andre van calster
  • Male
  • Gent,O.Vl.
  • Belgium
Share
  • Blog Posts (7)
  • Discussions
  • Groups
  • Photos
  • Photo Albums
  • Videos
 

andre van calster's Page

Latest Activity

andre van calster commented on andre van calster's blog post obstacle avoidance using a convolution neural network
"During training of my CNN I focused on avoiding persons. Static tests at the MCCB club (Charente Maritime – France) showed that my CNN-drone decided to stop at 5m. Dynamic tests in Loiter mode flying at 1.7-2.3 m/sec confirmed that my drone…"
Apr 18
Patrick Poirier commented on andre van calster's blog post obstacle avoidance using a convolution neural network
"Bonjour André, That is quite good !!  It makes the concept a real time avoidance system, even without the Movidius. The gain with Movidius  (5X) is less than what Intel's Marketing  is pretending with... ''one…"
Apr 12
Andreas Gazis commented on andre van calster's blog post obstacle avoidance using a convolution neural network
"Wow, this sounds seriously cool. I would love to see how aggressive flying it can handle."
Apr 11
andre van calster commented on andre van calster's blog post obstacle avoidance using a convolution neural network
"@ Mike Isted: Thx @ Patrick  Poirier I optimized my architecture and compared the average processing time Tav of one video frame on RPI3 with and without Intel's Movidius. The results obtained are: Tav (without Movidius) = 0.17 sec, Tav…"
Apr 11
Mike Isted commented on andre van calster's blog post obstacle avoidance using a convolution neural network
"Hi Andre, Excellent work, well done. I am slowly heading in a similar direction and am migrating from RPi/Picam to Jetson TX2/Realsense.  I am also moving to Mavros. As with you, I have learnt much from Adrian Rosebrock and his courses. Happy…"
Apr 9
andre van calster commented on andre van calster's blog post obstacle avoidance using a convolution neural network
"@Patrick Poirier Bonjour Patrick I still have to perform additional testing to get all the characteristics. This will be done In France during Eastern holidays. On my RPi3 I measure a cycle time of 0.2 sec (5Hz)."
Mar 15
Patrick Poirier commented on andre van calster's blog post obstacle avoidance using a convolution neural network
"Bonjour André, Looking at the video , I see you are using dronet  https://github.com/uzh-rpg/rpg_public_dronet for training on a fly/stop scenario which is the best strategy for testing. The speed seems pretty good on the PC (I would say…"
Mar 14
andre van calster commented on andre van calster's blog post obstacle avoidance using a convolution neural network
"@Auturgy I intend to publish my code at GitHub once I have cleaned up my code."
Mar 14
Andreas Gazis commented on andre van calster's blog post obstacle avoidance using a convolution neural network
"@ Hugues. Well, by and large CNNs are bundled under deep learning, which is bundled under machine learning, which is bundled under AI. This type of diagram gets thrown around a lot: We can argue definitions all we want but we don't have…"
Mar 14
Auturgy commented on andre van calster's blog post obstacle avoidance using a convolution neural network
"Great work! Is your plan to publish the code?"
Mar 13

MR60
Hugues commented on andre van calster's blog post obstacle avoidance using a convolution neural network
"Very nice but stop saying this is AI. This is not an artificial intelligence, but a pattern/image recognition or expert system."
Mar 13
andre van calster commented on andre van calster's blog post obstacle avoidance using a convolution neural network
"Thx for your interest. I only use Open CV captured images from my PiCam video stream I use dronekit version 2.9.0 I measured a cycle time (time between two consecutive images) of about 0.2sec Some more extensive testing will done during Eastern,…"
Mar 13
Andreas Gazis commented on andre van calster's blog post obstacle avoidance using a convolution neural network
"This is seriously impressive, well done! A few questions: 1 - The network is only fed individual still images, there is no comparison between previous and current image, correct? 2 - Is this running on the original Dronekit or DKPY 2.0? 3 - How…"
Mar 12
andre van calster posted a blog post

obstacle avoidance using a convolution neural network

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 module with tensorflow backend. I included my cnn algorithm in a dronekit script. By sending mavlink distance messages to the flight controller in loiter or altitude hold flight…See More
Mar 12
andre van calster commented on Chris Anderson's blog post Teaching drones to fly in cities by emulating cars and bikes
"congrats"
Jan 28

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

obstacle avoidance using a convolution neural network

Posted on March 12, 2018 at 5:30am 13 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

My XJ470 rebuilt

Posted on April 17, 2017 at 1:40pm 4 Comments

best viewed with 720p HD settings

This winter I rebuilt my XJ470: added a PiZero with a Picam. This PiZero functions as a companion computer with a python dronekit and a WiFi access point enabling a mavlinkbridge. Hence an android tablet, running Tower, can be connected to this WiFi access point for…

Continue

testflight xj470

Posted on September 12, 2015 at 2:42am 2 Comments

For bench marking my own developed flight controller, I built a Quanum XJ470 drone with a DroPix (Arducopter/PixHawk) flight controller. Some additional features: esc AFRO 30A; motors: SunnySky 980 KV; props 10 x 4.5. My first testflight shows that the drone with the DroPix flies great.

comment on complementary filtering

Posted on May 6, 2015 at 9:10am 2 Comments

Complementary filters enable sensor fusion, are easy to implement and eliminate integrating errors from gyro’s or accelerometers. Normally complementary filters are discussed in the frequency domain.  Using simple Python code a 1st order linear complementary filter for determining the…

Continue

Comment Wall

  • No comments yet!

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

Join DIY Drones

 
 
 

Groups

Season Two of the Trust Time Trial (T3) Contest 
A list of all T3 contests is here. The current round, the Vertical Horizontal one, is here

© 2018   Created by Chris Anderson.   Powered by

Badges  |  Report an Issue  |  Terms of Service