Tag: Deep Learning

12 November 2018

How to implement a geospatial data pipeline for deep learning

After focusing on street-scene images, our deep learning framework is currently exploited in order to analyze aerial images and building footprints with semantic segmentation algorithms. We recently extend these last works by investigating an instance-segmentation use case. Context In parallel to the last FOSS4G conference at Dar es Salaam (Tanzania), WeRobotics recently organized the Open
7 May 2018

Deeposlandia 0.4 has been released!

On a previous article published on this blog, we introduced our work dedicated to convolutional neural network. We are now happy to announce the 0.4 release of this R&D project! What’s new? Until the last released version (0.3.2), neural networks were built with the TensorFlow library. The major modification comes with the transition to the
25 October 2017

Detecting objects starting from street-scene images

Exploiting artificial intelligence within the geospatial data context tends to be easier and easier thanks to emerging deep learning techniques. Neural networks take indeed various kinds of designs, and cope with a wide range of applications. At Oslandia we bet that these techniques will have an added-value in our daily activity, as data is of