsat 8 & Landsat 7 & Landsat 5) and I tried to extract impervious areas, more exactly urban areas, but I can't obtained results very ...
4
votes
1answer
100 views

Classifying areas in scanned maps (not by colors but by pattern)

I have old land-use maps in a scanned format. I am trying to obtain proper land-use maps from it, similar to what is decribed here: Comparing areas in scanned historical land use maps using QGIS?. The ...
4
votes
0answers
625 views

How to create raster attribute table to a raster data using gdal python?

I classified a remote sensing data and saved it as a raster using Gdal python. I want to create a raster attribute table for this classified result.. my classified raster has five classes with 1,2,3,4,...
3
votes
2answers
136 views

Converting output of crosstab() in R to raster; from classified raster images to show overall land cover change in different classes?

I have two classified landsat images from 2014 and 2018 both of them containing 6 classes including urban,forest,barren etc. In order to see how each pixel's class changed or remained same from ...
3
votes
2answers
111 views

Works (publicly available) combining LUCAS with other European land data bases?

EUROSTAT provides the LUCAS dataset, a multi-purpose survey on the state and the dynamics of changes in land use and cover in the European Union. I wonder if there are any land classification ...
3
votes
1answer
85 views

Simple land classification (urban, suburban, rural) using polygons in MapInfo?

I have a large number of polygons which I need to classify as either rural, suburban or urban. These polygons represent wireless coverage for a cellular network. What I would like to achieve is a ...
3
votes
1answer
560 views

Classifying raster that takes neighbours into account?

I am working on classifying forest types using Sentinel-2 satellite imagery (10-m resolution; band-2, band-3, band-4 & band-8). I have ground-truthed field data as a training set. I want to set a ...
3
votes
1answer
1k views

Accuracy assessment in R - Calculation of User Accuracy

I want to assess the accuracy of the land cover classes classified by supervised classification of Landsat images. As reference data I use the aerial photography. I sampled the classified Landsat ...
3
votes
1answer
489 views

ENVI 5.0 Applying one ROI on various images

I'm comparing different classification methods (parallelepiped & max likehood) with ENVI 5.0 Classic. I'm supposed to use the same ROI from one image on various images and validate the ...
3
votes
1answer
356 views

SAGA 2.2.5 Problem Object Based Image Segmentation

Every time I use the Object Based Image Segmentation with Landsat 8 data I get a segmentated image which looks like a spider's web. The image contains no 0 values. Anyone has a idea how to fix this?
3
votes
1answer
197 views

Temporal spectral analysis in order to differentiate agricultural/croplands from natural/semi-natural grasslands using remotely sensed data

I am working on a critically endangered bustard species in India (Houbaropsis bengalensis). I need to prepare a land cover map of its 'suitable' grassland habitat across its distributional range. I ...
3
votes
0answers
196 views

Setting CRS automatically on Raster using QGIS? [duplicate]

I'm currently working with the Semi-Automatic Classification Plugin to help ID agricultural plots. However, when I attempt to set up the training I am given the error message. Error [61]: ...
3
votes
2answers
2k views

Orfeo Toolbox (OTB) KMeans classification issues QGIS 2.4

I am having trouble processing an image through the Unsupervised KMeans image classification in the OTB Toolbox of QGIS 2.4. I have a .tif image in the Input Image box and keep all the defaults. When ...
3
votes
0answers
841 views

Decision tree classifying of satellite image in R?

I want to classify satellite image in R using RWeka classifier, J48. I have a CSV file with the classes required, and raster data loaded in R. I am able to make the tree, however, I am not able to use ...
2
votes
3answers
4k views

Global shapefile of biomes/ecoregions?

I'm looking for a shapefile with this kind of information, only at considerably higher detail. In North America, ecoregions are classified by levels and grouped by vegetation type at much higher ...
2
votes
1answer
1k views

Using Erdas for land cover land use change detection

New to Erdas but I have to do a project and I have chosen to do a landcover land change detection. I have two Landsat 5 images, five years apart from each other. What is my next step? I imagine I ...
2
votes
1answer
35 views

Do I need to perform any corrections on Level-2 Landsat imagery?

My objective is to perform a land cover classification with multiple scenes over historical imagery (one year every decade). Most of the imagery I have downloaded is level-2 imagery. From my ...
2
votes
1answer
2k views

Accuracy assessment using Google Earth Engine?

