The Trendy application is being retired in the new year. The new web application, ThingSpeak, offers similar functionality. We recommend that active Trendy users who are looking to create new trends use ThingSpeak. To begin collecting your data in ThingSpeak, please read the tutorial : ThingSpeak for Trendy users. Although Trendy no longer allows the creation of new trends, the application will still remain accessible until January 13, 2016. Until that date, you can view your current trends and download your data. After that date, your data will no longer be accessible. Thanks for using Trendy and we encourage you to check out ThingSpeak.


Tracking Snowfall with Distributed Alpine Webcams

This plot is broken.

constant =


Error using horzcat
Dimensions of matrices being concatenated are not consistent.

I am interested in tracking the snow season of my favourite ski resort in the Alps, to help get a good idea of when are the best times to go. MATLAB Trendy is a good way of tracking this kind of information on a day by day basis. However, in order to achieve this I would like to be able to analyse webcam data to measure snow coverage. Fortunately I can download these images in realtime and use a predictive model to measure the total amount of snow in each image.

For more information on how the model was trained, see the following blog post. Essentially the average red, green and blue channel information of the images is stored, and a linear model estimates the amount of snow which the image contains.

Image data is obtained from

Plot Image
redCoeff =  0.042413;
greenCoeff = -0.1688;
blueCoeff =  0.09018;
coeffs = [redCoeff; greenCoeff; blueCoeff];
constant = 4.3638

[data1821 data1820 data1822]

predictions = [data1821 data1820 data1822]*coeffs + constant
plot(time1822, predictions)


    Add Tags