Training of a deep learning algorithm for quadcopter gesture recognition
Traditional methods to control Unmanned Aerial Vehicles are unintuitive and susceptible to radio interference. Recent research has shown that hand gestures are the most intuitive method for quadcopter control. Also, deep learning in the form of a convolutional neural network is a more compatible app...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | text |
| Published: |
Animo Repository
2020
|
| Subjects: | |
| Online Access: | https://animorepository.dlsu.edu.ph/faculty_research/2852 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | De La Salle University |
| Summary: | Traditional methods to control Unmanned Aerial Vehicles are unintuitive and susceptible to radio interference. Recent research has shown that hand gestures are the most intuitive method for quadcopter control. Also, deep learning in the form of a convolutional neural network is a more compatible approach to gesture recognition than other methods. This paper presents the design, and training of a deep learning convolutional neural network for gesture recognition and tracking of a quadrotor Unmanned Aerial Vehicle. The neural network was coded in Python using the Keras library and was trained on a laptop computer. Inference was performed on a Raspberry Pi 4 computer that is intended for use as a companion computer aboard a quadcopter. © 2020, World Academy of Research in Science and Engineering. All rights reserved. |
|---|