Let's plAIy - Object detection with Snap!, Tello Drone and NVIDIA Jetson

Talk
Schedule

Presented by:

Harley Lara

from Rhine-Waal University of Applied Sciences - EOLab

I like to build stuff 😁

Ilgar Rasulov

from Rhine-Waal University of Applied Sciences (Hochschule Rhein-Waal, HSRW)
<p>Ilgar is a master student at [Rhine-Waal University of Applied Sciences](https://www.hochschule-rhein-waal.de/en)(HSRW).</p> <p>He is busy with research tasks in the field of Data Science, Machine Learning and Artificial Intelligence. Before joining HSRW, he worked for several years as an ERP programmer and database manager for corporate clients.</p> <p>At HSRW, he is working with mini drones and Jetson computers. There are finished projects of Computer Vision applications, drone control...

Rolf Becker

from Rhine-Waal University of Applied Sciences (HSRW.eu)
<p><strong>Harley, Ilgar, and Ali</strong> are my students who are the creators of our contributions to SNAP!Con 2022. <strong>We are presenting together!</strong></p> <p>Rolf has been a professor for <strong>environmental physics</strong> at <strong>[Rhine-Waal University of Applied Sciences (HSRW)](https://www.hochschule-rhein-waal.de/en)</strong> since 2010. </p> <p>He received his diploma in physics from the University of Bonn and his [PhD in hydrology](https://primo.bibliothek.kit.edu/...

Ali Farzizada

from from HSRW EOLab

Ali is a student at [Rhine-Waal University of Applied Sciences (HSRW)] (https://www.hochschule-rhein-waal.de/en). He is currently a team member in [Earth Observation Lab (EOLab)] (https://wiki.eolab.de/doku.php).

Volunteer Hosts
Thanks for helping with Snap!Con 2022!

Brendan Henrique

REPLACEMENT Please note that this event replaces Introduction to the mathematics of Machine Learning in Snap!

Presentation
Open in a new tab

Snap! and AI

The talk will follow the process of classifying an image based on Snap! programming, sending it to the Jetson nano to analyze the image and reading it back to Snap for display and interaction, by tracking objects and following objects.

Snap! is used to take video frames from the drone's cam. These frames (pictures) are transmitted to the DetectNet server. This backend object detector reports the bounding box, the object type, and the confidence level for each identified object on the image back to Snap! This information is overlaid with the picture in Snap! This object metadata can be used by Snap! to control Tello minidrone and Jetbot.

Date:
2022 August 5 - 12:40 PDT
Duration:
20 min
Room:
Room 3
Conference:
Snap!Con 2022
Type:
Talk