Today we are going to describe a fun project we built at Preste, using Nvidia Jetson Xavier NX, Deep Learning and Computer Vision. In the...

In our first article related to the topic of DeepFakes, we have reminded our viewers on the dangers of these technologies, the various attempts from the industry to tackle the issue (including via a recent Kaggle competition launched by a consortium of major players such as Facebook) and our own idea to explore the topic further, by leveraging segmentation neural networks to not only recognize but also characterize the fakes, through the localization of modified areas. From

Deepfake comes with creative, fun but also more worrying applications. How good are machines at detecting them today ? Let's take a look.

Lately, we have been working at Preste on a project where we needed to build a computer vision solution for real-time processing and tracking of fast-moving objects . We used a 120 frames per second video camera and chose the NVidia Jetson TX2 platform to host our solution. As our algorithm strongly depended on fast tracking/detection capabilities there was a need for an efficient and fast deep neural network. In this post, we would like to share with you how we succeded i