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.

learn more… | top users | synonyms

26
votes
7answers
4k 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 ...
19
votes
3answers
6k views

How to perform Random Forest land classification?

This is a follow-up to a previous post: Machine Learning Algorithms for Land Classification. It seems that the Random Forest (RF) classification method is gaining much momentum in the remote ...
10
votes
3answers
3k views

How to reclassify a very large land cover dataset?

Consider the NLCD2001 Land Cover dataset for Alaska (download link). I need to reclassify this dataset so that only pixels of value 41, 42, and 43 are preserved; all other pixel values should become ...
8
votes
1answer
208 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 ...
5
votes
1answer
812 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
218 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
3answers
1k 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 ...
4
votes
1answer
2k 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 ...
4
votes
0answers
39 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 ...
3
votes
2answers
90 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
233 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 ...
3
votes
1answer
70 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
1answer
59 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: How to compare areas in scanned historical land use maps. The ...
3
votes
0answers
74 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 ...
3
votes
2answers
1k 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
380 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,...
2
votes
3answers
42 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
2answers
136 views

Feature extraction in remote sensing! [closed]

Which are the most common features in order to perform a supervised classification in remote sensing? Furthermore anyone worked with SAR features? Which are the most commonly used? Can anybody suggest ...
2
votes
1answer
32 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
425 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. My question is: what is my next step? ...
2
votes
2answers
334 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
28 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?
2
votes
1answer
274 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 ...
2
votes
1answer
516 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
3answers
2k views

Failed to create signature file

I need some help, because I've no clue how solve this issue 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 ...
2
votes
2answers
454 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
34 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?
2
votes
0answers
131 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
75 views

How to add new feature class to already classified image

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
0answers
76 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
389 views

Decision tree classification 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 ...
1
vote
3answers
99 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
437 views

Performing image segmentation in QGIS?

I have been trying to learn to work with QGIS (open-source GIS software) through some tutorials available online for classification of image for land cover. These tutorials used a dataset from Landsat ...
1
vote
1answer
71 views

How do you preform multi spectral image classification on non Landsat images in QGIS

My aim is to classify vegetation types, using areal/ satellite imagery, in a small (4km^2) area of the North York Moors (UK). This area contains two small rivers and their catchment areas; one of the ...
1
vote
1answer
220 views

How to differentiate between land and sea in python?

I'm going to plot some positions of ships, and thus see which areas (out at sea) where there is no vessels, however, if I do this in an ordinary geographical area defined by a square, all the land ...
1
vote
2answers
848 views

Classification, change detection and NDVI using landsat 2 (MSS), landsat 5 (TM) and Landsat 7 (ETM)

I have 3 Landsat images for the same area. One in 1972 (landsat 2 mss), one in 1996 (landsat 5 TM) and one in 2010 (landsat 7 ETM). I would like to detect changes in land cover and create diachronic ...
1
vote
1answer
614 views

How to calculate raster data in vector area?

I have two layers. One is a layer of USA ecoregions (there are 9 ecoregions). It is not raster (so it's vector?). The other layer is the National Land Use Data set (so I know where there's agriculture,...
1
vote
0answers
60 views

Raster Calculator and Land Change with multiple classifications

I am looking at land cover data that is separated into three classes: upland, wetland, and open water. I have the data for varying years. I am interested in seeing how the land has changed over the ...
1
vote
0answers
24 views

Band Separation from regular cameras

I have removed the IR block filter from a Sony digital compact camera so it has become multispectral (in a way). In addition to that I placed a IR pass filter, so it only captures photos in the Near-...
1
vote
0answers
47 views

How to extact very narrow water linear features from GeoEye-1 image

I need to extract beaver channels from a GeoEye image (attached image). What is the best approach to automatically delineate such very narrow and not very sharp water features?
1
vote
0answers
40 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
0answers
27 views

How to classify land cover with MMU 25hac

By using the 30 meter resolution of landsat TM & ETM+ data, I want to create the land use/ land cover map. I have read in several studies to first decide about the minimum mapping unit (MMU) that ...
1
vote
0answers
52 views

How to export multiple class training data from ArcGis into R?

I want to perform some machine learning classification of images using R. I'm having issues finding out how to export my training data from ArcGis into R and I'm looking for some help. Currently I do ...
1
vote
1answer
254 views

Extraction of pixels from layerstacked NDVI image

How do I get rice pixels only from layerstack NDVI (modis) or SASI image? I also have a thematic rice image Please tell me how to do in erdas.
1
vote
0answers
116 views

How to select MODIS pixels with 80% homogeneous landcover from landsat classification?

I have a complex landcover classification for a landsat scene at 30m spatial resolution. Includes about 600 land cover classes. There is a fair amount of clumping per group. I have a MODIS EVI 16 day ...
1
vote
0answers
80 views

How to perform image classification with SemiAutomaticClassificationPlugin and BIP files?

I have multiband satellite images BIP format, Landsat TM/ETM containing 7/8 bands respectively along with a separate header file, some of them corrected by nearest neighbour classifier. I'm working ...
1
vote
0answers
103 views

Distinguish between the types of cultivated crops in remote sensing

I recently produced map of LULC but there is the difficulty of distinguishing between the types of crops. Is there a method to distinguish between the types of cultivated crops such as wheat, barley, ...
0
votes
2answers
126 views

Classification of digital orthophoto

I have digital orthophotographs from 2013 that I'm attempting to classify in an effort to extract all the cultivated/pasture land from. I'm using the "Reclassify by Ascii File" tool for this ...
0
votes
1answer
65 views

When parametric classifiers fail?

In which situations are statistical assumptions (e.g. multivariate normal distribution within spectral classes) for parametric classifiers (e.g. maximum likelihood ) not valid for land-cover ...
0
votes
1answer
524 views

What software programs can run a supervised classification on an image segmented into objects?

I am trying to run a supervised MLC classification on a multispectral remotely sensed image, however, I want the image to be classified using a shapefile of segmented image objects (as opposed to the ...