7 votes
Accepted

Performing deep learning land cover classification using R?

The use of tensors in the evolution of deep learning methods has notably pushed the field of machine learning forward. This is why there is such buzz over Googles Tensorflow approach. It also provides ...
user avatar
4 votes

Pre-trained transfer learning models for satellite image classification

You can use the pre-trained models (tensorflow) from a remote sensing dataset, here is the golden standard for this domain: http://bigearth.net/
user avatar
4 votes

Deep Learning in QGIS: installing Tensorflow

Solved my problem. For reference: 1- pip install tensorflow-gpu in the Python 3.7 env of QGIS, be sure to use the py3_env command. 2-Be sure h5py is v2.9. I had to force this. This will prevent ...
user avatar
3 votes
Accepted

Looking for a deep learning platform for image recognition, preferably in QGIS

As far as I know, QGIS have not developed a framework yet to integrate Deep Learning into the workflow as ArcGIS did (see here): https://pro.arcgis.com/en/pro-app/help/analysis/image-analyst/deep-...
user avatar
3 votes

How were walkways found and added to Google Maps or OSM?

In this case the source is Open Street Map - you can get the history for the paths (walk ways). Example: https://www.openstreetmap.org/way/4708373/history you can find out that it was created 13 ...
user avatar
  • 48.6k
2 votes

Performing deep learning land cover classification using R?

How to implement Deep Learning in R using Keras and Tensorflow is a link where they use R for deep learning. In this tutorial they classify images to a certain class, I think you are interested in ...
user avatar
  • 345
2 votes

Can the ArcGIS Pro deep learning tools detect objects in non-nadir imagery?

In Esri's world non-nadir imagery is referred to as oriented imagery. This video on Driving Intelligence from Video and Oriented Imagery at Scale Using AI in ArcGIS (presenters David Yu, Shairoz ...
user avatar
  • 2,084
1 vote
Accepted

Exporting training data for deep learning in ArcGIS Pro with a fixed buffer area around each polygon

This is just an idea, so untested. The Export Training Data For Deep Learning has the parameter input_mask_polygons may be you can create your Bounding mask? You could create the your bounding boxes ...
user avatar
  • 38.9k
1 vote

How to estimate overlap of certain pixel colors in a raster image and a linestring shape added on top of it?

A simple approach would be to use NAIP imagery to calculate NDVI with the red and NIR (near infrared) bands and set a threshold over which you consider the electrical feeders to fall in a vegetated ...
user avatar
  • 23
1 vote

Error when training data for Deep Learning

Did you correctly install deep learning packages? Because I received same error message after I updated my ArcGIS Pro 2.6 from 2.5. I reinstalled the deep learning packages and it was solved. When you ...
user avatar
1 vote

How were walkways found and added to Google Maps or OSM?

I would say most, if not all, of openstreetmap walkways are manually added from tracing satellite imagery or GPS traces. Iv'e never heard of anything automated regarding walkways in openstreetmap. ...
user avatar
  • 111
1 vote
Accepted

ArcGIS Pro 2.5.0: Trouble with using new deep learning tools for object detection - Failed to execute (TrainDeepLearningModel)

The solution was to extract the first three bands (RGB bands), as I had a 16-bit unsigned orthomosaic with 5 bands. I extracted the first three bands (RGB bands), and then compiled them back into an ...
user avatar
  • 463
1 vote

Pre-trained transfer learning models for satellite image classification

Pre-trained models generally rely on the pre-processing of the imagery being very consistent. As such, it is generally not feasible to do transfer learning with a remote sensing based classification ...
user avatar

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