The goal of the FlyWave team of UAVs@Berkeley is to develop a drone that can maneuver autonomously using computer vision and deep learning to detect hand gestures.
- Alex Chan (Project Lead)
- Timothy Liu
- Raymond Gu
- Nick Mecklenburg
- Person classification
- Hand gesture detection
- Person movement tracking
- Gesture detection
- Using gestures to move the drone
- Parrot Bebop 2
- Packages: Tensorflow, Keras, OpenCV, and PyParrot (dependencies described here).
- Connect to the Bebop's Wifi.
- Before running any scripts, stand clear of the drone's takeoff area.
- In terminal, run:
python drone_movement.py
- Stand in front of Bebop, and make gestures as desired. Right arm out: Move bebop in an arc to the right Left arm out: Move bebop in an arc to the left Right arm up: Land drone Left arm up: Flip
Credit to: PyParrot
Copyright for object detection: See LICENSE for details. Copyright (c) 2017 Dat Tran.