Differences

This shows you the differences between two versions of the page.

--- snapcon2022:presentation-notes [2022/08/01 15:07] – created shreya
+++ snapcon2022:presentation-notes [2022/08/01 20:19] (current) – [Object Detection: Follow an Object with Drone (Ilgar, 3 mins, with Alonzo pilot)] rolf001
@@ Line 1: / Line 1: @@
-Introduction
+====== Workshop Notes ======
--Image Classification
+===== Preparation / Prerequisits =====
--Object detection
--Mini drones with OD
-Hands On
+  * Download ...
+  * Install ...
+  * Print ...
--Connect SNAP to the web server
+===== Introduction =====
--Image classification game
-Reflection
+  * The work of the EOLab Team -> Current state of development
+  * Image Classification
+  * Object detection
+  * Mini drones with OD
+===== Hands On =====
+  * Connect SNAP to the server in Nvidia Jetson
+  * Image classification game
+  * Object Detection ??
+===== Reflection =====
+====== Main Achievements (internal discussion) ======
+===== SNAP! and Mini-Drone (Harley, 3 mins, live, with Alonzo pilot) =====
+  * Tello SNAP Backend (Javascript backend, communication software interface, Wifi, client, binding to IP address), URL, eolab.de github
+    * One drone has a default IP, it is in "station" mode (the drone is AP, AP mode), 192.168.10.1
+    * Tello AP mode (client to Wifi), necessary for more than one drone in network and/or interaction with Jetson
+  * Tello SNAP! category (collection of SNAP! Javascript blocks), websocket interaction with the interface talking to the drone
+  * https://wiki.eolab.de/doku.php?id=drones:mini_drones:snap_tello
+===== Jetbot and Object Detection with SNAP! (Ali, 3 mins, with Alonzo driver) =====
+  * Object follower
+  * Jetbot Camera
+  * SNAP! is running remotely, could be running on Jetbot
+  * DetectNet (SSD-MobileNet V2, CoCo Dataset, 91 Classes)
+  * Closed Loop Control
+  * TODO: Short video!
+===== Object Detection: Follow an Object with Drone (Ilgar, 3 mins, with Alonzo pilot) =====
+  * Based on Harley's presentation on Tello SNAP! interaction
+  * New aspect: Object detection, Jetson
+  * Challenges
+    * Video stream from Tello drone to SNAP! (25 fps)
+    * Video stream from SNAP! to Jetson (extacting stage in base64 format, send message, wait response, sequential, 7 fps)
+    * Receive response from Jetson to SNAP! (bounding box, class label, coordinate transformation to the stage)
+  * Frame rate incl. analysis is 7 fps
+  * Problem (not serious): Realtime delay (latency) within the Tello drone video stream!
+  * TODO: Short video!