I'm using Google Earth Engine for Land Cover change detection, I would like to know whether we can generate Error Matrix (Accuracy Assessment) for a classified image in Earth Engine or not?
2
votes
1answer
385 views

Export Google Earth Placemarks to shapefile

We were provided with a few geotagged photos, from those photos we were expected to mark more classification points around the region for the classes like water, built-up and barren land. I was able ...
2
votes
2answers
266 views

Converting data from geodatabase to latitude and longitude format

I am computer science student with no experience in Geographic information systems. I am trying to convert a geodatabse National land cover database to a latitude and longitude format. This database ...
2
votes
1answer
172 views

Maximum likelihood classification, Landsat: Why to exclude thermal band?

(transfered from https://stackoverflow.com/questions/39348977/maximum-likelihood-classification-landsat-why-to-exclude-thermal-band) I search for an argument (which I could cite, ideally) to support ...
2
votes
3answers
111 views

substitute for landsat 7 for land classification?

I am doing a project where I need to do a land classification for a forest reserve in Honduras. The dates I need are 2005, 2010, and 2015. I'm good for 2015 with LS8, but I am having difficulty with ...
2
votes
1answer
275 views

vegetation classification from only the panchromatic band

I am mapping mangroves over a period of several years using satellite imagery. I use QGIS semi automatic classification plug in. Supervised classification (maximum likelihood) as I can visually ...
2
votes
1answer
126 views

Surface reflectance product - do I always need it?

There is a neat Surface Reflectance product of Landsat imagery. I know the difference between SR and raw products: SR presents calculated values, that are supposed to represent state of the Earth ...
2
votes
1answer
126 views

Differentiating between Water and Built-Up pixels in ArcGIS Desktop?

I am classifying an imagery that has 3 bands i.e., NIR, Red, and Green band. While classifying I am not able to differentiate between Water and Built-up pixels and there is lot cross contamination ...
2
votes
1answer
116 views

Why do some tools / scripts not open for use in the ArcGIS?

I am using the Image Classification toolbar to classify a composite LANDSAT image and every time I go to the "classification" drop down and chose the "Iso Cluster Unsupervised Classification" option ...
2
votes
1answer
498 views

Performing Random Forest using EnMap Box?

I am new to the software EnMap Box that incorporates Random Forest (RF) as one of its capability. To learn the Enmap, I followed the RF tutorial provided online. My goal is to use RF as a tool to ...
2
votes
1answer
100 views

Adding new feature class to already classified image in ArcGIS Desktop?

I have at hand this already classified image with 8 vegetation classes. Now I would want to change a part of existing vegetation class to a NEW vegetation class, making it 9 classes. I do not want ...
2
votes
1answer
1k views

How to add polygon layer into raster data?

I performed a supervised land-use classification with Erdas. Landsat data was used in ArcGIS to Digitize urban areas as polygon shapefile. I want to insert these polygons into the land-use raster data....
2
votes
1answer
968 views

Running Random Forest Classification on WorldViev-2 image in R - problem

I have a problem with performing RF in R for a WorldView-2 Scene. I've never ever before used R for remote sensing classification, so I simply followed what is written here. I've loaded scene (8-band ...
2
votes
2answers
776 views

How to manually reclassify a contiguous region of misclassified pixels?

The attached image is the result of an image segmentation algorithm on high resolution imagery. The smaller clusters of pixels represent trees and brush and the larger cluster of pixels (marked with ...
2
votes
0answers
186 views

Image classification: separating pine forest, lowland and upland hardwood

I want to classify 20 feet-resolution 4-band leaf-off image into lowland hardwood, upland hardwood, pine trees, and other (bare ground, water, roads etc). I am thinking to use randomForest package in ...
2
votes
2answers
1k views

Extracting Metadata of a GeoTiff image

I am working on Landsat 8 satellite image and want to perform land cover classification for a particular region Preferred software tool is R I have formed a RGB image from the satellite data and now ...
2
votes
0answers
244 views

How to visualise change matrices over time

i've hit a bit of a tricky visualisation issue; I am quantifying some land use and land use change (LULUC) over a number of years. Typically, for data going from year to the next, a land change ...
2
votes
0answers
83 views

LULC using SAR data

I have a Geocoded SAR data with me. I have to perform LULC classification. I have been given a shapefile (vector data) with the different LULC categories of the region. The region is mainly composed ...
1
vote
3answers
109 views

What are the white grids at 9.6953038715817,98.576672019046 in Google Maps?

A friend asked me to help interpret the white grids at 9.6953038715817,98.576672019046 in Google Maps. In satellite image the grids are connected to rivers flowing into the Andaman sea. Most of the ...
1
vote
1answer
238 views

Low Recall for Radar Image Flood Classification

I am following the example here to learn how to classify flood images. I am using a single band of the Sentinel-1 radar imagery. I am able to build and train my model without trouble. The problem is ...