Thank you for pointing me to the project. This is exactly what we are trying to achieve. Well, we have not reached to the stage where we will use neural nets. For our project we have been provided with geo-tagged images of crop fields as our ground data. We are using lansat-8 and sentinel images to build a model which would then predict the area under cultivation. We are trying to achieve this for 1 crop only for a small portion of land (district or taluk).
On Saturday, March 25, 2017 at 12:00:34 AM UTC+5:30, Arun Ganesh wrote: > > If you are interested in getting into neural networks > <http://neuralnetworksanddeeplearning.com> for visual recognition > <https://cs231n.github.io/convolutional-networks/> in satellite imagery, > maybe this project might be a good start to try out > https://github.com/rodowi/unmapped > > Its an attempt by a colleague from Mapbox to detect roads on satellite > imagery that are not mapped on OSM > <http://www.openstreetmap.org/#map=5/21.494/80.244>. > > Would also be great to hear more about your agricultural project. > > Arun > -- Datameet is a community of Data Science enthusiasts in India. Know more about us by visiting http://datameet.org --- You received this message because you are subscribed to the Google Groups "datameet" group. To unsubscribe from this group and stop receiving emails from it, send an email to datameet+unsubscr...@googlegroups.com. For more options, visit https://groups.google.com/d/optout.