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