Estimation of vegetated surfaces with Computer Vision: how we improved and scaled up our model
Here at nam.R, we’re putting our hard work into building a Digital Twin of the French territory. We aggregate, clean and re-organize a large quantity of data of different formats coming from many different providers.
How we improved our estimation of vegetated surfaces with Computer Vision
Here at nam.R, we’re putting our hard work into building a Digital Twin of the French territory. We aggregate, clean and re-organize a large quantity of data of different formats coming from many different providers. Among them are aerial images (geo-referenced photographs taken by an airplane), which play a crucial role and represent one of the richest sources of information of the area they describe. You’ll discover with this article how at nam.R we have improved our estimation of vegetated surfaces.
Today, we want to take you through the study of a very meaningful case for us, the detection of vegetated surfaces around buildings. In this project, we will show you how we build a dataset suited to our application and what we went through. The detection of vegetation is a simple yet powerful tool to help understand the quality of life around the populated areas.
We decided to focus on the vegetated zones’ segmentation, which means we predict a class between “vegetation” or “not vegetation” for each pixel.
Simple ideas don’t always lead to good results:
Our first idea for detecting vegetated areas consisted on a very simple thresholding of the HSV value:
HSV wheel and hues selected for vegetation detection
We could consider as vegetation pixels with a hue between 40 and 160 for example (values we chose empirically). This encompasses the yellowish greens as well as more blue-green hues. We’d need to take into account saturation and value (luminance) as well in order to consider the scene luminosity and the image’s saturation. This was our first model, which consisted basically a filter on 3 dimensions. In order to smooth out the pixel classification we run standard morphological operators, closing and opening, to help regularize the detections spatially.
Test image, filtered hue, smoothed out mask, image and detection overlap
This is a very cheap task that could make it easy to process the whole territory. However, this cheapness also makes it very unreliable. Indeed, shadows were poorly detected and the pixels classified as vegetation using such an algorithm could as well be part of a green colored roof, green shades of water or even simple chromatic aberrations in our data!
Vegetation detection through the hue value doesn’t always work
nam.R is a data & deep-tech company, specialized in geolocated intelligence, building a digital representation of the physical world. nam.R aims at providing easy-to-use and actionable data to public and private organisations to massify and optimise their actions, investments and projects.
Strictly Necessary Cookies
Strictly Necessary Cookie should be enabled at all times so that we can save your preferences for cookie settings.
If you disable this cookie, we will not be able to save your preferences. This means that every time you visit this website you will need to enable or disable cookies again.