andre van calster
  • Male
  • Gent,O.Vl.
  • Belgium
Share
  • Blog Posts (10)
  • Discussions
  • Groups
  • Photos
  • Photo Albums
  • Videos
 

andre van calster's Page

Latest Activity

andre van calster commented on andre van calster's blog post improved inference speed on rpi3 using Intel's NCS1
"A faster inference is achieved using Intel's NCS2"
Oct 23
andre van calster commented on andre van calster's blog post improved inference speed on rpi3 using Intel's NCS1
"Thx Rana. There is a short wiki (on my git page, tab wiki) describing my project. I included a link to this wiki in the README.md file."
Oct 15
Rana commented on andre van calster's blog post improved inference speed on rpi3 using Intel's NCS1
"Great efforts n great results indeed ! There is no wiki on the git page which you should do asap, it should include wiring diagram, BOM and more which you think, is required for anyone interested to test it."
Oct 15
andre van calster commented on andre van calster's blog post improved inference speed on rpi3 using Intel's NCS1
"thx"
Oct 14
Andreas Gazis commented on andre van calster's blog post improved inference speed on rpi3 using Intel's NCS1
"Very nice, I love watching your videos."
Oct 13
andre van calster posted a blog post

improved inference speed on rpi3 using Intel's NCS1

By using Intels OpenVINO and neural computing stick (NCS1) the inference speed of my neural network is increased from 5 frames per second (fps) to 20 using a RPI3. This enabled a far better obstacle avoidance performance of my drone. More info at https://github.com/avncalst/drone_cnn.See More
Oct 13
andre van calster posted a blog post

VTOL testflight

Simple testflight of my E-Flite Convergence equipped with a pixracer flight controller complemented with a "sbus to pwm" home-made circuit to extend the number of servo outputs. Flight stack: Ardupilot Quadplane; Flight mode: loiter.See More
Jul 2

Profile Information

About Me:
Retired prof. in (micro)electronics
Please tell us a bit about your UAV interest
Like building, designing electronic sensor modules. Today's project is designing and building a quadcopter.
Hometown:
Gent, Belgium

1st quadcopter

I bought an Frsky DF 2.4Ghz Combo Pack and dismantled the transmitter package and built my own transmitter as shown.

Apart from the DFT 8-channel  transmitter,  the RC Tx/Rx unit has an own built board with 2 psoc1 mcu’s from Cypress for generating the ppm signal, reading the sticks position and  BT pc communication.

Milling of pcb

A python program controls the settings of the RC Tx/Rx unit and displays the telemetry data

The different parts of the quadcopter are milled in plastic and aluminum. The flightcontroller is the wellknown KK2.0.

Testflights were successful and I gained a lot of experience from this 1st quadcopter.

Andre van calster's Blog

improved inference speed on rpi3 using Intel's NCS1

Posted on October 13, 2019 at 4:52am 5 Comments

By using Intels OpenVINO and neural computing stick (NCS1) the inference speed of my neural network is increased from 5 frames per second (fps) to 20 using a RPI3. This enabled a far better obstacle avoidance performance of my drone. More info at https://github.com/avncalst/drone_cnn.

VTOL testflight

Posted on July 2, 2019 at 9:00am 0 Comments

Simple testflight of my E-Flite Convergence equipped with a pixracer flight controller complemented with a "sbus to pwm" home-made circuit to extend the number of servo outputs. Flight stack: Ardupilot Quadplane; Flight mode: loiter.

Convolutional Neural Network (2) for advoiding obstacles

Posted on July 31, 2018 at 12:49am 1 Comment

By changing the CNN of my previous post CNN (1) into a multi-classification CNN (fly, go left, go right, stop) and adding an appropriate multi-thread python dronekit script, my drone…

Continue

obstacle avoidance using a convolution neural network

Posted on March 12, 2018 at 5:30am 16 Comments

Recently I started working on convolutional neural networks (cnn) for obstacle avoidance. With the help of "DroNet" from ETH Zurich and the "Deep Learning for Computer Vision" book from Adrian Rosebrock, I managed to build my first cnn algorithm for obstacle avoidance. The cnn module is written in python, using a keras…

Continue

Comment Wall

  • No comments yet!

You need to be a member of DIY Drones to add comments!

Join DIY Drones

 
 
 

© 2019   Created by Chris Anderson.   Powered by

Badges  |  Report an Issue  |  Terms of Service