PIXHAWK Onboard Pattern Recognition Video



This video shows the PIXHAWK onboard pattern recognition. Interested in the hardware to run it onboard? Two approaches have been implemented: One is extremely efficient and runs at 30 Hz on a Gumstix Overo (ARM Cortex-A8, Smartphone processor). This approach is based on first detecting quadrangles and then matching the objects enclosed by these. We used this approach on a Gumstix Overo onboard our PIXHAWK Pioneer Coaxial helicopter and won last years EMAV 2009 competition with it.

The second approach is more general and uses closed contours fed into a SVM. It can detect arbitrary shapes, but requires more processing power. Through our PIXHAWK middleware, the camera image can be sent to both in parallel to allow a maximum detection.

The video shows the first, highly efficient and robust approach in action:

If you have questions on the video or approach, please contact Fabian Landau.

Please note that the detection is done onboard of our coaxial and quadrotor MAVs with no external processing. The software is part of the ai_vision PIXHAWK repository and will be made available as GNU GPLv3 code.

Views: 861


Developer
Comment by Mark Colwell on August 6, 2010 at 8:46am
Work those processors! Nice fast response !
Comment by simonl on August 6, 2010 at 11:58am
V. impressive!
Comment by Darren on August 9, 2010 at 10:50am
Hmm... Could this then be used for the Ground Station system to track visually an RC model flying. Potentialy augmenting an Antenna tracker. Wonder if the zoom/focus can be computer controlled as well... (double hmmm...)
Comment by pixhawk on August 9, 2010 at 10:34pm
Not the approach in the video, but the second approach using SVMs. You can train the SVM on all sorts of orientations of the RC model in front of the sky and it'll then be able to track it, even when it clouds or other RC models get into the background. But you would need of course a pretty good mechanical tracking system.
Comment by Ron Jacobs on October 12, 2010 at 7:53pm
How many pixhawk are out there being used/tested right now?

Could you recognize and track terrain contours? Highway patterns? Symbols on rooftops? Giant barcodes?

Comment

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

© 2020   Created by Chris Anderson.   Powered by

Badges  |  Report an Issue  |  Terms of Service