svm satellite

Support Vector Machines – on recognizing pixel clusters in satellite data

Scikit-learn, the machine learning library built for Python over 10 years ago is an excellent resource for estimating data and can integrate into geospatial workflows. Helpfully, when choosing an estimator, scikit-learn supplies an interactive diagram to choose the best estimator for the job. One of the big things about machine learning is the need to Read more about Support Vector Machines – on recognizing pixel clusters in satellite data[…]

Earth Observation Sentinel2

Interactive Trackbar to edge detect Sentinel 2 data

The user interface in OpenCV has a Trackbar. This is a really useful feature for interacting with images. By adjusting the slider the user can manipulate the image allowing for the adjustment of threshold values until the image display is optimised. When I wrote about interactive image segmentation I noted one of the critical things Read more about Interactive Trackbar to edge detect Sentinel 2 data[…]

Beginners guide to user Interaction with OpenCV in Python

I have been working with OpenCV for a while now and I still find the speed of results very impressive. It makes for a compelling case for its use in image processing. Computer Vision, at least to me, represents such an incredible opportunity for Remote Sensing specialists as well as non-specialists. I have been meaning Read more about Beginners guide to user Interaction with OpenCV in Python[…]

Interactive Image Segmentation part 3 – Automation

This is the 3rd part in a series on interactive image segmentation. In part 1 I looked at how thresholding an image of coins has the potential to help map circular fields in the desert. In part 2 I applied this watershed algorithm to satellite data and created an output shapefile. In part 3 I Read more about Interactive Image Segmentation part 3 – Automation[…]

Interactive Image Segmentation part 2

This is the second part of a blog series on mapping circular fields. In part one I talked about the challenges for mapping in Desert environments and about how thresholding and the Watershed Algorithm can be used to detect coins – this offers a potentially useful way to map circular fields. These are a challenge Read more about Interactive Image Segmentation part 2[…]

Interactive Image Segmentation part 1

A few weeks ago I saw this tweet from UrtheCast We wish you a happy #EarthDay with this stunning #DEIMOS1 view of crop circles in the desert in #SaudiArabia! #PrecisionAg #Geoanalytics pic.twitter.com/szcSptjHMS — UrtheCast (@UrtheCast) April 22, 2017 It is a stunning image, captured by Deimos 1, of crop circles in Saudi Arabia. I really Read more about Interactive Image Segmentation part 1[…]

Sat Colours

I’ve been thinking about how colour could be displayed for a Satellite Image. The Earth is beautiful. In some software, in the legend, a Satellite image is displayed as below Image from http://webhelp.esri.com/arcgisexplorer/2500/en/legend_window.htm It does contain some useful information, ie what band is being displayed Red, Green and Blue, but it tells us very little Read more about Sat Colours[…]

EO point based unsupervised classification

With remote sensing we often talk about the 3 resolutions: spatial, temporal and spectral. In recent years a massive step change has occurred with temporal data. Even this week there has been another huge leap forward. Planet have just announced that they are to launch a world record 88 of its doves and, if successful, Read more about EO point based unsupervised classification[…]

Extracting values from satellite imagery

Last week I wrote about using Earth Observation data without ever looking at a satellite image; extracting the values from an image and then presenting the data in an informative way. Using Earth Observation data without ever looking at a satellite image Just how easy is it to extract the values from images? Sentinel 2a Read more about Extracting values from satellite imagery[…]

Processing images on the Google Cloud

October 2016 brought the announcement from Google that it had all Landsat and Sentinel data on its cloud. Amazon are also hosting all this data, ESRI are using the Amazon cloud and so are Planet (both of these for over a year). Never before has so much Earth Observation data been available to everyone. I Read more about Processing images on the Google Cloud[…]

Reclassify and Numpy

I have previously written about automatically edge detecting. Using OpenCV is a nice way of quickly running the edge detect and getting some information back about the image. You can read about the Canny edge detection algorithm here Here is how Wikipedia details the process of the canny edge detection (if you didn’t click the Read more about Reclassify and Numpy[…]

Edge detecting with Planet API

You know about planet (formerly Planet Labs), right? Their aim is to map every part of the Earth’s surface everyday using their Dove satellites. One Pixel for every area every day. Temporal data at its best! If you get an image every day and you want to monitor it (change being the obvious reason) a Read more about Edge detecting with Planet API[…]